-
公开(公告)号：US20180260702A1
公开(公告)日：2018-09-13
申请号：US15819336
申请日：2017-11-21
发明人： Kohei YAMAMOTO , Kurato MAENO
CPC分类号： G06N3/08 , G01S7/417 , G01S13/931 , G01S2007/356 , G06N3/04 , G06N3/0454 , G06N3/084
摘要： It is possible to improve estimation accuracy with regard to data in which significance is attached to a relative phase.Provided is an information processing device including an estimation unit configured to estimate a status by using a neural network. The neural network includes a first complex-valued neural network to which complex data is input, a phase difference computation layer from which phase difference for each element between a plurality of sets with regard to the complex data is output, and a second complex-valued neural network from which complex data is output on the basis of the phase difference.
-
公开(公告)号：US20180082137A1
公开(公告)日：2018-03-22
申请号：US15689755
申请日：2017-08-29
发明人： Iain Melvin , Eric Cosatto , Igor Durdanovic , Hans Peter Graf
CPC分类号： G01S13/931 , B60G2400/823 , B60Q9/008 , B60R1/00 , B60R2300/301 , B60R2300/8093 , B60W30/09 , B60W2420/42 , B60W2420/52 , G01S7/20 , G01S7/2955 , G01S7/417 , G01S13/867 , G01S17/936 , G01S2013/936 , G01S2013/9367 , G01S2013/9375 , G06K9/00805 , G06K9/46 , G06K9/6215 , G06K9/6232 , G06N3/0454 , G06N3/08 , G06N3/084
摘要： A computer-implemented method and system are provided for driving assistance. The system includes an image capture device configured to capture image data relative to an outward view from a motor vehicle. The system further includes a processor configured to detect and localize objects, in a real-world map space, from the image data using a trainable object localization Convolutional Neural Network (CNN). The CNN is trained to detect and localize the objects from image and radar pairs that include the image data and radar data for different driving scenes of a natural driving environment. The processor is further configured to provide a user-perceptible object detection result to a user of the motor vehicle.
-
公开(公告)号：US20170371035A1
公开(公告)日：2017-12-28
申请号：US15193373
申请日：2016-06-27
申请人： Kiomars Anvari
发明人： Kiomars Anvari
CPC分类号： G01S13/867 , G01S7/417 , G01S13/62 , G01S13/93 , G06K9/00664
摘要： A protection and guidance gear or equipment for monitoring and detection of impacts from surrounding objects. The protection and guidance gear or equipment comprises of a number of image sensors to record images, use images to estimate and calculate environment parameters, a number of wireless sensors to measure environment parameters, and a controller with artificial intelligence to process the information data from image processor and wireless sensor. The controller utilizes the received information data from image processors and wireless sensor to evaluate various environmental parameters which can be used to activate certain functions and devices.
-
公开(公告)号：US20170315226A1
公开(公告)日：2017-11-02
申请号：US15611277
申请日：2017-06-01
摘要： Provided are methods of using electromagnetic waves for detecting metal and/or dielectric objects. Methods include directing microwave and/or mm wave radiation in a predetermined direction using a transmission apparatus, including a transmission element; receiving radiation from an entity resulting from the transmitted radiation using a detection apparatus; and generating one or more detection signals in the frequency domain using the detection apparatus. Methods may include operating a controller,' wherein operating the controller includes causing the transmitted radiation to be swept over a predetermined range of frequencies, performing a transform operation on the detection signal(s) to generate one or more transformed signals in the time domain, and determining, from one or more features of the transformed signal, one or more dimensions of a metallic or dielectric object upon which the transmitted radiation is incident. A system and method for remote detection and/or identification of a metallic threat object using late time response (LTR) signals is also disclosed.
