Accelerate High Resolution Image Pedestrian Detection With Non-Pedestrian Area Estimation

Detecting pedestrians at high speed in high resolution (HR) images is important for preventing collisions in autonomous vehicle. The HR images provide more detail information while creating a heavy computational load, resulting in slower detection speed. We find that the pedestrians are usually not present in the upper part of the HR image, due to the camera vertical field of view and the distance between pedestrian and camera. We named this area a non-pedestrian area (NPA). Therefore, we are able to reduce the calculation time while maintaining the detection accuracy by removing NPA from the HR image. According to this concept, we propose a novel pedestrian detection acceleration algorithm called Non-Pedestrian Area Estimation (NPAE). The NPAE algorithm estimates and removes non-pedestrian areas of the image, followed by pedestrian detection of the NPAE output image. Two datasets with three different resolution images are used to test our proposed NPAE algorithm on both GPU and CPU platforms. The RetinaNet is chosen as the reference pedestrian detector. Our algorithm increases the detection speed with 42% on the GPU platform and with 52% speed increase on the CPU platform, for the test images with a resolution of $1920 \times 1080$ pixel. In terms of detection accuracy, NPAE improves by up to 37.94% compared to classical data optimization acceleration methods. The detection accuracy results are well preserved in both platforms.