会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Systems and methods for recognizing objects in radar imagery
    • US09978013B2
    • 2018-05-22
    • US14794376
    • 2015-07-08
    • Deep Learning Analytics, LLC
    • John Patrick Kaufhold
    • G01S13/90G06N3/04G01S7/41
    • G06N3/0454G01S7/417G01S13/90G01S13/9035
    • The present invention is directed to systems and methods for detecting objects in a radar image stream. Embodiments of the invention can receive a data stream from radar sensors and use a deep neural network to convert the received data stream into a set of semantic labels, where each semantic label corresponds to an object in the radar data stream that the deep neural network has identified. Processing units running the deep neural network may be collocated onboard an airborne vehicle along with the radar sensor(s). The processing units can be configured with powerful, high-speed graphics processing units or field-programmable gate arrays that are low in size, weight, and power requirements. Embodiments of the invention are also directed to providing innovative advances to object recognition training systems that utilize a detector and an object recognition cascade to analyze radar image streams in real time. The object recognition cascade can comprise at least one recognizer that receives a non-background stream of image patches from a detector and automatically assigns one or more semantic labels to each non-background image patch. In some embodiments, a separate recognizer for the background analysis of patches may also be incorporated. There may be multiple detectors and multiple recognizers, depending on the design of the cascade. Embodiments of the invention also include novel methods to tailor deep neural network algorithms to successfully process radar imagery, utilizing techniques such as normalization, sampling, data augmentation, foveation, cascade architectures, and label harmonization.
    • 8. 发明授权
    • SAR image formation
    • SAR图像形成
    • US09329264B2
    • 2016-05-03
    • US13768046
    • 2013-02-15
    • RAYTHEON COMPANY
    • Michael Y. Jin
    • G01S13/90G01S13/524G01S13/00G01S7/288
    • G01S13/9035G01S13/5242G01S13/90G01S2007/2883G01S2007/2886
    • SAR imaging method that includes applying PRF decimation to range-compressed IQ data to generate PRF-decimated range-compressed IQ data for each image block of an image and applying motion compensation to the PRF-decimated range-compressed IQ data to generate motion-compensated data for each image block. The method includes computing first stage image values at image grid point intersections of iso-range lines and vertical grid lines for each image bock based on the motion-compensated data for each image block. The method also includes computing second stage image values for the image grid point intersections by interpolation using the first stage image values at the image grid point intersections and correcting image phase of the second stage image values for the image grid point intersections to generate phase-corrected image values for each image block. The method includes generating a full-resolution SAR image by summing the phase-corrected image values for each image block.
    • SAR成像方法包括将PRF抽取应用于范围压缩的IQ数据,以生成图像的每个图像块的PRF抽取的范围压缩的IQ数据,并将运动补偿应用于PRF抽取的范围压缩的IQ数据以产生运动补偿 每个图像块的数据。 该方法包括基于每个图像块的运动补偿数据计算每个图像块的等距线和垂直网格线的图像网格点交点处的第一阶段图像值。 该方法还包括通过使用图像网格点交叉点处的第一级图像值进行插值并针对图像网格点交叉点校正第二级图像值的图像相位来计算图像网格点交点的第二级图像值,以生成相位校正 每个图像块的图像值。 该方法包括通过对每个图像块的相位校正图像值求和来产生全分辨率SAR图像。
    • 10. 发明授权
    • Higher order processing for synthetic aperture radar (SAR)
    • 合成孔径雷达(SAR)的高阶处理
    • US09261593B1
    • 2016-02-16
    • US13799837
    • 2013-03-13
    • Lockheed Martin Corporation
    • Paul D. MountcastleSvetlana M. Bachmann
    • G01S7/292G01S7/41G01S13/56G01S13/90
    • G01S7/292G01S7/41G01S7/411G01S7/412G01S7/415G01S13/56G01S13/9029G01S13/9035G01S2013/9088
    • A method for processing received return signals in a visual synthetic aperture radar (ViSAR) system is provided. The method includes receiving a plurality of pulsed radar return signals over a time period corresponding to a plurality of data frames. From this data, processing is performed to generate a SAR image for each single data frame of the plurality of data frames. In parallel, the radar pulses used to form the image frames are buffered into a longer pulse sequence that is used to perform the detection processing, including identifying targets as having characteristics associated with one or more predetermined motion classes according to phase changes sensed between data frames. A visual indication of targets associated with a predetermined motion class is generated, and overlaid onto one of the SAR images.
    • 提供了一种在视觉合成孔径雷达(ViSAR)系统中处理接收到的返回信号的方法。 该方法包括在对应于多个数据帧的时间段内接收多个脉冲雷达返回信号。 根据该数据,执行处理,以生成多个数据帧中的每个单个数据帧的SAR图像。 并行地,用于形成图像帧的雷达脉冲被缓冲到用于执行检测处理的较长脉冲序列中,包括根据在数据帧之间感测到的相位变化将目标识别为具有与一个或多个预定运动类别相关联的特性 。 产生与预定运动类别相关联的目标的视觉指示,并且覆盖在一个SAR图像上。