Semantic Segmentation of Radar Data

专利名称：Semantic Segmentation of Radar Data发明人：Ankit Laddha,Carlos Vallespi-Gonzalez,Duncan Blake Barber,JacobWhite,Anurag Kumar

申请号：US16575855申请日：20190919

公开号：US20210003665A1公开日：20210107

专利附图：

摘要：Systems, methods, tangible non-transitory computer-readable media, anddevices associated with sensor output segmentation are provided. For example, sensor

data can be accessed. The sensor data can include sensor data returns representative ofan environment detected by a sensor across the sensor's field of view. Each sensor datareturn can be associated with a respective bin of a plurality of bins corresponding to thefield of view of the sensor. Each bin can correspond to a different portion of the sensor'sfield of view. Channels can be generated for each of the plurality of bins and can includedata indicative of a range and an azimuth associated with a sensor data return associatedwith each bin. Furthermore, a semantic segment of a portion of the sensor data can begenerated by inputting the channels for each bin into a machine-learned segmentationmodel trained to generate an output including the semantic segment.

申请人：UATC, LLC

地址：San Francisco CA US

国籍：US

更多信息请下载全文后查看