A Lightweight Motional Object Behavior Prediction System Harnessing Deep Learning Technology for Embedded ADAS Applications

Electronics

Wen-Chia Tsai¹  Jiun-In Guo¹  Kuan-Chou Chen¹  Jhih-Sheng Lai¹  Vinay M.Shivanna¹ 

[1] Department of Electronics Engineering and Institute of Electronics, National Yang Ming Chiao Tung University, Hsinchu 30010, Taiwan;

关键词: behavior recognition;    deep learning;    embedded ADAS applications;    lightweight CNN model;    pedestrian detection;    vehicle cut-in;   

DOI  :  10.3390/electronics10060692

来源: DOAJ

【 摘 要 】

This paper proposes a lightweight moving object prediction system to detect and recognize pedestrian crossings, vehicles cutting-in, and vehicles ahead applying emergency brakes based on a 3D Convolution network for behavior prediction. The proposed design significantly improves the performance of the conventional 3D convolution network (C3D) adapted to predict the behaviors employing behavior recognition network capable of performing object localization, which is pivotal in detecting the numerous moving objects’ behaviors, combining and verifying the detected objects with the results of the YOLO v3 detection model with that of the proposed C3D model. Since the proposed system is a lightweight CNN model requiring far lesser parameters, it can be efficiently realized on an embedded system for real-time applications. The proposed lightweight C3D model achieves 10 frames per second (FPS) on a NVIDIA Jetson AGX Xavier and yields over 92.8% accuracy in recognizing pedestrian crossing, over 94.3% accuracy in detecting vehicle cutting-in behavior, and over 95% accuracy for vehicles applying emergency brakes.

【 授权许可】

Unknown