Object detection and object tracking in front of the vehicle using front view camera

Modern vehicles are equipped with the different systems that help driver in the driving process ensuring safer and more comfortable driving. These systems are called Advanced Driver Assistance Systems (ADAS) and are step toward fully autonomous driving. The integral part of autonomous driving is an...

Full description

Saved in:

Bibliographic Details
Published in:	2019 Zooming Innovation in Consumer Technologies Conference (ZINC) pp. 27 - 32
Main Authors:	Ciberlin, Juraj, Grbic, Ratko, Teslic, Nikola, Pilipovic, Milos
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.05.2019
Subjects:	advanced driver assistance systems Autonomous vehicles Classification algorithms Detectors Machine learning algorithms Object detection Object tracking Viola-Jones algorithm
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Modern vehicles are equipped with the different systems that help driver in the driving process ensuring safer and more comfortable driving. These systems are called Advanced Driver Assistance Systems (ADAS) and are step toward fully autonomous driving. The integral part of autonomous driving is an object detection and tracking by using front view camera which provides necessary information for emergency braking, collision avoidance, path planning, etc. In this paper, one possible approach to object detection and tracking in autonomous driving is presented. Two object detection methods are implemented and tested: Viola-Jones algorithm and YOLOv3. The Viola-Jones algorithm is used to create object detectors which detections are tracked in a video sequence. Nine object detectors were trained and they are divided into four groups (vehicle detectors, pedestrian detector, traffic light detector and traffic sign detectors). In second case, the YOLOv3 model was used for object detection. Both methods are evaluated in terms of accuracy and processing speed. For the purpose of object tracking, Median Flow tracking method and correlation tracking method are implemented and evaluated.
DOI:	10.1109/ZINC.2019.8769367