精华内容
下载资源
问答
  • 脉冲多普勒雷达

    2014-08-30 13:38:58
    脉冲多普勒雷达》电子书。来源雷达手册。
  • 脉冲多普勒雷达的matlab仿真,包裹下变频、脉冲压缩、MTI和MTD。多普勒脉冲雷达回波仿真。产生回波,对回波进行距离压缩,进行两脉冲对消,观察运动、盲速与静止目标的对消情况。
  • 脉冲多普勒雷达简介

    2018-09-07 09:55:25
    脉冲多普勒雷达学习资源,介绍了PD雷达的地杂波谱以及不同的PRF对测速测距的影响。
  • 脉冲多普勒雷达的光学信息处理
  • 次奈奎斯特脉冲多普勒雷达的一般顺序延迟多普勒估计方案
  • LFM线性调频信号脉冲多普勒雷达matlab仿真,MTD,MTI。
  • 压缩采样脉冲多普勒雷达联合延迟多普勒估计的Cramer-Rao界
  • 具有独立测量功能的亚奈奎斯特脉冲多普勒雷达
  • 脉冲多普勒雷达测速

    2013-08-20 14:59:45
    讲述了脉冲多普勒雷达测速的原理及改进方法,还给出了测试额实验结果。
  • 通过一位采样实现超高分辨率脉冲多普勒雷达感应
  • 针对传统的压制干扰和欺骗式干扰难以对脉冲多普勒雷达产生显著干扰效果的问题,研究了一种利用数字储频技术和卷积调制方式产生灵巧噪声干扰的方法。这种干扰不但具有压制干扰的特点,还具有欺骗干扰的性质,不但在...
  • 脉冲多普勒雷达by Braden Riggs and George Williams (gwilliams@gsitechnology.com) Braden Riggs和George Williams(gwilliams@gsitechnology.com) In the world of data science the industry, academic, and ...

    脉冲多普勒雷达

    by Braden Riggs and George Williams (gwilliams@gsitechnology.com)

    Braden Riggs和George Williams(gwilliams@gsitechnology.com)

    In the world of data science the industry, academic, and government sectors often collide when enthusiasts and experts alike, work together to tackle the challenges we face day-to-day. A prime example of this collaboration is the Israeli Ministry of Defense Directorate of Defense Research & Development (DDR&D)’s MAFAT challenges. A series of data science related challenges with real-world application and lucrative prize pools. In the program’s own words:

    在数据科学世界中,当发烧友和专家都共同努力应对我们日常面临的挑战时,行业,学术界和政府部门经常发生冲突。 以色列国防部国防研究与发展局(DDR&D)的MAFAT挑战就是这种合作的主要例证。 一系列与数据科学相关的挑战,包括现实应用和丰厚的奖池。 用程序本身的话来说:

    The goal of the challenge is to explore the potential of advanced data science methods to improve and enhance the IMOD current data products. The winning method may eventually be applied to real data and the winners may be invited to further collaborate with the IMOD on future projects.- MAFAT Competition Coordinators

    挑战的目标是探索先进数据科学方法的潜力,以改善和增强IMOD当前数据产品。 获奖方法可能最终会应用于真实数据,获奖者可能会被邀请在未来的项目上与IMOD进一步合作。- MAFAT竞赛协调员

    Given the recent inception of the program, there haven’t been many challenges yet, however, there are expected to be a variety of challenges ranging from complicated Natural Language Processing puzzles to computer-vision related endeavors.

    鉴于该程序是最近开始的,因此还没有很多挑战,但是,预计会出现各种各样的挑战,从复杂的自然语言处理难题到计算机视觉相关的工作。

    One such challenge, their second one made available thus far, caught my eye. It involves creating a model for classifying living, non-rigid objects that have been detected by doppler-pulse radar systems. The challenge, “MAFAT Radar Challenge — Can you distinguish between humans and animals in radar tracks?” implores competitors to develop a model that can accurately distinguish humans from animals based on a spectrum of radio signals recorded from various doppler-pulse radar sites on various days. If you are interested in participating I recommend visiting the challenge site before reading on.

    这样的挑战之一,到目前为止已经提供的第二个挑战引起了我的注意。 它涉及创建一个模型,以对多普勒脉冲雷达系统已检测到的活的非刚性物体进行分类。 挑战“ MAFAT雷达挑战-您能区分雷达轨道中的人与动物吗? 恳请竞争对手开发一种模型,该模型可以根据在不同日子从各个多普勒脉冲雷达站点记录的无线电信号频谱,准确地将人与动物区分开。 如果您有兴趣参加,建议您访问 在继续阅读之前先挑战网站

    那么,我们正在处理什么样的数据?我们需要了解什么? (So what kind of data are we working with and what do we need to know about it?)

    Image for post
    Image for post
    An example of the data included for the competition split by Animal/Human and High/Low Signal-Noise-Ratio. The I/Q matrices have been converted into spectrograms for visualization, and the doppler readings have been added in white. As you can see there are some differences present in the files. Images provided by MAFAT. Reposted with Author’s permission.
    比赛数据包括动物/人类和高/低信噪比。 I / Q矩阵已转换为频谱图以进行可视化,并且多普勒读数已添加为白色。 如您所见,文件中存在一些差异。 图片由 MAFAT 提供 经作者许可重新发布。

    The key to developing an accurate and competitive model is to first understand the data, how it was sourced, and what it is missing. Included with the competition is 5 CSV files containing the metadata, and 5 pickle files (serializing Python object structure format) containing doppler readings that track the object’s center of mass and slow/fast time readings in the form of a standardized I/Q matrix.

    开发准确而具有竞争力的模型的关键是首先了解数据,数据来源和缺失内容。 竞赛中包括5个包含元数据的CSV文件 ,以及5个 包含多普勒读数的 pickle文件 (序列化Python对象结构格式) ,它们以标准化I / Q矩阵的形式跟踪对象的质心和慢/快时间读数

    Before we go any further it is worth breaking down a few key concepts relating to signals and the specific types of data collected. The signal readings that make up the dataset fall into two levels of quality, High Signal to Noise Ratio, and Low Signal to Noise Ratio. This reading, High SNR and Low SNR divides the set into two levels of quality, one with high clarity that hasn’t been heavily tainted by a noise generating process, and one with low clarity that has had aspects such as weather impact the quality of the reading.

    在进一步研究之前,有必要分解一些与信号和所收集数据的特定类型有关的关键概念。 构成数据集的信号读数分为两个质量级别,即高信噪比低信噪比 。 该读数分为高信噪比和低信噪比,将数据集分为两个质量级别,一个是高清晰度,没有受到噪声生成过程的严重影响;另一个是低清晰度,对天气的影响很大。阅读。

    Image for post
    KF6HI. Reposted with Author’s permission.KF6HI 。 经作者许可重新发布。

    You might be wondering why we would even choose to include low SNR readings given the impact noise has on the data, however to my surprise this data is actually quite valuable when developing an effective model. Real-life is messy, and the true reading one might expect to see will not always be high quality, hence it is important to make sure our model is adaptive and geared towards a range of data readings, not just the highest quality ones. Furthermore, we are working with a limited amount of data (which we will explore in-depth below) and hence want to utilize everything at our disposal for training the model.

    您可能想知道为什么考虑到噪声对数据的影响,我们为什么甚至选择包括低SNR读数,但是令我惊讶的是,在开发有效模型时,该数据实际上非常有价值。 现实生活是一团糟,人们可能期望看到的真实读数并不总是高质量的,因此,重要的是要确保我们的模型具有自适应性,并且适合多种数据读数,而不仅仅是高质量的读数。 此外,我们正在处理数量有限的数据(我们将在下面深入探讨),因此希望利用我们掌握的所有信息来训练模型。

    Another series of concepts worth understanding is the notion of an I/Q matrix and what a doppler reading entails. An I/Q matrix consists of an N x M matrix, in our case a 32 x 128 matrix, that stores the slow and fast signal readings as cartesian elements, where “I” represents the real part and “M” represents the imaginary part. You can picture each row of this matrix as representing a signal pulse from the source, and each column of this matrix representing a reading for returning radio waves that have bounced off objects or targets in the direction of interest. The time between pulses is “slow time” and the time between readings of said pulses is considered “fast time”, if you are still confused or further interested I highly recommend you follow this link for more information.

    值得理解的另一系列概念是I / Q矩阵的概念以及多普勒读数的含义。 I / Q矩阵由N x M矩阵(在我们的示例中为32 x 128矩阵)组成,该矩阵将笛卡尔元素的慢速和快速信号读数存储为笛卡尔元素,其中“ I”代表实部,“ M”代表虚部。 您可以将此矩阵的每一行表示为代表来自源的信号脉冲,并将该矩阵的每一列表示为用于返回沿感兴趣方向从物体或目标反弹的无线电波的读数。 如果您仍然感到困惑或感兴趣,那么脉冲之间的时间为“慢时间”,而读取脉冲之间的时间为“快速时间”,我强烈建议您点击此链接以获取更多信息。

    Image for post
    A visualization of fast time relative to slow time. In our case, the I/Q matrix would have 32 rows and 128 columns. Image by Author.
    快速时间相对于慢时间的可视化。 在我们的情况下,I / Q矩阵将具有32行和128列。 图片由作者提供。

    Also included in the dataset, separate from the I/Q matrix, is the doppler burst readings. Consisting of one row of 128 readings the doppler burst can be used to track an object’s speed and direction of travel. Much like how the sirens on a police car change sound as the car drive past you, the doppler effect relates to the range in wavelength characteristics of objects in motion. By bouncing radio signals off objects of interest we can see how the radio waves change shape and hence infer a number of parameters about the object of interest such as speed, direction, and acceleration.

