Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm

Jin Tao; Jianting Shi; Yinan Chen; Jiancai Wang

Machine Learning and Intelligent Communications. 6th EAI International Conference, MLICOM 2021, Virtual Event, November 2021, Proceedings

Research Article

Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm

Download

2 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-031-04409-0_21,
    author={Jin Tao and Jianting Shi and Yinan Chen and Jiancai Wang},
    title={Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm},
    proceedings={Machine Learning and Intelligent Communications. 6th EAI International Conference, MLICOM 2021, Virtual Event, November 2021, Proceedings},
    proceedings_a={MLICOM},
    year={2022},
    month={5},
    keywords={Infrared image YOLOv4 Pedestrian detection Network structure YOLOv3},
    doi={10.1007/978-3-031-04409-0_21}
}

Jin Tao
Jianting Shi
Yinan Chen
Jiancai Wang
Year: 2022
Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm
MLICOM
Springer
DOI: 10.1007/978-3-031-04409-0_21

Jin Tao¹^,*, Jianting Shi², Yinan Chen², Jiancai Wang³

1: Graduate College, Heilongjiang University of Science and Technology
2: School of Computer and Information Engineering, Heilongjiang University of Science and Technology
3: Academic Affairs Office, Heilongjiang University of Science and Technology

*Contact email: taojin@usth.edu.cn

Abstract

Because pedestrians are always in the active state, each target is at a different distance from the camera, resulting in a certain difference in the size of similar targets in the figure. Therefore, an infrared pedestrian detection algorithm is proposed in the paper based on Yolov4 algorithm. Aiming at the problems of low recognition rate and high background influence in infrared image downlink human small target detection, the network structure of YOLOv4 is optimized. Compared with YOLOv4 and YOLOv3, the mean Average Precision is improved by 0.53% and 1.05%, which improves the detection accuracy in a certain extent.

Keywords: Infrared image YOLOv4 Pedestrian detection Network structure YOLOv3

Published: 2022-05-18
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-031-04409-0_21

Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm

Abstract

About EAI

Community

Publish with EAI