Pedestrian Detection in Driverless Cars: Comparison on Versions of CNN

Pedestrian detection is one of the useful branch of object detection. Many works have already been developed to polish acquisition of detection approaches. The improved performance time and precision of the detection approaches which enables to reliably applied to autonomous vehicles to avoid accidents. This paper presents a performance comparison on pedestrian detection using RCNN, FAST-RCNN, and Faster- RCNN.