    与I / Q矩阵分开的数据集中还包括多普勒猝发读数。 由128个读数的一行组成,多普勒猝发可用于跟踪物体的速度和行进方向。 就像警车上的警笛声一样,当汽车驶过您时,多普勒效应与运动物体的波长特性范围有关。 通过将无线电信号从目标物体上弹起,我们可以看到无线电波如何改变形状,从而推断出有关目标物体的许多参数,例如速度,方向和加速度。

    Great, now that we have a bit of terminology under our belt it is time to discuss the five file pairs provided for the competition. These file pairs, whilst in the same format, differ from each other greatly and form five distinct sets:

    太好了,现在我们有了一些专业术语,现在该讨论为比赛提供的五对文件了。 这些文件对虽然格式相同,但彼此之间有很大差异,并形成五个不同的集合:

    • Training set: As the name describes, the training set consists of a combination of human and animal, with high and low SNR readings created from authentic doppler-pulse radar recordings.

      训练集:顾名思义,训练集由人和动物组成,具有由真实的多普勒脉冲雷达记录创建的高和低SNR读数。

      Training set: As the name describes, the training set consists of a combination of human and animal, with high and low SNR readings created from authentic doppler-pulse radar recordings.6656 Entries

      训练集:顾名思义,训练集由人和动物组成,具有由真实的多普勒脉冲雷达记录创建的高和低SNR读数。 6656个条目

    • Test set: For the purposes of the competition, a test set is included to evaluate the quality of the model and rank competitors. The set is unlabeled but does include a balanced mix of high and low SNR.

      测试集:出于竞争目的,其中包括一个测试集,用于评估模型的质量并为竞争对手排名。 该集合未标记,但包含高和低SNR的平衡混合。

      Test set: For the purposes of the competition, a test set is included to evaluate the quality of the model and rank competitors. The set is unlabeled but does include a balanced mix of high and low SNR.106 Entries

      测试集:出于竞争目的,其中包括一个测试集,用于评估模型的质量并为竞争对手排名。 该集合未标记,但包含高和低SNR的平衡混合。 106条目

    • Synthetic Low SNR set: Using readings from the training set a low SNR dataset has been artificially created by sampling the high SNR examples and artificially populating the samples with noise. This set can be used to better train the model on low SNR examples.

      合成低信噪比集:使用训练集中的读数,通过对高信噪比示例进行采样并用噪声人工填充样本来人工创建低信噪比数据集。 此集合可用于在低SNR实例上更好地训练模型。

      Synthetic Low SNR set: Using readings from the training set a low SNR dataset has been artificially created by sampling the high SNR examples and artificially populating the samples with noise. This set can be used to better train the model on low SNR examples.50883 Entries

      合成低信噪比集:使用训练集中的读数,通过对高信噪比示例进行采样并用噪声人工填充样本来人工创建低信噪比数据集。 此集合可用于在低SNR实例上更好地训练模型。 50883条目

    • The Background set: The background dataset includes readings gathered from the doppler-pulse radars without specific targets. This set could be used to help the model better distinguish noise in the labeled datasets and help the model distinguish relevant information from messy data.

      背景集:背景数据集包括从多普勒脉冲雷达收集的,没有特定目标的读数。 该集合可用于帮助模型更好地区分标记数据集中的噪声,并帮助模型将相关信息与混乱数据区分开。

      The Background set: The background dataset includes readings gathered from the doppler-pulse radars without specific targets. This set could be used to help the model better distinguish noise in the labeled datasets and help the model distinguish relevant information from messy data.31128 Entries

      背景集:背景数据集包括从多普勒脉冲雷达收集的,没有特定目标的读数。 该集合可用于帮助模型更好地区分标记数据集中的噪声,并帮助模型将相关信息与混乱数据区分开。 31128个条目

    • The Experiment set: The final set and possibly the most interesting, the experiment set includes humans recorded by the doppler-pulse radar in a controlled environment. Whilst not natural this could be valuable for balancing the animal-heavy training set provided.

      实验装置:最终装置,也许是最有趣的装置,该实验装置包括多普勒脉冲雷达在受控环境中记录的人类。 这虽然不自然,但对于平衡提供的大量动物训练集可能很有​​价值。

      The Experiment set: The final set and possibly the most interesting, the experiment set includes humans recorded by the doppler-pulse radar in a controlled environment. Whilst not natural this could be valuable for balancing the animal-heavy training set provided.49071 Entries

      实验装置:最终装置,也许是最有趣的装置,该实验装置包括多普勒脉冲雷达在受控环境中记录的人类。 这虽然不自然,但对于平衡提供的大量动物训练集可能很有​​价值。 49071条目

    As I have already alluded to, the training set isn’t populated with a satisfactory amount of data points. This constitutes the challenge, generating a sufficient amount of data to train the model on, from the supplementary synthetic, background, and experimental sets. This challenge is further exacerbated by the imbalance of the data.

    正如我已经提到的,训练集中没有填充令人满意的数据点。 这就构成了挑战,需要从补充的合成,背景和实验集中生成足够数量的数据来训练模型。 数据不平衡进一步加剧了这一挑战。

    With such a small dataset it is important to ensure the data is balanced and unbiased as this can lead to significant misinterpretations of the set by the model, and small inconsistencies can get extrapolated into significant errors.

    使用如此小的数据集,重要的是要确保数据平衡且无偏见,因为这可能导致模型对集合的严重误解,并且小的不一致性可能会推断出严重的错误。

    Image for post
    Image by Author
    图片作者

    The first key imbalance is the difference between the number of high and low SNR tracks. As you can see from the adjacent graph there are almost two thousand more low SNR data points than high SNR.

    第一个关键失衡是高和低SNR磁道数之间的差异。 从相邻的图表中可以看到,低SNR数据点比高SNR多了近两千。

    |

    |

    Image for post
    Image by Author
    图片作者

    The second key imbalance is between the number of Humans and Animals in the dataset. Clearly, with such a significant difference the model might become biased towards predicting animal instead of human, since this prediction would net a high accuracy for little effort on the model’s part.

    第二个关键的不平衡是数据集中的人类和动物数量之间。 显然,由于存在如此巨大的差异,模型可能会偏向于预测动物而不是人类,因为这种预测将为模型方面付出很少的努力而获得很高的准确性。

    |

    |

    Image for post
    Image by Author
    图片作者

    Both of these disparities cause significant issues when building the model. If we take a closer look at the relationship between signal quality and target type we see that the majority of animals have low SNR readings and the majority of humans have high SNR readings. Whilst this may seem minor, extrapolated over a number of training intervals our model may make the mistake of conflating a cleaner signal with that of a human, and a noisy signal with that of an animal.

    建立模型时,这两个差异都会导致严重问题。 如果我们仔细研究信号质量和目标类型之间的关系,我们会发现大多数动物的SNR读数较低,而大多数人的SNR读数较高。 尽管这似乎很小,但在许多训练间隔中推断出来,我们的模型可能会犯错误,将较干净的信号与人的信号混淆,而将噪声信号与动物的信号混淆。

    |

    |

    基准模型和初始印象: (The Baseline Model and Initial Impressions:)

    Interestingly enough, along with the data provided, a baseline model was included for the competitors. This model serves as an example of how the final submission should be formatted as well as providing a relative starting point for competitors. So what is the baseline model?

    有趣的是,连同所提供的数据,还包括了针对竞争对手的基线模型。 该模型是如何格式化最终提交文件以及为竞争对手提供相对起点的示例。 那么基线模型是什么?

    The MAFAT challenge organizers decided to start strong by beginning with Convolutional Neural Network (CNN), a form of artificial intelligence designed for computer vision problems. The model takes an input image and weights parameters based on their importance in discerning the final result, which in our case would be an animal or a human. This particular CNN has two convolutional layers, followed by two max-pooling layers, which again is followed by two “dense” layers, before finally being activated by a ReLU function and regularized with a Sigmoid function. This is better visualized with a diagram:

    MAFAT挑战组织者决定从强大的卷积神经网络(CNN)开始 ,这是为计算机视觉问题设计的一种人工智能形式。 模型根据输入在识别最终结果中的重要性来获取输入图像和权重参数,在我们的例子中,该结果将是动物或人类。 这个特殊的CNN具有两个卷积层 ,然后是两个最大池化层 ,再是两个“密集”层 ,最后由ReLU函数激活并由 Sigmoid函数进行正则化。 使用图表可以更好地将其可视化:

    Image for post
    Image for post
    MAFAT. Reposted with Author’s permission.MAFAT 。 经作者许可重新发布。

    As you can see in the above diagram we start with the 126x32 I/Q matrix. This matrix, along with 15 others, are aligned, and the first convolution of training happens, of which the result is altered and resized to a different dimensionality. Eventually, the model concludes with a single value, a number somewhere between 0 and 1 where the closer to 0 the more likely the signal is an animal, and the closer to 1 the more likely the signal is human. It is alright if you don’t understand the logic or the terminology behind this baseline model, these techniques are quite elaborate and if I were to go into detail this blog would be twice as long. If you are interested this link goes into more detail.

    如上图所示,我们从126x32 I / Q矩阵开始。 该矩阵与其他15个矩阵对齐,并且发生了第一次训练卷积,其结果被更改并调整为其他维度。 最终,模型以一个单一值结束,该数字介于0到1之间,其中越接近0则信号越可能是动物,而越接近1则信号就越可能是人。 如果您不了解此基准模型背后的逻辑或术语,那也没关系,这些技术都非常详尽,如果我要详细介绍,那么此博客的时间将是原来的两倍。 如果您有兴趣,请访问此链接

    In addition to the model, the baseline attempt includes a few other noteworthy strategies for increasing the accuracy of prediction. As discussed earlier the training set is heavily imbalanced, to help amend this discrepancy the training set is supplemented with more data from the experiment set. This is to help the CNN understand and recognize human patterns within the data and will ideally lead to a higher level of accuracy. In our own attempt, we trained the model without changing the baseline structure, and validated (scored the accuracy of the model) on a sample of the training data withheld from the model. The results are visualized below:

    除模型外,基线尝试还包括其他一些值得注意的策略,可以提高预测的准确性。 如前所述,训练集严重失衡,为了帮助纠正这种差异,训练集还添加了来自实验集的更多数据。 这是为了帮助CNN了解和识别数据中的人为模式,并且理想情况下将导致更高的准确性。 在我们自己的尝试中,我们在不更改基线结构的情况下对模型进行了训练,然后对从模型中保留的训练数据样本进行了验证(对模型的准确性进行评分)。 结果如下所示:

    Image for post
    Results of baseline model graphed. Image by Author.
    绘制基线模型的结果。 图片由作者提供。

    As you can see from the results the model performed perfectly on the training data, and almost perfectly on the validation set. For a baseline model, this is pretty impressive, right? Well as it turns out, by the admission of MAFAT themselves, the baseline model doesn’t perform well on the test set, averaging only a 75% accuracy. Given the scope of the project and the technology they are trying to produce, 75% simply won’t cut it. Hence we have to go back to the drawing board to figure out how we can create a more accurate model.

