MOVING VEHICLES DETECTION AND RECOGNITION BASED ON DEEP-LEARNING ALGORITHM AND ARTIFICIAL INTELLIGENCE FOR INTELLIGENT DRIVER ASSISTANCE SYSTEMS

Vu Hong Son; Nguyen Van Hien

Vu Hong Son Hung Yen University of Technology and Education
Nguyen Van Hien Hung Yen University of Technology and Education

Keywords: advanced driver assistance system, YOLO recognition model, deep-learning algorithm and artificial intelligence

Abstract

Advanced driver assistance systems (ADASs) play an important role in camera-only active safety systems and intelligent autonomous vehicles. For these applications, real-time and reliable detection performance is required. However, moving vehicles detection is challenging due to their density of vehicles illumination variations, articulation, partial occlusion, shadow, and complicated background in the realworld environments. Besides, real-time detection and recognition performance is also critical. This paper proposes a model using deep-learning algorithm and artigical intelligence in order to increase accuracy and response time for ADASs. Accordingly, we first propose the YOLO (You Only Look One) model along with our own sample datasets and training algorithm. Experimental results are then are conducted in a NVIDIA Jetson TX2 embedded computer. Experimental results show that the proposed method achieves a speedup of at least 1.6x with detection rate of 90 % for static cameras; and a speedup of at least 1.7x with detection rate of 67 % in high resolution images (1280x720) for moving cameras.

References

A. F. Agarap, Deep Learning using Rectified Linear Units (ReLU), arXiv:1803.08375, 2018.

G. S. W. Luger, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, ISBN 978-0-8053-4780-7, 26 July 2020.

M. Galvani, History and future of driver assistance”. IEEE Instrumentation Measurement Magazine, ISSN 1941-0123, 2019.

Ultralytics, “YOLOv5 Documentation”. Available: https://docs.ultralytics.com/.

S. D. R. G. A. F. Joseph Redmon, You Only Look Once: Unified, Real-Time Object Detection, arXiv:1506.02640 [cs.CV], 8 Jun 2015.

C. H. Thuc, “Precision, Recall và F1-score là gì?,” 23 02 2020. Available: https://caihuuthuc. wordpress.com/2020/02/23/precision-recall-va-f1-score-la-gi/.

D. Thuan, Evolution of YOLO Algorithm and YOLOv5: The State-of-the-art Object Detection, Bachelor thesis (3.092Mt), Spring 2021.

M. Schumann, A Book about Colab and related activities, ISBN 978-0-89439-085-2, 2015.

GeeksforGeeks, “Python Virtual Environment | Introduction,” 2020. Available: https://www.geeksforgeeks.