Suraj Pattar

Robotics AI Research Engineer / Ph.D. in AI and Robotics / Data Scientist / 3D Printing Enthusiast

Pedestrian Detection Comparison

Keywords: Pedestrian Detection, Computer Vision, GTA5, OpenCV, MATLAB, Yolov4, Detectron2

Project Description

This is a quick comparison of various pedestrian detection/object detection frameworks. I’ve used a video from GTA5 to see how well the models used can generalize to a different domain (as they weren’t trained on such synthetic data).

The models/frameworks used for comparison are MATLAB(PedNet), OpenCV-HogDescriptor(Default People Detector), Yolov4(COCO Detection) and Detectron2(Faster-RCNN-COCO Detection).

(Link to the code coming soon).