OS31-3 An improved network for pedestrian-vehicle detection based on YOLOv7

Title:	OS31-3 An improved network for pedestrian-vehicle detection based on YOLOv7
Publication:	ICAROB2023
Volume:	28
Pages:	803-807
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2023.OS31-3
Author(s):	Zhihui Chen, Xiaoyan Chen, Keying Ren
Publication Date:	February 9, 2023
Keywords:	YOLOv7, target detection, Swin Transformer, CNeB
Abstract:	With the continuous development and improvement of information technology, target detection has gradually attracted people's attention. Therefore, object detection has become more important. In this paper, a large number of experiments have been made to improve the detection accuracy of pedestrians, vehicles and license plates in cities. The improved algorithm based on YOLOv7 was used to conduct a large number of experiments on the urban pedestrian vehicle dataset. Experiments show that new improvements have improved detection accuracy.
PDF File:	https://alife-robotics.co.jp/members2023/icarob/data/html/data/OS/OS31/OS31-3.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/