    从结果中可以看出,该模型在训练数据上表现完美,在验证集上表现完美。 对于基准模型,这是非常令人印象深刻的,对吗? 事实证明,通过MAFAT本身的接受,基线模型在测试集上的表现不佳,平均准确性仅为75%。 考虑到项目范围和他们试图生产的技术,75%根本不会削减。 因此,我们必须回到制图板上,找出如何创建更准确的模型。

    什么不起作用,我们可以看到一种模式吗? (What isn’t working and can we see a pattern?)

    So now that we understand how the baseline model works we need to understand what kind of mistakes the model is making on the test data. The best way to understand these patterns and the mistakes made by the model is to visualize the data, although this is easier said than done. Because of the high dimensionality of the data, it can be hard to visualize and understand in a meaningful way. Luckily for us, there is a solution to this problem, T-distributed Stochastic Neighbor Embedding for high dimensional data, also known as TSNEs. A TSNE is essentially its own machine learning algorithm for non-linear dimension reduction. It works by constructing a probability distribution over the different pairings of data where higher probabilities can be imagined as pairings of higher similarity. As the TSNE function continues it repeats this process, slowly predicting dimensionality until it reaches a stage where it is digestible to the human brain. Our code for producing the TSNE, along with the baseline notebook can be found here. In our case, we extracted the vector representation of the spectrogram using the final layer of the network before classification and computed the TSNE on the resulting vector.

    因此,既然我们了解了基准模型的工作原理,我们就需要了解该模型在测试数据上犯了什么样的错误。 理解这些模式和模型所犯错误的最好方法是可视化数据,尽管说起来容易做起来难。 由于数据的高维度,可能很难以有意义的方式可视化和理解。 幸运的是,对于这个问题,有一个解决方案,即针对高维数据的T分布随机邻居嵌入,也称为TSNE。 TSNE本质上是其自己的用于非线性降维的机器学习算法。 它通过在不同数据对上构建概率分布来工作,其中较高的概率可以想象为较高相似性的对。 随着TSNE功能的继续,它会重复此过程,慢慢预测维数,直到达到人脑可消化的阶段。 我们用于生产TSNE的代码以及基准笔记本 可以在这里找到。 在我们的案例中,我们提取了 在分类之前使用网络的最后一层对频谱图进行矢量表示,并在生成的矢量上计算TSNE。

    Because of the stochastic nature of the algorithm, TSNE’s look different every time they are computed, however, they are useful for pointing out noteworthy clusters of similar data. Computing the TSNE for our model produces the following plot where:

    由于该算法具有随机性,因此每次计算时,TSNE的外观都会有所不同,但是,它们对于指出相似数据的值得注意的簇很有用。 为我们的模型计算TSNE会产生以下图,其中:

    Green = animalBlue = humanRed = incorrect prediction in the validation setTeal = location of a test set value

    绿色=动物蓝色=人类红色=验证集中的预测不正确Teal =测试集值的位置

    Image for post
    TSNE graph. Image by Author.
    TSNE图。 图片由作者提供。

    As you can see there are some pretty significant clusters of animals and a few clusters of humans. Because there are fewer humans in the training set the human clusters are less apparent when compared to the animal clusters. As indicated by the red points there are a few areas where the model makes incorrect predictions. This is noteworthy because it appears as though the red points form two distinct clusters themselves, suggesting that the majority of incorrectly predicted points are close to two separate epicenters. What is also noteworthy is that there are a significant number of teal points that also fall in these regions, which explains why the baseline model is only scoring around ~75%, because the model would be incorrectly predicting these points.

    如您所见,这里有一些非常重要的动物群和一些人类群。 由于训练集中的人较少,因此与动物群相比,人群的明显性较低。 如红色点所示,模型在一些区域进行了错误的预测。 这是值得注意的,因为它看起来好像红点本身形成了两个不同的簇,这表明大多数错误预测的点都靠近两个单独的震中。 还值得注意的是,在这些区域中也有大量的蓝绿色点,这解释了为什么基线模型仅得分在〜75%左右,因为模型会错误地预测这些点。

    It also appears that the test set is relatively spread out not forming as clear of a center and being relatively even between animals and humans, although we can’t know this for sure as we don’t possess the labels for points at those locations.

    似乎测试集也相对分散,没有形成清晰的中心,并且在动物和人之间相对均匀,尽管我们不能确切知道这一点,因为我们在那些位置没有点的标签。

    下一步: (Where to next:)

    Image for post
    It can be hard to know which direction to take the project. Photo by Javier Allegue Barros on Unsplash
    很难知道该项目的发展方向。 Javier Allegue BarrosUnsplash拍摄的照片

    Given this information, there are a number of different strategies we can explore for boosting the overall quality of the model or in creating a different model altogether. In an ideal world, we would have a larger training dataset, this would be a great solution to the problem as the more points we have to train on, the more chance the model has of understanding a pattern that can lead to the correct classification of the red clusters above. Unfortunately, this isn’t an option and we are limited to the data provided or any data we can gather from external sources. This seems like a good place to start because the distribution is so unbalanced between humans, animal, low SNR, and high SNR. By developing a better distribution of data, be that from the auxiliary sets provided, or from some external source, we can retrain the model and see how the results improve. Depending on the performance of the baseline model on a more balanced dataset, we can then move forward towards creating an improved model.

    有了这些信息,我们可以探索许多不同的策略来提高模型的整体质量或完全创建不同的模型。 在理想的世界中,我们将拥有一个更大的训练数据集,这将是一个很好的解决方案,因为我们必须训练的点越多,该模型就越有可能理解一种可以导致正确分类的模式的机会。上面的红色簇。 不幸的是,这不是一种选择,我们仅限于提供的数据或我们可以从外部来源收集的任何数据。 这似乎是一个不错的起点,因为人,动物,低SNR和高SNR之间的分布非常不平衡。 通过开发更好的数据分布,无论是从提供的辅助集中还是从某些外部来源,我们都可以重新训练模型并查看结果如何改善。 根据基线模型在更平衡的数据集上的性能,然后我们可以朝着创建改进的模型前进。

    As I write this now some competitors have already scored accuracies greater than 95%. A leader board of competitors and their scores can be found here. This is a multipart series with more updates to come as we proceed through the competition.

    在撰写本文时,一些竞争对手的准确度已超过95%。 一个 竞争对手排行榜及其分数可在此处找到 这是一个分为多个部分的系列,随着比赛的进行,将会有更多更新。

    来源和其他阅读: (Sources and Additional Reading:)

    IQ Modulation. (n.d.). Retrieved August 13, 2020, from https://www.keysight.com/upload/cmc_upload/All/IQ_Modulation.htm?cmpid=zzfindnw_iqmod

    智商调制。 (nd)。 于2020年8月13日从https://www.keysight.com/upload/cmc_upload/All/IQ_Modulation.htm?cmpid=zzfindnw_iqmod检索

    Saha, S. (2018, December 17). A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way. Retrieved August 13, 2020, from https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53

    Saha,S.(2018年12月17日)。 卷积神经网络综合指南-ELI5方法。 于2020年8月13日从https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53检索

    Understanding I/Q Signals and Quadrature Modulation: Radio Frequency Demodulation: Electronics Textbook. (n.d.). Retrieved August 13, 2020, from https://www.allaboutcircuits.com/textbook/radio-frequency-analysis-design/radio-frequency-demodulation/understanding-i-q-signals-and-quadrature-modulation/

    了解I / Q信号和正交调制:射频解调:电子教科书。 (nd)。 于2020年8月13日从https://www.allaboutcircuits.com/textbook/radio-frequency-analysis-design/radio-frequency-demodulation/understanding-iq-signals-and-quadrature-modulation/检索

    What is I/Q Data? (n.d.). Retrieved August 13, 2020, from http://www.ni.com/tutorial/4805/en/

    什么是I / Q数据? (nd)。 于2020年8月13日从http://www.ni.com/tutorial/4805/en/检索

    All images used are either created by myself or used with the explicit permission of the authors. Links to the author’s material are included under each image.

    所有使用的图像要么由我自己创建,要么在作者的明确许可下使用。 每个图像下方都包含指向作者资料的链接。

    翻译自: https://medium.com/gsi-technology/training-a-model-to-use-doppler-pulse-radar-for-target-classification-2944a312148c

    脉冲多普勒雷达

    展开全文
  • 雷达系统 学习笔记(四)——脉冲多普勒雷达1

    万次阅读 多人点赞 2018-05-16 20:39:59
    第五章 脉冲多普勒雷达 脉冲多普勒雷达特点:具有脉冲雷达的距离分辨力和连续波雷达的速度分辨力,有较强的抑制杂波能力,因而能在较强的杂波背景中分辨出目标回波。 5.1 脉冲多普勒雷达的基本概念 5.1.1 PD...

