Abstract

The World Health Organization estimates that well in excess of one million of lives are lost each year due to road traffic accidents. Since the human factor is the preeminent cause behind the traffic accidents, the development of reliable Advanced Driver Assistance Systems (ADASs) and Autonomous Vehicles (AVs) is seen by many as a possible solution to improve road safety. ADASs rely on the car perception system input that consists of camera(s), LIDAR and/or radar to detect pedestrians and other objects on the road. Hardware improvements as well as advances done in employing Deep Learning techniques for object detection popularized the Convolutional Neural Networks in the area of autonomous driving research and applications. However, the availability of quality and large datasets continues to be a most important contributor to the Deep Learning based model’s performance. With this in mind, this work analyses how a YOLO-based object detection architecture responded to limited data available for training and containing low-quality images. The work focused on pedestrian detection, since vulnerable road user’s safety is a major concern within AV and ADAS research communities. The proposed model was trained and tested on data gathered from Coventry, United Kingdom, city streets. The results show that the original YOLOv3 implementation reaches a 42.18% average precision (AP) and the main challenge was in detecting small objects. Network modifications were made and our final model, based on the original YOLOv3 implementation, achieved 51.6% AP. It is also demonstrated that the employed data augmentation approach is responsible for doubling the average precision of the final model.

Statistics