-
公开(公告)号：US20170307735A1
公开(公告)日：2017-10-26
申请号：US15262947
申请日：2016-09-12
申请人： Mohsen Rohani , Song Zhang , Hao Chen
发明人： Mohsen Rohani , Song Zhang , Hao Chen
CPC分类号： G01S7/417 , G01S13/865 , G01S13/867 , G01S13/89 , G01S17/89 , G06N20/00
摘要： A method and system for using one or more radar systems for object detection based on machine learning in an environment is disclosed. A scanning radar or combination of radars mounted on a vehicle or moving object scans the environment to acquire information. The radar data may be a 3D point cloud, 2D radar image or 3D radar image. The radar data may also be combined with data from LIDAR, vision or both. A machine learning algorithm is then applied to the acquired data to detect dynamic or static objects within the environment, and identify at least one object feature comprising one of a type, location, distance, orientation, size or speed of an object.
-
公开(公告)号：US09746552B2
公开(公告)日：2017-08-29
申请号：US14873807
申请日：2015-10-02
摘要： Provided are methods of using electromagnetic waves for detecting metal and/or dielectric objects. Methods include directing microwave and/or mm wave radiation in a predetermined direction using a transmission apparatus, including a transmission element; receiving radiation from an entity resulting from the transmitted radiation using a detection apparatus; and generating one or more detection signals in the frequency domain using the detection apparatus. Methods may include operating a controller, wherein operating the controller includes causing the transmitted radiation to be swept over a predetermined range of frequencies, performing a transform operation on the detection signal(s) to generate one or more transformed signals in the time domain, and determining, from one or more features of the transformed signal, one or more dimensions of a metallic or dielectric object upon which the transmitted radiation is incident. A system and method for remote detection and/or identification of a metallic threat object using late time response (LTR) signals is also disclosed.
-
公开(公告)号：US09701265B2
公开(公告)日：2017-07-11
申请号：US14968027
申请日：2015-12-14
发明人： David S Breed
IPC分类号： B60R16/037 , B60R25/25 , B60R21/013 , B60R21/0136 , B60R21/015 , B60R21/0132 , B60R21/0134 , B60R21/203 , B60R21/2165 , B60R21/276 , B60R22/20 , H04W4/00 , H01Q1/32 , B60N2/48 , B60N2/66 , B60N2/00 , B60N2/015 , B60N2/06 , B60N2/28 , G01G19/414 , G01M5/00 , G01F23/00 , G01F23/20 , G01F23/296 , G06F3/02 , G06F3/023 , G06K9/00 , G07C5/00 , G07C5/08 , G08B25/01 , B60C23/00 , B60C29/06 , B60N2/02 , G01S7/41 , B60R1/12 , B60R21/00 , B60R21/231 , B60R21/26 , B60R22/28 , B60R22/46 , B60R22/48 , G01S13/93 , G08B13/196
CPC分类号： B60R16/037 , B60C23/00 , B60C23/0479 , B60C29/066 , B60N2/002 , B60N2/015 , B60N2/0232 , B60N2/0244 , B60N2/0248 , B60N2/0252 , B60N2/0276 , B60N2/067 , B60N2/28 , B60N2/2806 , B60N2/2863 , B60N2/66 , B60N2/829 , B60N2/853 , B60N2/888 , B60N2002/0268 , B60N2002/0272 , B60R21/013 , B60R21/0132 , B60R21/0134 , B60R21/0136 , B60R21/01516 , B60R21/01526 , B60R21/0153 , B60R21/01532 , B60R21/01534 , B60R21/01536 , B60R21/01538 , B60R21/01542 , B60R21/01544 , B60R21/01546 , B60R21/01548 , B60R21/01552 , B60R21/01554 , B60R21/203 , B60R21/21656 , B60R21/276 , B60R22/201 , B60R25/25 , B60R2001/1223 , B60R2001/1253 , B60R2021/0027 , B60R2021/01315 , B60R2021/23153 , B60R2021/26094 , B60R2021/2765 , B60R2022/208 , B60R2022/288 , B60R2022/4685 , B60R2022/4825 , G01F23/0076 , G01F23/20 , G01F23/2962 , G01G19/4142 , G01M5/0008 , G01S7/417 , G01S2013/9321 , G01S2013/9332 , G01S2013/936 , G06F3/0219 , G06F3/0233 , G06F3/0237 , G06F3/0238 , G06K9/00362 , G06K9/00624 , G06K9/00832 , G07C5/008 , G07C5/0808 , G08B13/19647 , G08B25/016 , H01Q1/3291 , H04W4/80
摘要： Method for controlling a vehicle including a smartphone-engaging coupling element. Data about operational status of the vehicle is transferred from one or more vehicle-resident systems to a smartphone when the smartphone is engaged with the coupling element. Commands are received by the vehicle from the smartphone when the smartphone is engaged with the coupling element, which commands being based in part on data previously transferred from the vehicle-resident system(s) to the smartphone when the smartphone is engaged with the coupling element. A vehicular system, e.g., seat positioning system, mirror positioning system, passenger compartment temperature control system, route guidance or navigation system, changes its operation in accordance with the commands received by the vehicle from the smartphone when the smartphone is engaged with the coupling element.