    第五章 脉冲多普勒雷达

      脉冲多普勒雷达特点:具有脉冲雷达的距离分辨力和连续波雷达的速度分辨力,有较强的抑制杂波能力,因而能在较强的杂波背景中分辨出目标回波。

    5.1 脉冲多普勒雷达的基本概念

    5.1.1 PD雷达定义

    PD雷达是通过脉冲发射并利用多普勒效应检测目标信息的脉冲雷达。
    具有如下三点特征:

    • 具有足够高的脉冲重复频率,以致不论杂波或所观测到的目标都没有速度模糊;
    • 能实现对脉冲串频谱单根谱线的多普勒滤波,即频率滤波;
    • 由于重复频率(PRF)很高,通常对所观测的目标产生距离模糊。
    5.1.2 PD雷达分类

    PD{PRFPRFPRF{

    5.2 脉冲多普勒雷达的杂波

    5.2.1 PD雷达性能指标

    用杂波衰减CA和杂波下可见度SCV来描述。
    CA:定义为对某一速度目标的杂波和信号功率输入比与输出比的比值,即

    CA(υr)=(C/S)i(C/S)o|υr

    SCV:
    SCV(υr)=CA(υr)DXC

    式中,检测因子DXC为当已知后续处理时,检测所需的(C/S)o

    5.2.2机载下视PD雷达的杂波谱

      多普勒雷达的基本特点之一,是在频域-时域分布相当宽广且相当强的背景杂波中检测出有用的信号。这种背景杂波通常被称为脉冲多普勒杂波,其杂波频谱是多普勒频率-距离的函数。
      孤立目标对雷达发射信号的散射作用所产生的回波信号的多普勒频移,正比于雷达与运动目标之间的径向速度υ,所以当雷达平台以地速υR水平移动,地速矢量与地面一小块地杂波之间的夹角为Ψ时,其多普勒频移为:

    fd=2υRλcosΨ

    式中,υR为载机地速,Ψ为地速矢量与地面杂波A之间的夹角。

      PD雷达发射具有N个矩形脉冲串,其载频为f0,脉宽为τ,脉冲重复频率为fr,脉冲间隔周期为Tr,脉冲持续时间为NT,则N个矩形脉冲串傅里叶变换的正频率部分如下:
    这里写图片描述
    F(ω)可表示为:
    这里写图片描述
    杂波分析
    这里写图片描述
    1、主瓣杂波
    多普勒中心频率(即主波束中心Ψ0处对应的多普勒频率)为

    fMD=fd(Ψ0)=2υRλcosΨ0

    假设天线主波束的宽度为θB,则主瓣杂波的边缘位置间的最大多普勒频率差值为

    fMD=fd(Ψ0θB/2)fd(Ψ0+θB/2)2υRλθBcosΨ0

    机载PD雷达的主瓣杂波的强度可以比雷达接收机的噪声强70~90dB,主瓣杂波的多普勒频率fMD也在不断变化,并且变化范围在±(2υR)/λ之内。
    2、旁瓣杂波
    天线旁瓣接收到的雷达回波是无用的,所以可称其为旁瓣杂波。除了高度回波,旁瓣杂波不如主瓣旁波能量集中,但它占据很宽的频带。
    旁瓣杂波区的多普勒频率范围为±fc,max,则

    fc,max=2υRλ

    雷达天线的旁瓣波束增益通常要比它的主波束增益低得多。当PD雷达不运动时,旁瓣杂波与主瓣杂波在频域上重合;当PD雷达运动时,旁瓣杂波与主瓣杂波就分布在不同的频域上。
    3、高度线杂波
    当天线方向图中的某个旁瓣垂直照射地面时,是属于Ψ=90°fd=0的情况。通常,机载下视PD雷达的地面杂波中fd=0位置上的杂波叫做高度线杂波。在零多普勒频移处总有一个较强的“杂波”。
    4、无杂波区
    地面杂波分为主瓣杂波区、旁瓣杂波区和高度线杂波区。
    通常恰当选择雷达信号的脉冲重复频率fr,使得其地面杂波既不重叠也不连接,从而出现了无杂波区。
    5、杂波频率与目标多普勒频率间的关系
    这里写图片描述

    5.2.3 三种PD雷达脉冲重复频率选择的比较

    1、低PRF
    ①没有距离模糊,但有许多多普勒模糊(盲速)。
    ②在远距离由于地球的曲率没有杂波,因而可在无杂波情况下工作。
    ③旁瓣杂波并不像在高PRF脉冲多普勒系统中一样重要。
    ④在相同的性能下,要求的平均功率和天线孔径乘积比高PRF脉冲多普勒雷达小。
    ⑤通常比高PRF脉冲多普勒更简单。费用通常比同样性能的高PRF脉冲多普勒雷达少得多。
    2、中PRF
    ①具有距离和多普勒模糊
    ②没有高PRF系统存在的无杂波区,因此,高速目标的检测性能不如高PRF系统。
    ③较小的距离模糊意味着天线旁瓣看见的杂波少,因此,与高PRF系统相比,可在更远距离检测低相对速度的目标。
    ④中PRF系统相当于用高速目标的检测能力换取低速目标的更好检测,因此,如果只有一个系统可用的话,战斗机或截击机应用雷达更愿意采用中PRF系统。
    ⑤与高PRF系统相比,可获得更好的距离精度和距离分辨力。
    ⑥为了减少旁瓣杂波,天线必须有低的旁瓣。
    3、高PRF
    ①多普勒频移没有模糊,但有盲速,但存在许多距离模糊。
    ②在无杂波区可以检测远距离高速接近目标。
    ③低径向速度目标通常被距离上折叠起来的近距离旁瓣杂波淹没在多普勒频域区,检测效果差。
    ④与低PRF系统相比,高PRF导致更多的杂波通过天线旁路进入雷达,因而要求更大的改善因子。
    ⑤为了使旁瓣杂波最小,天线旁瓣必须低。
    ⑥同其他雷达相比,距离精度和距离上分辨多个目标的能力比其他雷达差。

    5.3 脉冲多普勒雷达的基本组成

    这里写图片描述
    1、收发开关
      在PD雷达中,收发开关通常是诸如环形器等无源器件,可在发射和接收之间将天线有效地切换。由于铁氧体环形器隔离度的典型值为20-50dB,因此尚有相当大的能量耦合到接收机。
    2、接收机保护器(R/P)
      接收机保护器是一个快速响应的大功率开关,可防止由收发开关泄露过来的大功率发射机输出信号损坏高灵敏度的接收机前端。为了使发射脉冲之后的门中的灵敏度降低到最小,接收机保护器必须有快速的恢复能力。
    3、射频衰减器
      射频(RF)衰减器不仅可以抑制由R/P进入接收机的发射机泄露,而且控制进入接收机的输入信号电平。所接收到的信号电平始终低于饱和电平。比较典型的方法是,在搜索时采用杂波AGC,而在单目标跟踪时采用目标AGC,以防止假信号的产生而使性能将低。
    4、杂波定位
      通常作为稳定本振一部分的压控振荡器(VOC)与主波束杂波差频后得到零频或直流。当杂波为直流时,就降低了对同相(I)和正交(Q)通道的幅度平衡和相位平衡的要求。这是因为不平衡所导致的镜像将落于直流的附近,可以很容易地将它和主波束杂波一起滤除。
    5、发射脉冲抑制器
      接收机中频段提供的发射脉冲抑制器可进一步衰减发射机泄露,是一种波门选取器件。
    6、信号处理
      通过正交混频,接收机的模拟输出信号下变频为基带信号。同相信号和正交信号经匹配滤波器滤波,由A/D变换为数字信号。A/D之后一般是延迟线杂波对消器和多普勒滤波器组,为的是用来抑制主波束杂波和进行相参积累。
      滤波器组通常采用FFT来实现或当滤波器较少时用离散傅里叶变换DFT来完成。合适的加权可用来降低滤波器的旁瓣。
      I/Q合成近似形成FFT输出的电压包络,也可以用检波后积累(PDI),即每个距离门-多普勒滤波器的输出在几个相参周期内线性相加。PDI的输出再于恒虚警(CFAR)处理形成的检测门限比较。
      在CFAR电路之后是离散的旁路抑制逻辑电路及距离模糊和速度模糊解算器。最后的检测输出被送往雷达显示器和计算机。

    展开全文
  • 脉冲多普勒雷达信号程序仿真,包括信号生成,MTI滤波,多普勒滤波器组滤波,恒虚警处理
  • 应用systemvue进行脉冲多普勒雷达仿真和校验
  • 脉冲多普勒雷达In the world of data science the industry, academic, and government sectors often collide when enthusiasts and experts alike, work together to tackle the challenges we face day-to-day....

    脉冲多普勒雷达

    by Braden Riggs and George Williams (gwilliams@gsitechnology.com)

    Braden Riggs和George Williams(gwilliams@gsitechnology.com)

    In the world of data science the industry, academic, and government sectors often collide when enthusiasts and experts alike, work together to tackle the challenges we face day-to-day. A prime example of this collaboration is the Israeli Ministry of Defense Directorate of Defense Research & Development (DDR&D)’s MAFAT challenges. A series of data science related challenges with real-world application and lucrative prize pools. In the program’s own words:

    在数据科学世界中,当发烧友和专家都共同努力应对我们日常面临的挑战时,行业,学术界和政府部门经常发生冲突。 以色列国防部国防研究与发展局(DDR&D)的MAFAT挑战就是这种合作的主要例证。 一系列与数据科学相关的挑战,包括现实应用和丰厚的奖池。 用程序本身的话来说:

    The goal of the challenge is to explore the potential of advanced data science methods to improve and enhance the IMOD current data products. The winning method may eventually be applied to real data and the winners may be invited to further collaborate with the IMOD on future projects.- MAFAT Competition Coordinators

    挑战的目标是探索先进数据科学方法的潜力,以改善和增强IMOD当前数据产品。 获奖方法可能最终会应用于真实数据,获奖者可能会被邀请在未来的项目上与IMOD进一步合作。- MAFAT竞赛协调员

    Given the recent inception of the program, there haven’t been many challenges yet, however, there are expected to be a variety of challenges ranging from complicated Natural Language Processing puzzles to computer-vision related endeavors.

    鉴于该程序是最近启动的,因此还没有很多挑战,但是,预计会出现各种各样的挑战,从复杂的自然语言处理难题到计算机视觉相关的工作。

    One such challenge, their second one made available thus far, caught my eye. It involves creating a model for classifying living, non-rigid objects that have been detected by doppler-pulse radar systems. The challenge, “MAFAT Radar Challenge — Can you distinguish between humans and animals in radar tracks?” implores competitors to develop a model that can accurately distinguish humans from animals based on a spectrum of radio signals recorded from various doppler-pulse radar sites on various days. If you are interested in participating I recommend visiting the challenge site before reading on.

