YOLOv3-mobile for Real-time Pedestrian Detection on Embedded GPU
Mohammad Alkhaleefah, Narendra Babu Tatini, Hung-Te Lee, Tan-Hsu Tan, Shang‐Chih Ma, Yang-Lang Chang · 2021
Pedestrian detection is one of the challenging tasks in the technology of autonomous driving. Recently, the object detection network of you only look once (YOLO), especially YOLOv3 and YOLOv3-tiny have demonstrated a high level of pedestrian detection performance on a powerful GPU card such as Pascal Titan X. However, it is still challenging to use YOLOv3 and YOLOv3-tiny on embedded GPU system due to their large network size. In this paper, we present a lightweight YOLOv3-mobile network by refining the architecture of YOLOv3-tiny to improve its pedestrian detection efficiency on embedded GPUs such as Nvidia Jetson TX1. The experimental results showed that the proposed framework can accelerate the frame rate per second (FPS) from 18 FPS to 37 FPS with comparable mean average precision (mAP).