An obstacle detection method based on the fusion of millimeter wave radar and machine vision sensor information is proposed. First, the joint calibration of the millimeter-wave radar and the camera is carried out to realize the space-time synchronization of the radar and the image data, the target position detected by the radar is accurately projected into the image, and then a method of generating the radar target interest area is proposed, and the image information Use the frame difference method to detect the moving objects in the image to get the detection area. Finally, the radar detection area is compared with the machine vision detection area to calculate the coincidence degree, and the target is initially classified as a pedestrian or a vehicle according to the coincidence degree. Experimental results show that this method can well realize the joint detection of obstacles by millimeter-wave radar and machine vision, and makes up for the shortcomings of single sensors in obstacle detection.
