Applied and Computational Engineering

- The Open Access Proceedings Series for Conferences


Proceedings of the 5th International Conference on Computing and Data Science

Series Vol. 17 , 23 October 2023


Open Access | Article

Research on identification of floating garbage using improved YOLO v7 algorithm

Weixuan Li * 1 , Haotian Zhu 2
1 Tianjin Polytechnic University
2 University of Sussex

* Author to whom correspondence should be addressed.

Applied and Computational Engineering, Vol. 17, 95-104
Published 23 October 2023. © 2023 The Author(s). Published by EWA Publishing
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Citation Weixuan Li, Haotian Zhu. Research on identification of floating garbage using improved YOLO v7 algorithm. ACE (2023) Vol. 17: 95-104. DOI: 10.54254/2755-2721/17/20230920.

Abstract

The floating garbage is becoming more and more serious, but little research has addressed recognition of these floating garbage. Intelligent target recognition of floating garbage using deep learning techniques is therefore essential. The YOLOv7 algorithm has strong ability of extracting target features and is significantly faster than its previous version at the same accuracy. The technique is provide based on the YOLOv7 algorithm for identifying floating garbage in this paper, as a result, develop and implement a target monitoring function for floating garbage identification. Specifically, the combination of YOLO v7 and SE attention mechanism was used to improve ability of target sensing. The training process was optimized by using EIOU loss, resulting in a significant improvement in the efficiency of the final model compared to the normal YOLOV7 algorithm model, significant improvements of 20% and 25% in the model metrics mAP_0.5:0.95 and mAP_0.5, respectively.

Keywords

floating garbage, deep learning, target detection, YOLOv7

References

1. Tang Wei, Gao Han, Liu Siyang. Design and implementation of a small waterside intelligent rubbish cleaning robot system based on Raspberry Pi. 2019, Sci. Tech. Eng. 19(34): 239-247.

2. Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv:2207. 02696. https: / / arxiv. org / abs/ 2207. 02696.

3. Zhang X P, Xu Z Y, Qu S,et al. Recognition algorithm of marine ship based on improved YOLOv5 deep learning. 2022, J. Dalian Ocean Univ., 37(5):866-872.

4. Zhang Dajie, YOLOv7 Network Architecture In-depth Analysis https: //blog. csdn. net/zqwwwm/article/details/125901507.

5. Du Peng, Shen Ming, Su Tonghua. Deep learning and object detection. 2020, Beijing: Electronic Industry Press.

6. Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning.2021, Neurocomput. 452: 48-62.

7. Brauwers G, Frasincar F. A general survey on attention mechanisms in deep learning. 2021, IEEE Trans. Knowl. Data Enginee.,1-11.

8. Kong Yisi, Hu Xiaofeng, Zhu Feng, Tao Jiuyang. Exploring the attention mechanism in battlefield situational awareness. 2017, J. Sys. Simul., 29(10): 2233-2241.

9. Zheng Z H,Wang P, Liu W, et al. Distance-IoU loss:faster and better learning for bounding box regression. 2020, AAAI Conf. Artif. Intell., 34(7): 12993-13000.

10. Zhang Y F, Ren W, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression arXiv: 2101.08158v1.

Data Availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).

Volume Title
Proceedings of the 5th International Conference on Computing and Data Science
ISBN (Print)
978-1-83558-025-7
ISBN (Online)
978-1-83558-026-4
Published Date
23 October 2023
Series
Applied and Computational Engineering
ISSN (Print)
2755-2721
ISSN (Online)
2755-273X
DOI
10.54254/2755-2721/17/20230920
Copyright
© 2023 The Author(s)
Open Access
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Copyright © 2023 EWA Publishing. Unless Otherwise Stated