Abstract: A method of detecting and tracking objects includes (a) obtaining point-cloud data captured by camera sensors on a vehicle travelling along a road surface, (b) compressing the point-cloud data to bird's-eye-view (BEV) data representing a view along a BEV direction oriented approximately perpendicular to the road surface, the BEV data representing the objects on a BEV plane oriented approximately parallel the road surface, (c) establishing a grid of cells for the BEV plane, (d) for each cell, determining occupancy values of the cell for a time tn and performing noise reduction by assigning weights to the cell based on predicted occupancy values of the cell for the time tn and on occupancy values of the cell for a previous time tn?1, and (e) outputting to a controller of the vehicle, in real time or nearly real time, an occupancy evidence map of objects in the vehicle's environment.

Abstract: A system and a method are provided for repairing a depth map. The repairing includes representing pixels of the depth map using a matrix H having values corresponding to depths, the pixels including hole pixels and non-hole pixels; determining a confidence mask matrix C for the depth map; for each hole pixel, determining a kernel G of neighboring pixels, the neighboring pixels having values corresponding to a predetermined distribution, and convolving the kernel G with corresponding portions of the matrix C and the matrix H to obtain an estimated depth; generating a corrected matrix ? in which values for non-hole pixels are retained and in which the hole pixels have values corresponding to their estimated depths. The estimated depths may be normalized based on the matrix C. An updated depth map based on the corrected matrix ? may be outputted to a control system of a vehicle.