Road object detection using Yolov3 and Kitti dataset

Abstract

Road objects (such as pedestrians and vehicles) detection is a very important step to enhance road safety and achieve autonomous driving. Many on-vehicle sensors, such as radars, lidars and ultrasonic sensors, are used to detect surrounding objects. However, cameras are widely used sensors for road objects detection for the rich information they provide and their inexpensive prices with compared to other sensors. Machine learning and computer vision algorithms are utilized to classify objects in the collected images and videos. There are many computer vision algorithms proposed for image and video object detection, e.g. logistic regression and SVM with feature extraction. However, Convolutional Neural Network (CNN) algorithms showed a high detection accuracy compared to other approaches. This research implements You Only Look Once (YOLO) algorithm that uses Draknet-53 CNN to detect four classes: pedestrians, vehicles, trucks and cyclists. The model is trained using Kitti images dataset which is collected from public roads using vehicle's front looking camera. The algorithm is tested, and detection results are presented.