    这样的挑战之一,到目前为止已经提供的第二个挑战引起了我的注意。 它涉及创建一个模型,以对多普勒脉冲雷达系统已检测到的活的非刚性物体进行分类。 挑战“ MAFAT雷达挑战-您能区分雷达轨道中的人与动物吗? 恳请竞争对手开发一种模型,该模型可以根据在不同日子从各个多普勒脉冲雷达站点记录的无线电信号频谱,准确地将人与动物区分开。 如果您有兴趣参加,我建议您访问 在继续阅读之前先挑战网站

    那么,我们正在处理什么样的数据?我们需要了解什么? (So what kind of data are we working with and what do we need to know about it?)

    Image for post
    Image for post
    An example of the data included for the competition split by Animal/Human and High/Low Signal-Noise-Ratio. The I/Q matrices have been converted into spectrograms for visualization, and the doppler readings have been added in white. As you can see there are some differences present in the files. Images provided by MAFAT. Reposted with Author’s permission.
    比赛数据包括动物/人类和高/低信噪比。 I / Q矩阵已转换为频谱图以进行可视化,并且多普勒读数已添加为白色。 如您所见,文件中存在一些差异。 图片由 MAFAT 提供 经作者许可重新发布。

    The key to developing an accurate and competitive model is to first understand the data, how it was sourced, and what it is missing. Included with the competition is 5 CSV files containing the metadata, and 5 pickle files (serializing Python object structure format) containing doppler readings that track the object’s center of mass and slow/fast time readings in the form of a standardized I/Q matrix.

    开发准确而具有竞争力的模型的关键是首先了解数据,数据来源和缺失内容。 竞赛中包括5个包含元数据的CSV文件 ,以及5个 包含多普勒读数的 pickle文件 (序列化Python对象结构格式) ,它们以标准化I / Q矩阵的形式跟踪对象的质心和慢/快时间读数

    Before we go any further it is worth breaking down a few key concepts relating to signals and the specific types of data collected. The signal readings that make up the dataset fall into two levels of quality, High Signal to Noise Ratio, and Low Signal to Noise Ratio. This reading, High SNR and Low SNR divides the set into two levels of quality, one with high clarity that hasn’t been heavily tainted by a noise generating process, and one with low clarity that has had aspects such as weather impact the quality of the reading.

    在进一步研究之前,有必要分解一些与信号和所收集数据的特定类型有关的关键概念。 构成数据集的信号读数分为两个质量级别,即高信噪比低信噪比 。 该读数分为高信噪比和低信噪比两类,将质量分为两个级别,一个级别的高清晰度没有受到噪声生成过程的严重影响,而另一个级别的低清晰度却受到天气等因素的影响。阅读。

    Image for post
    KF6HI. Reposted with Author’s permission.KF6HI 。 经作者许可重新发布。

    You might be wondering why we would even choose to include low SNR readings given the impact noise has on the data, however to my surprise this data is actually quite valuable when developing an effective model. Real-life is messy, and the true reading one might expect to see will not always be high quality, hence it is important to make sure our model is adaptive and geared towards a range of data readings, not just the highest quality ones. Furthermore, we are working with a limited amount of data (which we will explore in-depth below) and hence want to utilize everything at our disposal for training the model.

    您可能想知道为什么考虑到噪声对数据的影响,我们为什么甚至选择包括低SNR读数,但是令我惊讶的是,在开发有效模型时,该数据实际上非常有价值。 现实生活是一团糟,人们可能期望看到的真实读数并不总是高质量的,因此,重要的是要确保我们的模型具有自适应性,并且适合各种数据读数,而不仅仅是高质量的读数。 此外,我们正在处理数量有限的数据(我们将在下面深入探讨),因此希望利用我们掌握的所有信息来训练模型。

    Another series of concepts worth understanding is the notion of an I/Q matrix and what a doppler reading entails. An I/Q matrix consists of an N x M matrix, in our case a 32 x 128 matrix, that stores the slow and fast signal readings as cartesian elements, where “I” represents the real part and “M” represents the imaginary part. You can picture each row of this matrix as representing a signal pulse from the source, and each column of this matrix representing a reading for returning radio waves that have bounced off objects or targets in the direction of interest. The time between pulses is “slow time” and the time between readings of said pulses is considered “fast time”, if you are still confused or further interested I highly recommend you follow this link for more information.

    值得理解的另一系列概念是I / Q矩阵的概念以及多普勒读数的含义。 I / Q矩阵由N x M矩阵(在我们的示例中为32 x 128矩阵)组成,该矩阵将笛卡尔元素的慢和快信号读数存储为笛卡尔元素,其中“ I”代表实部,“ M”代表虚部。 您可以将矩阵的每一行表示为代表来自源的信号脉冲,并将矩阵的每一列表示为用于返回沿感兴趣方向从物体或目标反弹的无线电波的读数。 脉冲之间的时间为“慢时间”,而所述脉冲之间的时间间隔为“快速时间”,如果您仍然感到困惑或对此有进一步的兴趣,我强烈建议您点击此链接以获取更多信息。

    Image for post
    A visualization of fast time relative to slow time. In our case, the I/Q matrix would have 32 rows and 128 columns. Image by Author.
    快速时间相对于慢时间的可视化。 在我们的情况下,I / Q矩阵将具有32行和128列。 图片由作者提供。

    Also included in the dataset, separate from the I/Q matrix, is the doppler burst readings. Consisting of one row of 128 readings the doppler burst can be used to track an object’s speed and direction of travel. Much like how the sirens on a police car change sound as the car drive past you, the doppler effect relates to the range in wavelength characteristics of objects in motion. By bouncing radio signals off objects of interest we can see how the radio waves change shape and hence infer a number of parameters about the object of interest such as speed, direction, and acceleration.

    与I / Q矩阵分开的数据集中还包括多普勒猝发读数。 由128个读数的一行组成,多普勒脉冲串可用于跟踪物体的速度和行进方向。 就像警车上的警笛声一样,当汽车驶过您时,多普勒效应与运动物体的波长特性范围有关。 通过将无线电信号弹离目标物体,我们可以看到无线电波如何改变形状,从而推断出有关目标物体的许多参数,例如速度,方向和加速度。

    Great, now that we have a bit of terminology under our belt it is time to discuss the five file pairs provided for the competition. These file pairs, whilst in the same format, differ from each other greatly and form five distinct sets:

    太好了,现在我们有了一些专业术语,现在该讨论为比赛提供的五对文件了。 这些文件对虽然格式相同,但彼此之间有很大差异,并形成五个不同的集合:

    • Training set: As the name describes, the training set consists of a combination of human and animal, with high and low SNR readings created from authentic doppler-pulse radar recordings.

      训练集:顾名思义,训练集由人和动物组成,具有由真实的多普勒脉冲雷达记录创建的高和低SNR读数。

      Training set: As the name describes, the training set consists of a combination of human and animal, with high and low SNR readings created from authentic doppler-pulse radar recordings.6656 Entries

      训练集:顾名思义,训练集由人和动物组成,具有从真实的多普勒脉冲雷达记录创建的高和低SNR读数。 6656个条目

    • Test set: For the purposes of the competition, a test set is included to evaluate the quality of the model and rank competitors. The set is unlabeled but does include a balanced mix of high and low SNR.

      测试集:出于竞争目的,其中包括一个测试集,用于评估模型的质量并为竞争对手排名。 该集合未标记,但包含高和低SNR的平衡混合。

      Test set: For the purposes of the competition, a test set is included to evaluate the quality of the model and rank competitors. The set is unlabeled but does include a balanced mix of high and low SNR.106 Entries

      测试集:出于竞争目的,其中包括一个测试集,用于评估模型的质量并为竞争对手排名。 该集合未标记,但包含高和低SNR的平衡混合。 106条目

    • Synthetic Low SNR set: Using readings from the training set a low SNR dataset has been artificially created by sampling the high SNR examples and artificially populating the samples with noise. This set can be used to better train the model on low SNR examples.

      合成低信噪比集:使用训练集中的读数,通过对高信噪比示例进行采样并用噪声人工填充样本来人工创建低信噪比数据集。 此集合可用于在低SNR实例上更好地训练模型。

      Synthetic Low SNR set: Using readings from the training set a low SNR dataset has been artificially created by sampling the high SNR examples and artificially populating the samples with noise. This set can be used to better train the model on low SNR examples.50883 Entries

      合成低信噪比集:使用训练集中的读数,通过对高信噪比示例进行采样并用噪声人工填充样本来人工创建低信噪比数据集。 此集合可用于在低SNR实例上更好地训练模型。 50883条目

    • The Background set: The background dataset includes readings gathered from the doppler-pulse radars without specific targets. This set could be used to help the model better distinguish noise in the labeled datasets and help the model distinguish relevant information from messy data.

      背景集:背景数据集包括从多普勒脉冲雷达收集的,没有特定目标的读数。 该集合可用于帮助模型更好地区分标记数据集中的噪声,并帮助模型将相关信息与混乱数据区分开。

      The Background set: The background dataset includes readings gathered from the doppler-pulse radars without specific targets. This set could be used to help the model better distinguish noise in the labeled datasets and help the model distinguish relevant information from messy data.31128 Entries

      背景集:背景数据集包括从多普勒脉冲雷达收集的,没有特定目标的读数。 该集合可用于帮助模型更好地区分标记数据集中的噪声,并帮助模型从混乱数据中区分相关信息。 31128个条目

    • The Experiment set: The final set and possibly the most interesting, the experiment set includes humans recorded by the doppler-pulse radar in a controlled environment. Whilst not natural this could be valuable for balancing the animal-heavy training set provided.

