skip to main content
10.1145/3633637.3633663acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccprConference Proceedingsconference-collections
research-article

Small Object Detection with YOLOv8 Algorithm Enhanced by MobileViTv3 and Wise-IoU

Published: 28 February 2024 Publication History

Abstract

Small object detection is an important and challenging task in computer vision, with widespread applications in fields such as remote sensing, autonomous driving, and security. However, due to factors such as small size, indistinct features, and complex backgrounds of small objects, traditional convolutional neural network (CNN)-based object detection algorithms often struggle to effectively detect small objects. To address issues such as insufficient feature extraction, suboptimal anchor box matching, and unbalanced loss functions, an improved YOLOv8 algorithm is proposed. This algorithm enhances the detection accuracy of small objects by adding a lightweight visual transformer, MobileViTv3, which can enhance feature representation capabilities, and a Wise-IoU loss function that adaptively adjusts the ratio of positive and negative samples and regression coefficients. Results show that the improved YOLOv8 algorithm achieves an increase of 2.5%, 2.1%, and 2.9% in precision, recall, and mAP respectively on the public remote sensing dataset VisDrone2019 and 2.4%, 2.7%, and 3.5% on DOTA compared to the original algorithm. It can effectively improve the accuracy of small object detection in complex scenarios while meeting the requirements for detection speed.

References

[1]
Z. Du, H. Zhou, and C. Li. 2022. Small Object Detection Based on Deep Convolutional Neural Networks: A Review. Computer Science 49, 12 (Dec. 2022), 205–218. https://doaj.org/article/5898aee63fee49ee9460fe960819967a
[2]
W. Ge, L. Ma, and L. Qu. 2023. Research on Object Detection Algorithm for Unmanned Vehicles on Freeway. Computer Simulation 40, 1 (Jan. 2023), 137–142. http://www.cnki.com.cn/Article/CJFDTotal-JSJN202301024.html
[3]
Liang Guo, Qiang Wang, Wei Xue, and Jia Guo. 2023. A Small Object Detection Algorithm Based on Improved YOLOv5. In Journal of University of Electronic Science and Technology of China, Vol. 52. 1–8. https://doi.org/10.3969/j.issn.1001-0548.2023.01.001
[4]
C. Li. 2021. Small target detection algorithm based on YOLOv5. Yangtze River Information and Communication 13, 9 (2021), 1–6. http://www.cnki.com.cn/Article/CJFDTotal-CJXX202109001.html
[5]
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. In Proceedings of the European Conference on Computer Vision (ECCV). 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
[6]
Y. Liu. 2021. An Improved Algorithm for Object Detection Based on YOLO Series. Computer Engineering and Applications 57, 20 (Oct. 2021), 1–8. http://www.ceaj.org/CN/abstract/abstract1079.html
[7]
Zhi M. Qi, X.2023. A Review of Attention Mechanisms in Image Processing. Computer Science and Exploration (July 2023). http://kns.cnki.net/kcms/detail/11.5602.TP.20230629.1447.002.html
[8]
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the Advances in Neural Information Processing Systems (NIPS). 91–99. https://doi.org/10.1109/TPAMI.2016.2577031
[9]
P. Sun. 2019. Overview of Research and Application Progress of Face Recognition Technology. Computer Applications and Software 36, 11 (Nov. 2019), 130–153. http://www.cas.net.cn/CN/abstract/abstract1073.html
[10]
Zanjia Tong, Yuhang Chen, Zewei Xu, and Rong Yu. 2023. Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv preprint arXiv:2301.10051 (2023). https://arxiv.org/abs/2301.10051
[11]
Ultralytics. 2019. YOLOv5 in PyTorch. https://github.com/ultralytics/yolov5.
[12]
Ultralytics. 2023. YOLOv8 in PyTorch. https://github.com/ultralytics/ultralytics.
[13]
W. Wu, H. Liu, and L. Li. 2021. Application of local fully convolutional neural network combined with YOLO v5 algorithm in small target detection of remote sensing image. PLOS ONE 16, 10 (Oct. 2021), e0259283. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0259283
[14]
Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liangpei Zhang. 2018. DOTA: A Large-Scale Dataset for Object Detection in Aerial Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3974–3983. https://doi.org/10.1109/CVPR.2018.00418
[15]
H. Yang and L. Meng. 2023. A small target detection algorithm based on improved YOLOv5 in aerial image. Computer Engineering and Science 45, 6 (June 2023), 1–10. http://www.cnki.com.cn/Article/CJFDTotal-JSGX202306001.html
[16]
H. Yin, B. Chen, and Y. Chai. 2016. A Small Object Detection Algorithm Based on Improved YOLOv5. Journal of Computer Science and Technology 31, 5 (Oct. 2016), 1024–1033. https://doi.org/10.1007/11390-016-1680-9
[17]
Chuangye Zhang. 2021. MobileViTv3: A Compact Transformer for Visual Recognition. arXiv preprint arXiv:2112.01280 (2021). https://arxiv.org/abs/2112.01280
[18]
Pengfei Zhu, Longyin Wen, Xiao Bian, Haibin Ling, and Qinghua Hu. 2018. Vision Meets Drones: A Challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 6 (2018), 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
[19]
R. Zhu and F. Yang. 2023. Improved YOLOv5 Small Object Detection Algorithm in Moving Scenes. Computer Engineering and Applications 59, 10 (Oct. 2023), 196–203.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition
October 2023
589 pages
ISBN:9798400707988
DOI:10.1145/3633637
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 28 February 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. MobileViTv3
  2. Small object detection
  3. Wise-IoU
  4. YOLOv8 algorithm

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICCPR 2023

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 165
    Total Downloads
  • Downloads (Last 12 months)165
  • Downloads (Last 6 weeks)11
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media