@inproceedings{0a04f9bb949244a3ab91a8fcdfef93fb,
title = "Deep Learning-Based Autonomous Vehicle on SoC",
abstract = "This paper presents a Zynq SoC-based autonomous driving system with traditional image processing and Deep Learning Processing Units (DPUs). A 1/5-scale kid's electric vehicle was modified and tested on an autonomous driving track. The traditional method with Hough transform achieved \textasciitilde{}13.64 FPS but was vulnerable to environmental noise. In contrast, the DPU-based system integrated three optimized models: UFLD (6.29 FPS), YOLOv3-tiny (3.54 FPS original, 85.47 FPS optimized), and YOLACT (2.90 FPS original, 20.27 FPS optimized). Optimizations included quantization, input resizing, and backbone replacement. The results support real-time AI perception on embedded systems through DPU optimization. This work may contribute to future research on AI accelerator-based autonomous driving systems.",
keywords = "Autonomous Driving, Deep Learning Processing Unit (DPU), Lane Detection, ZYNQ-SoC",
author = "Hwang, \{Gyu Hyeon\} and Oh, \{Ho Bin\} and Choi, \{Min Kwon\} and Sim, \{Hyeon Jin\} and Hong, \{Hyeong Keun\} and \{Wook Jeon\}, Jae",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2025 ; Conference date: 07-07-2025 Through 10-07-2025",
year = "2025",
doi = "10.1109/ITC-CSCC66376.2025.11137739",
language = "English",
series = "2025 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2025 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2025",
}