      实验装置:最终装置,也许是最有趣的装置,该实验装置包括多普勒脉冲雷达在受控环境中记录的人类。 这虽然不自然,但对于平衡提供的大量动物训练集可能很有​​价值。

      The Experiment set: The final set and possibly the most interesting, the experiment set includes humans recorded by the doppler-pulse radar in a controlled environment. Whilst not natural this could be valuable for balancing the animal-heavy training set provided.49071 Entries

      实验装置:最终装置,也许是最有趣的装置,该实验装置包括多普勒脉冲雷达在受控环境中记录的人类。 这虽然不自然,但对于平衡提供的大量动物训练集可能很有​​价值。 49071条目

    As I have already alluded to, the training set isn’t populated with a satisfactory amount of data points. This constitutes the challenge, generating a sufficient amount of data to train the model on, from the supplementary synthetic, background, and experimental sets. This challenge is further exacerbated by the imbalance of the data.

    正如我已经提到的,训练集中没有填充令人满意的数据点。 这就构成了挑战,需要从补充的合成,背景和实验集中生成足够数量的数据来训练模型。 数据不平衡进一步加剧了这一挑战。

    With such a small dataset it is important to ensure the data is balanced and unbiased as this can lead to significant misinterpretations of the set by the model, and small inconsistencies can get extrapolated into significant errors.

    使用如此小的数据集,重要的是要确保数据平衡且无偏见,因为这可能导致模型对集合的严重误解,并且小的不一致性可能会推断出重大错误。

    Image for post
    Image by Author
    图片作者

    The first key imbalance is the difference between the number of high and low SNR tracks. As you can see from the adjacent graph there are almost two thousand more low SNR data points than high SNR.

    第一个关键失衡是高和低SNR磁道数之间的差异。 从相邻的图表中可以看到,低SNR数据点比高SNR多了近两千。

    |

    |

    Image for post
    Image by Author
    图片作者

    The second key imbalance is between the number of Humans and Animals in the dataset. Clearly, with such a significant difference the model might become biased towards predicting animal instead of human, since this prediction would net a high accuracy for little effort on the model’s part.

    第二个关键的不平衡是数据集中的人类和动物数量之间。 显然,由于存在这种显着差异,因此该模型可能会偏向于预测动物而不是人类,因为这种预测将为模型方面付出很少的努力而获得很高的准确度。

    |

    |

    Image for post
    Image by Author
    图片作者

    Both of these disparities cause significant issues when building the model. If we take a closer look at the relationship between signal quality and target type we see that the majority of animals have low SNR readings and the majority of humans have high SNR readings. Whilst this may seem minor, extrapolated over a number of training intervals our model may make the mistake of conflating a cleaner signal with that of a human, and a noisy signal with that of an animal.

    建立模型时,这两个差异都会导致严重问题。 如果我们仔细研究信号质量和目标类型之间的关系,我们会发现大多数动物的SNR读数较低,而大多数人的SNR读数较高。 尽管这似乎很小,但在许多训练间隔中推断出来,我们的模型可能会犯错误,将较干净的信号与人的信号混淆,而将噪声信号与动物的信号混淆。

    |

    |

    基准模型和初始印象: (The Baseline Model and Initial Impressions:)

    Interestingly enough, along with the data provided, a baseline model was included for the competitors. This model serves as an example of how the final submission should be formatted as well as providing a relative starting point for competitors. So what is the baseline model?

    有趣的是,连同所提供的数据,还包括了针对竞争对手的基线模型。 该模型是如何格式化最终提交文件以及为竞争对手提供相对起点的示例。 那么基线模型是什么?

    The MAFAT challenge organizers decided to start strong by beginning with Convolutional Neural Network (CNN), a form of artificial intelligence designed for computer vision problems. The model takes an input image and weights parameters based on their importance in discerning the final result, which in our case would be an animal or a human. This particular CNN has two convolutional layers, followed by two max-pooling layers, which again is followed by two “dense” layers, before finally being activated by a ReLU function and regularized with a Sigmoid function. This is better visualized with a diagram:

    MAFAT挑战赛组织者决定从强大的卷积神经网络(CNN)开始 ,这是为计算机视觉问题设计的一种人工智能形式。 模型根据输入在识别最终结果中的重要性来获取输入图像和权重参数,在我们的例子中,该结果将是动物或人类。 这个特定的CNN具有两个卷积层 ,然后是两个最大池化层 ,然后又是两个“密集”层 ,最后由ReLU函数激活并由 Sigmoid函数进行正则化。 使用图表可以更好地将其可视化:

    Image for post
    Image for post
    MAFAT. Reposted with Author’s permission.MAFAT 。 经作者许可重新发布。

    As you can see in the above diagram we start with the 126x32 I/Q matrix. This matrix, along with 15 others, are aligned, and the first convolution of training happens, of which the result is altered and resized to a different dimensionality. Eventually, the model concludes with a single value, a number somewhere between 0 and 1 where the closer to 0 the more likely the signal is an animal, and the closer to 1 the more likely the signal is human. It is alright if you don’t understand the logic or the terminology behind this baseline model, these techniques are quite elaborate and if I were to go into detail this blog would be twice as long. If you are interested this link goes into more detail.

    如上图所示,我们从126x32 I / Q矩阵开始。 该矩阵与其他15个矩阵对齐,并且发生了第一次训练卷积,其结果被更改并调整为不同的维度。 最终,模型以单个值结束,该数字介于0到1之间,其中数字越接近0,表示该信号越可能是动物,而数字越接近1,则表示该信号更可能是人类。 如果您不了解此基准模型背后的逻辑或术语,那也没关系,这些技术都非常详尽,如果我要详细介绍,那么此博客的时间将是原来的两倍。 如果您有兴趣,请访问此链接

    In addition to the model, the baseline attempt includes a few other noteworthy strategies for increasing the accuracy of prediction. As discussed earlier the training set is heavily imbalanced, to help amend this discrepancy the training set is supplemented with more data from the experiment set. This is to help the CNN understand and recognize human patterns within the data and will ideally lead to a higher level of accuracy. In our own attempt, we trained the model without changing the baseline structure, and validated (scored the accuracy of the model) on a sample of the training data withheld from the model. The results are visualized below:

    除模型外,基线尝试还包括其他一些值得注意的策略,可以提高预测的准确性。 如前所述,训练集严重失衡,为了帮助纠正这种差异,训练集还添加了来自实验集的更多数据。 这是为了帮助CNN了解和识别数据中的人为模式,并且理想情况下将导致更高的准确性。 在我们自己的尝试中,我们在不更改基线结构的情况下对模型进行了训练,然后对从模型中保留的训练数据样本进行了验证(对模型的准确性进行评分)。 结果显示如下:

    Image for post
    Results of baseline model graphed. Image by Author.
    绘制基线模型的结果。 图片由作者提供。

    As you can see from the results the model performed perfectly on the training data, and almost perfectly on the validation set. For a baseline model, this is pretty impressive, right? Well as it turns out, by the admission of MAFAT themselves, the baseline model doesn’t perform well on the test set, averaging only a 75% accuracy. Given the scope of the project and the technology they are trying to produce, 75% simply won’t cut it. Hence we have to go back to the drawing board to figure out how we can create a more accurate model.

    从结果中可以看出,该模型在训练数据上表现完美,在验证集上表现几乎完美。 对于基准模型,这是非常令人印象深刻的,对吗? 事实证明,通过MAFAT本身的接受,基线模型在测试集上的表现不佳,平均准确性仅为75%。 考虑到项目范围和他们试图生产的技术,75%根本不会削减。 因此,我们必须回到制图板上,找出如何创建更准确的模型。

    什么不起作用,我们可以看到一种模式吗? (What isn’t working and can we see a pattern?)

    So now that we understand how the baseline model works we need to understand what kind of mistakes the model is making on the test data. The best way to understand these patterns and the mistakes made by the model is to visualize the data, although this is easier said than done. Because of the high dimensionality of the data, it can be hard to visualize and understand in a meaningful way. Luckily for us, there is a solution to this problem, T-distributed Stochastic Neighbor Embedding for high dimensional data, also known as TSNEs. A TSNE is essentially its own machine learning algorithm for non-linear dimension reduction. It works by constructing a probability distribution over the different pairings of data where higher probabilities can be imagined as pairings of higher similarity. As the TSNE function continues it repeats this process, slowly predicting dimensionality until it reaches a stage where it is digestible to the human brain. Our code for producing the TSNE, along with the baseline notebook can be found here. In our case, we extracted the vector representation of the spectrogram using the final layer of the network before classification and computed the TSNE on the resulting vector.

    因此,既然我们了解了基准模型的工作原理,我们就需要了解该模型在测试数据上犯了什么样的错误。 理解这些模式和模型所犯错误的最好方法是可视化数据,尽管说起来容易做起来难。 由于数据的高维度,可能很难以有意义的方式可视化和理解。 幸运的是,对于这个问题,有一个解决方案,即针对高维数据的T分布随机邻居嵌入,也称为TSNE。 TSNE本质上是其自己的用于非线性降维的机器学习算法。 它通过在不同数据对上构建概率分布来工作,其中较高的概率可以想象为较高相似性的对。 随着TSNE功能的继续,它会重复此过程,慢慢预测维数,直到达到人脑可消化的阶段。 我们用于生产TSNE的代码以及基准笔记本 可以在这里找到。 在我们的案例中,我们提取了 在分类之前使用网络的最后一层对频谱图进行矢量表示,并在生成的矢量上计算TSNE。

    Because of the stochastic nature of the algorithm, TSNE’s look different every time they are computed, however, they are useful for pointing out noteworthy clusters of similar data. Computing the TSNE for our model produces the following plot where:

    由于该算法具有随机性,因此每次计算时,TSNE的外观都会有所不同,但是,它们对于指出相似数据的值得注意的簇很有用。 为我们的模型计算TSNE会产生以下图,其中:

    Green = animalBlue = humanRed = incorrect prediction in the validation setTeal = location of a test set value

    绿色=动物蓝色=人类红色=验证集中的预测不正确Teal =测试集值的位置

    Image for post
    TSNE graph. Image by Author.
    TSNE图。 图片由作者提供。

    As you can see there are some pretty significant clusters of animals and a few clusters of humans. Because there are fewer humans in the training set the human clusters are less apparent when compared to the animal clusters. As indicated by the red points there are a few areas where the model makes incorrect predictions. This is noteworthy because it appears as though the red points form two distinct clusters themselves, suggesting that the majority of incorrectly predicted points are close to two separate epicenters. What is also noteworthy is that there are a significant number of teal points that also fall in these regions, which explains why the baseline model is only scoring around ~75%, because the model would be incorrectly predicting these points.