-
公开(公告)号：US20170168156A1
公开(公告)日：2017-06-15
申请号：US15118216
申请日：2015-02-03
CPC分类号： G01S13/931 , G01S7/024 , G01S7/411 , G01S7/417 , G01S13/862 , G01S13/867 , G01S13/87
摘要： A system for use in a vehicle determining the type of terrain ahead of the vehicle, the system comprising; a processor configured to receive sensor output data from a plurality of vehicle-mounted sensors, including at least one radar sensor and at least one acoustic sensor, each for receiving a reflected signal from the terrain ahead of the vehicle; and a data memory configured to store pre-determined data relating sensor output data, for the or each acoustic sensor and the or each radar sensor, to a terrain type; wherein the processor is configured to compare the sensor output data with the pre-determined data to determine an indication of the terrain type corresponding to the sensor output data.
-
公开(公告)号：US20160019458A1
公开(公告)日：2016-01-21
申请号：US14794376
申请日：2015-07-08
CPC分类号： G06N3/0454 , G01S7/417 , G01S13/90 , G01S13/9035
摘要： 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.
摘要翻译： 本发明涉及用于检测雷达图像流中物体的系统和方法。 本发明的实施例可以从雷达传感器接收数据流，并使用深层神经网络将接收的数据流转换成一组语义标签，其中每个语义标签对应于雷达数据流中的一个对象，深层神经网络具有 确定。 运行深层神经网络的处理单元可以与雷达传感器一起配置在机载车辆上。 处理单元可配置强大的高速图形处理单元或现场可编程门阵列，其尺寸，重量和功率要求较低。 本发明的实施例还涉及为利用检测器和物体识别级联实时分析雷达图像流的对象识别训练系统提供创新的进步。 对象识别级联可以包括至少一个识别器，其从检测器接收非背景图像块流，并且自动地将一个或多个语义标签分配给每个非背景图像块。 在一些实施例中，还可以并入用于斑块背景分析的单独识别器。 根据级联的设计，可能有多个检测器和多个识别器。 本发明的实施例还包括定制深层神经网络算法以成功处理雷达图像的新方法，利用诸如归一化，采样，数据增加，移动，级联架构和标签协调之类的技术。
-
公开(公告)号：US20150260838A1
公开(公告)日：2015-09-17
申请号：US14726776
申请日：2015-06-01
CPC分类号： G01S7/41 , G01S7/20 , G01S7/411 , G01S7/417 , G01S13/02 , G01S13/66 , G01S13/723 , G01S13/878 , G01S13/89
摘要： Techniques are provided for sparse array RF imaging for surveillance applications. Objects in a three dimensional (3-D) image-data-set obtained from multi-static radio frequency detection data are classified, for example, as human or non-human. One or more geometric image features are extracted from the image-data-set that support a target classification process; and the one or more objects are classified as a threat based on a parametric evaluation of the extracted geometric image features.
摘要翻译： 为监控应用提供了稀疏阵列RF成像技术。 从多静态射频检测数据获得的三维（3-D）图像数据集中的对象被分类为例如人或非人。 从支持目标分类处理的图像数据集中提取一个或多个几何图像特征; 并且基于对所提取的几何图像特征的参数估计，将一个或多个对象分类为威胁。
-
-
-
-
-
-
-
-
-
搜索结果
432 条记录 (耗时 0.034 秒)
