Education, Science, Technology, Innovation and Life
Open Access
Sign In

Application of YOLOv8 Image Recognition Model for Human Actions Recognition in the Surveillance Filed

Download as PDF

DOI: 10.23977/jipta.2024.070111 | Downloads: 55 | Views: 1321

Author(s)

Yuhan Lin 1, Jingchu Wang 1, Dong Lin 2

Affiliation(s)

1 Jinan University–University of Birmingham Joint Institute at Jinan University, Jinan University, Guangzhou, China
2 Hangzhou Hengsheng Digital Equipment Technology Co., Ltd, Hangzhou, China

Corresponding Author

Dong Lin

ABSTRACT

With the rapid advancement of computer vision technology, the application of image recognition has expanded across various fields, particularly in public safety and intelligent surveillance systems. This paper reviews the evolution of YOLO models from v1 to v8, focusing on the advancements in detection speed, computational efficiency, and accuracy of YOLOv8. We analysed YOLOv8's algorithm and network architecture, detailing its application to human action recognition in surveillance imagery. Through comprehensive testing on diverse surveillance videos, we validate YOLOv8's enhanced performance and efficiency in recognizing human postures and actions. Our findings underscore YOLOv8's significant practical value and its potential for broader application in intelligent surveillance systems.

KEYWORDS

Computer vision, image recognition, YOLOv8, surveillance image processing

CITE THIS PAPER

Yuhan Lin, Jingchu Wang, Dong Lin, Application of YOLOv8 Image Recognition Model for Human Actions Recognition in the Surveillance Filed. Journal of Image Processing Theory and Applications (2024) Vol. 7: 91-100. DOI: http://dx.doi.org/10.23977/jipta.2024.070111.

REFERENCES

[1] Terven, J., & Cordova-Esparza, D. (2024, February 4). A comprehensive review of YOLO architectures in Computer Vision: From YOLOV1 to Yolov8 and Yolo-Nas. arXiv.org. https://arxiv.org/abs/2304.00501v7
[2] Detailed explanation of YOLOv8 [Network Structure + Code + Practical Implementation]. (n.d.). CSDN Blog. http://t.csdnimg.cn/78mzS 
[3] Zhao Jida, Zhen Guoyong, Chu Chenqun. UAV image target detection algorithm based on YOLOv8[J]. Computer Engineering, 2024, 50(04), 113-120. https://doi.org/10.19678/j.issn.1000-3428.0068268
[4] Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2024, May 22). Real-time flying object de-tection with yolov8. arXiv.org. https://arxiv.org/abs/2305.09972v2 
[5] Ma, S., & Xu, Y. (2023, July 14). MPDIoU: A loss for efficient and accurate bounding box regression. arXiv.org. https://arxiv.org/abs/2307.07662
[6] Yin Beichen, Wang Zijjian., Cheng Zhi, et al. Research on inspection robot target detection method based on improved YOLOv8 model [J]. Medical Equipment, 2024, 45(03), 1-8. https://doi.org/10.19745/j.1003-8868.2024041.

Downloads: 2477
Visits: 176106

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.