    如您所见,这里有一些非常重要的动物群和一些人类群。 由于训练集中的人较少,因此与动物群相比,人群的明显性较低。 如红色点所示,模型在一些区域进行了错误的预测。 这是值得注意的,因为它看起来好像红点本身形成了两个不同的簇,这表明大多数错误预测的点都靠近两个单独的震中。 还值得注意的是,在这些区域中也有大量的蓝绿色点,这解释了为什么基线模型仅得分在〜75%左右,因为模型会错误地预测这些点。

    It also appears that the test set is relatively spread out not forming as clear of a center and being relatively even between animals and humans, although we can’t know this for sure as we don’t possess the labels for points at those locations.

    似乎测试集也相对分散,没有形成清晰的中心,并且在动物和人之间相对均匀,尽管我们不能确切知道这一点,因为我们在那些位置没有点的标签。

    下一步: (Where to next:)

    Image for post
    It can be hard to know which direction to take the project. Photo by Javier Allegue Barros on Unsplash
    很难知道该项目的发展方向。 Javier Allegue BarrosUnsplash拍摄的照片

    Given this information, there are a number of different strategies we can explore for boosting the overall quality of the model or in creating a different model altogether. In an ideal world, we would have a larger training dataset, this would be a great solution to the problem as the more points we have to train on, the more chance the model has of understanding a pattern that can lead to the correct classification of the red clusters above. Unfortunately, this isn’t an option and we are limited to the data provided or any data we can gather from external sources. This seems like a good place to start because the distribution is so unbalanced between humans, animal, low SNR, and high SNR. By developing a better distribution of data, be that from the auxiliary sets provided, or from some external source, we can retrain the model and see how the results improve. Depending on the performance of the baseline model on a more balanced dataset, we can then move forward towards creating an improved model.

    有了这些信息,我们可以探索许多不同的策略来提高模型的整体质量或完全创建不同的模型。 在理想的世界中,我们将拥有一个更大的训练数据集,这将是一个很好的解决方案,因为我们必须训练的点越多,该模型就越有机会理解可以正确分类的模式。上面的红色簇。 不幸的是,这不是一种选择,我们仅限于提供的数据或我们可以从外部来源收集的任何数据。 这似乎是一个不错的起点,因为人,动物,低SNR和高SNR之间的分布非常不平衡。 通过开发更好的数据分布,无论是从提供的辅助集中还是从某些外部来源,我们都可以重新训练模型并查看结果如何改善。 根据基线模型在更平衡的数据集上的性能,然后我们可以朝着创建改进的模型前进。

    As I write this now some competitors have already scored accuracies greater than 95%. A leader board of competitors and their scores can be found here. This is a multipart series with more updates to come as we proceed through the competition.

    在撰写本文时,一些竞争对手的准确度已超过95%。 一个 竞争对手排行榜及其分数可在此处找到 这是一个分为多个部分的系列,随着比赛的进行,将会有更多更新。

    资料来源和其他阅读: (Sources and Additional Reading:)

    IQ Modulation. (n.d.). Retrieved August 13, 2020, from https://www.keysight.com/upload/cmc_upload/All/IQ_Modulation.htm?cmpid=zzfindnw_iqmod

    智商调制。 (nd)。 于2020年8月13日从https://www.keysight.com/upload/cmc_upload/All/IQ_Modulation.htm?cmpid=zzfindnw_iqmod检索

    Saha, S. (2018, December 17). A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way. Retrieved August 13, 2020, from https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53

    Saha,S.(2018年12月17日)。 卷积神经网络综合指南-ELI5方法。 于2020年8月13日从https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53检索

    Understanding I/Q Signals and Quadrature Modulation: Radio Frequency Demodulation: Electronics Textbook. (n.d.). Retrieved August 13, 2020, from https://www.allaboutcircuits.com/textbook/radio-frequency-analysis-design/radio-frequency-demodulation/understanding-i-q-signals-and-quadrature-modulation/

    了解I / Q信号和正交调制:射频解调:电子教科书。 (nd)。 于2020年8月13日从https://www.allaboutcircuits.com/textbook/radio-frequency-analysis-design/radio-frequency-demodulation/understanding-iq-signals-and-quadrature-modulation/检索

    What is I/Q Data? (n.d.). Retrieved August 13, 2020, from http://www.ni.com/tutorial/4805/en/

    什么是I / Q数据? (nd)。 于2020年8月13日从http://www.ni.com/tutorial/4805/en/检索

    All images used are either created by myself or used with the explicit permission of the authors. Links to the author’s material are included under each image.

    所有使用的图像要么由我自己创建,要么在作者的明确许可下使用。 每个图像下方都包含指向作者资料的链接。

    翻译自: https://towardsdatascience.com/training-a-model-to-use-doppler-pulse-radar-for-target-classification-2944a312148c

    脉冲多普勒雷达

    展开全文
  • 动目标显示与脉冲多普勒雷达:MATLAB程式设计 作者:施莱赫 (D.Curtis Schleher)
  • 雷达系统 学习笔记(五)——脉冲多普勒雷达

    万次阅读 多人点赞 2018-05-17 12:34:21
    第五章 脉冲多普勒雷达 5.4 脉冲多普勒雷达的信号处理 5.4.1 概述 5.4.2 抑制各种杂波的滤波器和恒虚警处理  脉冲多普勒雷达接收机是一个复杂的信号处理系统,在这一系统中包括对发射机泄漏和高度杂波的抑制,...

    第五章 脉冲多普勒雷达

    5.4 脉冲多普勒雷达的信号处理

    5.4.1 概述

    5.4.2 抑制各种杂波的滤波器和恒虚警处理

      脉冲多普勒雷达接收机是一个复杂的信号处理系统,在这一系统中包括对发射机泄漏和高度杂波的抑制,单边带滤波和主杂波抑制,再带滤波器组,视频积累和恒虚警检测,而且接收机是多路的,更增加了其复杂性。
      这里写图片描述
     
    1、单边带滤波器
    这里写图片描述
      单边带滤波器是一个带宽近似等于脉冲重复频率fr的带通滤波器,其主要作用是从回波频谱中只滤出单根谱线,从而使得后面的各种滤波处理在单根谱线上进行。使用单边带滤波器还可以避免目标多普勒频率时出现的模糊,同时也避免了后面信号处理过程中可能产生的频谱折叠效应。
      由于单边带滤波器仅取出回波信号的单根谱线,因而使信号功率下降了d2倍(d为发射脉冲占空系数),但因其输出的杂波和噪声功率也同样减小,所以单边带滤波器并不降低接收机的信杂比。
      PD雷达对于单边带滤波器的性能参数要求得十分严格,而月一般要求带外抑制至少要大于60dB,因此通常是采用石英晶体滤波器来满足这些技术要求。
    2、主瓣杂波抑制滤波器
    这里写图片描述
      主瓣杂波的干扰最强,常常比目标回波能量要高出60~80dB。 确定主瓣杂波中心频率fMB有两种方法:一种方法是利用频率跟踪,另一种方法则不用频率跟踪,而是由天线指向和载机飞行速度计算出主瓣杂波应有的多普勒频移fMB,直接控制压控振荡器去产生fc+fMB的振荡频率。
      主瓣杂波抑制滤波器的幅一频特性应是主瓣杂波频谱包络的倒数,以使通过滤波器后输出的杂波频谱可近似为平坦的特性。
      从匹配滤波理论的角度来看,由于主瓣杂波是色噪声,因此主瓣杂波抑制滤波器相当于一个白化滤波器,经过主瓣杂波抑制之后,后面的多普勒滤波器可以按照白噪声中的匹配滤波理论来进行设计。
    3、高度杂波的滤除
      高度杂波是由地面的垂直反射所形成的杂波,它比漫反射所形成的旁瓣杂波要强得多。当载机水平飞行时,高度杂波的多普勒频移为0,通常可以采用一个单独的固定频率抑制滤波器—零多普勒频率滤波器来滤除它。
      还可以用以下两种方式来滤除:其一是使用可防止检测高度线杂波专用的CFAR电路;其二是使用航迹消隐器除去最后输出的高度线杂波。
    4、多普勒滤波器组
    这里写图片描述
    ①多普勒滤波器组是覆盖预期的目标多普勒频移范围的一组邻接的窄带滤波器。
    ②多普勒滤波器组可以设在中频,也可以设在视频。
    ③每个滤波器的带宽应设计得尽量与回波信号的谱线宽度相匹配。
    ④多普勒滤波器组基本上都是采用数字滤波方法来实现。
    5、恒虚警处理
      根据杂波环境的不同及对雷达性能要求的不同,在PD雷达中可以采用参量法或非参量法CFAR处理技术,根据背景于扰电平来自动调节检测门限,以达到使虚警概率恒定的目的。

    5.4.3 滤波器组的具体处理方法

    1、中频信号处理
    距离门的作用:
    ①距离量化,并由此提取距离信息;
    ②消除本距离单元以外的杂波,首先从时间上进行分辨。
    这里写图片描述
      每一个距离门对应一个距离单元和相应的一条距离通道,每一通道有一单边带滤波器,用它来选取中心频率附近目标可能出现的频率范围,然后送到窄带滤波器去提取速度信息。单边带滤波器输出到窄带滤波器组以前尚需经过领多普勒滤波和主瓣杂波滤波。信号经主瓣杂波滤波器后,其输出再次和杂波跟踪振荡器混频,使信号的频谱位置复原到原来的位置上,便于下面继续在中频范围内进行多普勒信号处理。
      N个相干脉冲通过宽度为1/NTr的窄带滤波器相当于对N个回波脉冲进行相参积累,覆盖全部测速范围fr所需要的滤波器数目为
      

    fr1/NTr=N

    2、零中频信号处理
      零中频信号处理就是讲中频信号经相干检波器后变成视频信号进行滤波,为避免检波引起的频谱折叠,保持区分正负频率的能力,采用正交双通道处理。
    3、窄带滤波器组实现
      当目标速度未知时,应采用邻接的窄带多普勒滤波器组来覆盖目标可能出现的所有多普勒频率范围。其实现方法有模拟式、数字式(快速傅里叶变换)和近代模拟式(线性调频频谱变换(CT))三种。

