Data from Department of Electronic and Optical Engineering Provide New Insights into Networks (Spgcn: Ground Filtering Method Based On Superpoint Graph Convolution Neural Network for Vehicle Lidar)

摘要

By a News Reporter-Staff News Editor at Network Daily News - Research findings on Networks are discussed in a new report. According to news reporting originating in Hebei, People’s Republic of China, by NewsRx journalists, research stated, “Light detection and ranging (LiDAR) point clouds are sparse, unstructured, and disordered; hence, traditional convolutional neural networks are unsuitable for direct application in point-cloud data processing. Graph convolution neural networks (GCNs) can be used to process point-cloud data having the aforementioned characteristics; however, they are inefficient when the adjacent relationship of the point cloud is uncertain and adjacency-matrix elements are abundant.”