    5.5 脉冲多普勒雷达的数据处理

    5.5.1 脉冲多普勒雷达的跟踪

    1、单目标跟踪系统
    (1)角度跟踪系统
      PD雷达的单目标角度跟踪一与常规雷达相同,可用顺序波束序列转换或单脉冲体制。
    (2)速度(多普勒频率)跟踪系统
      频率跟踪环路根据频率敏感元件的不同可以分为锁频式和锁相式两种。
      ①锁相系统是测量多普勒频率的优选装置,其理论上的稳态测速误差为0。
      ②为了保证锁相系统处于跟踪状态,压控振荡器的相位总得基本同步地跟踪信号相位变化,它们之间的误差不能超过信号周期的几分之一。因此,对雷达设备的稳定性提出较高的要求。
      ③当系统的带宽一定时,锁相系统就存在最大可跟踪目标加速度的限制,而在锁频系统中就无此限制。
    (3)距离跟踪系统
      在这种跟踪方案中,距离门用一个低频参考信号进行脉冲位置调制或跳动其脉冲宽度的一小部分。跨过多个脉冲周期的跟踪可以用一个具有比一个脉冲周期长的时间基准的距离跟踪器实现。
    2、四维分辨跟踪系统
    综合距离、速度、两个角度(方位角和俯仰角)等四个跟踪回路。就构成具有四维分辨能力的跟踪系统。
    角度上的分辨由角跟踪系统和波束宽度决定,跟踪伺服系统使天线对准目标。距离上的分辨率由距离跟踪系统和距离门的宽度决定。
    ①四维分辨系统的主要优点是能在速度坐标即多普勒频率上分辨目标。
    ②四维分辨系统的另一个重要的特性是由于加了窄带滤波器,只能通过相应的一根回波谱线,从而滤除噪声,所以可以提高信噪比。
    ③四维分辨系统的上述优点决定了它具有很强的抗干扰能力。
    3、多目标跟踪系统
    多目标跟踪可 由多路接收通道实现。

    5.5.2 测距和测速模糊的解算

    1、测距和测速模糊的基本概念
      当脉冲重复频率很高时,对应一个发射脉冲产生的回波可能要经过几个周期以后才能被收到,若目标的真是距离是R,而按照常规方法读出的目标距离是Ra,产生的误差是

    R=n(c/2fr)

    上述由于目标回波的延迟时间可能大于脉冲重复周期,使收发脉冲的对应关系发生混乱,同一距离读数可能对应几个目标真实距离的现象叫做距离模糊,距离读数Ra叫做模糊距离。
      当脉冲重复频率较低时,目标回波的多普勒频移可能超过脉冲重复频率,使回波谱线与发射信号的谱线的对应关系发生混乱。相差nfr的目标多普勒频移会读做同样的多普勒频移,测量出的一个速度可能对应几种真实速度,这种现象叫做测速模糊。
      脉冲多普勒雷达的最大不模糊距离和速度有如下限制,即

    Rmaxvmax=λc/8

    2、测距模糊解算
    (1)多重脉冲重复频率测距法
      采用双重PRF所能达到的最大无模糊距离Ru,maxfr1fr2最大公约频率1/tu决定。
    (2)连续改变脉冲重复频率测距法
      在满足把目标回波保持在每个脉冲周期的中点的前提下,测出距离波门的移动速度R(t)、PRF的瞬时值fr(t)和PRF的变化率fr(t)根据R(t)=R(t)fr(t)fr(t)就可以计算出目标的无模糊距离。
    (3)射频调制测距法
      雷达发射的高重复频率脉冲串的载频分为两部分:一部分载频不变,另一部分载频随时间线性增长,频率变化率是kFM,非调频部分的信号用于测量目标回波的多普勒频移fd,当雷达工作于线性调频状态时,目标回波除了多普勒频移外,还有一个与距离成正比的频移f=fd2fd1。目标回波的真实延时为f/kFM,所以可以求出目标的真实距离为R=cf/2kFM
    (4)脉冲调制测距法
      脉冲调制测距法是通过改变发射脉冲的波形参数(幅度、宽度和位置),对接收到的回波信号加以识别和计算处理来消除距离模糊的方法。
    3、测速模糊的解算
      多重PRF信号可以用来消除测速模糊,利用多普勒滤波器组在每个重复频率下测出模糊距离,再根据余弦定理,推导出目标真实相对速度。
      另一种方法是利用距离跟踪的粗略微分数据来消除测速模糊。

    5.6 脉冲多普勒雷达的距离性能

    5.6.1 影响PD雷达距离方程的主要因素

    1、发射脉冲遮挡频率
    当采用高或中脉冲重复频率时,测距都会产生模糊,也就是目标回波的延时可能超过一个脉冲重复周期。
    当回波全部被发射机脉冲挡住时,影响最为严重,使作用距离降为0——称为盲距。
    2、跨越效应
    回波脉冲不是完全进入一个距离门,而是跨接在两个相邻的距离门中间——产生了跨越。
    跨越一般和遮挡一起用统计平均的方法研究。
    3、频域处理和带宽的影响
    在主瓣杂波被滤除的同时,那些多普勒频移正好落在主瓣杂波的频率上的运动目标回波也被滤除了。这就是频域中的遮挡现象。
    回波谱线跨越子滤波器引起的损失比起回波对距离门跨越的损失要小的多。

    5.6.2 PD雷达的距离方程

    1、无杂波区的距离方程
    当运动目标的多普勒频移落入无杂波区时,在检测中与目标回波抗衡的只有系统噪声。

    R04=PavG2λ2σDAV(4π)3κT0BnNFL

    DAVPD雷达损失系数,NF系统噪声系数。
    当要求信噪比为S/N时作用距离R和R0的关系为

    R=R0S/N4

    2、旁瓣杂波区的距离方程
    若目标回波的多普勒频移落在旁瓣杂波区,检测时与信号抗衡的分量是杂波与噪声之和。此时PD雷达信噪比为1的距离方程可表示为:

    R04=PavG2λ2σDAV(4π)3[C+κT0BnNF]L

    5.6.3 PD雷达与常见脉冲雷达距离性能的比较

    在输出信噪比都为1的情况下,PD雷达在有杂波十扰但目标回波多普勒频移落在无杂波区时,考虑了遮挡和跨越损失后的平均作用距离,比常规脉冲雷达没有杂波于扰时的作用距离还要大。若常规脉冲雷达也工作在同样杂波于扰情况下,距离性能还要大大变坏。
    PD雷达距离性能的优越性主要是由它的工作体制和信号处理方式决定的。
    ①PD雷达采用相参体制,利用了目标运动的多普勒效应,检测实质上是在频域进行的。
    ②信号处理采用距离门和多普勒窄带滤波,实质上是相参积累器。
    ③常规脉冲雷达一般采用非相参体制,接收机的特性近似匹配于单个脉冲。
    若考虑增加非相参积累,信噪比将得到改善,则两种雷达在无杂波干扰时的距离性能将趋与接近。

    展开全文
  • 脉冲多普勒雷达信号处理_有源干扰的建模仿真
  • 解距离模糊是中频脉冲重复频率的脉冲多普勒雷达关键技术之一。提出了采用快速余差查表法有效解决PD雷达距离模糊问题的算法。该算法的运算量较少,实时处理能力强。以3重CPI进行仿真实验,表明该算法能够保证低虚警...
  • 本书详细的介绍了脉冲多普勒雷达的工作原理和结构,介绍了脉冲多普勒雷达的杂波模型级处理方法以及PD雷达的信号处理和数据处理。
  • 根据脉冲多普勒雷达在无模糊测速条件下的信号处理方法分析了雷达的回波特性,并且通过计算机仿真,验证了利用所述方法得到的目标物理特性与雷达回波特性.结果表明,对于近程高仰角运动目标,从目标物理特性的角度,其径向...
  • 基于Simulink的脉冲多普勒雷达系统建模仿真
  • 本文讨论的弹载脉冲多普勒雷达目标模拟器主要是在外场静态联试时为雷达提供模拟动态目标回波信号,以检查其截获跟踪性能。
  • 脉冲多普勒雷达抗拖曳式干扰方法研究,廖云,何松华,首先对拖曳式干扰的特点进行了分析;然后提出了一种在中远距离情况下通过适当的制导策略、在载机逃离波束之前实现载机和诱饵多普
  • 传统的脉冲多普勒雷达存在严重的测距测速模糊和盲区效应。该文结合压缩感知理论,考虑在正常脉冲重复间隔(Pulse Repetition Interval, PRI)上叠加一个随机扰动,并把PRI的随机变化巧妙转化为稀疏观测矩阵的受限等距...
  • 雷达进行PD测速主要是利用了目标回波中携带的多普勒信息,在频域实现目标和杂波的分离,它可以把位于特定距离上、具有特定多普勒频移的目标回波检测出来,而把其他的杂波和干扰滤除。因此要求雷达必须具备很强的抑制...
  • 脉冲多普勒雷达系统是最常见的雷达系统之一,尤其是在军事应用中。这些雷达主要用于估计目标的两个基本参数:距离和多普勒频率。估计这些参数的常用方法是匹配滤波、脉冲多普勒处理,最后是恒虚警率(CFAR)算法。...
  • 利用Simulink 语言,对脉冲多普勒雷达系统进行了建模,仿真结果还行

空空如也

空空如也

1 2 3 4 5 ... 13
收藏数 245
精华内容 98
关键字:

脉冲多普勒雷达