Peng Yang
ABSTRACT
An improved Yolov8 model is proposed to address the issue of low detection accuracy due to the complex background and small target features in mask detection under crowded conditions. Firstly, the C2f module in Backbone was changed to a PC2f module, and Sim attention was introduced, which improved the detection speed while enhancing the extraction of image features; Secondly, BiFPN was introduced to replace the PAN-FPN structure in the Neck layer of the original network, improving the detection performance; Replace the original loss function with the Wise-IOU loss function to improve the boundary box regression performance of the network; Finally, add a small target detection layer, changing the 3 detection heads to 4 detection heads, which is more conducive to improving the detection effect of small target objects. The experimental results show that the improved model has a 1.4% increase in mAP (50) and a 14.6% increase in FPS compared to the original model.
- XU Degang,WANG Lu,LI Fan.Review of Typical Object Detection Algorithms for Deep Learing[J]. Computer Engineering and Applications,2021,57(08):10-25.Google Scholar
- Zhao Wenqing;Kong Zixu;Zhou Zhendong,et al. Target detection algorithm of aerial remote sensing based on feature enhancement technology [J]. Journal of Image and Graphics,2021,26(03):644-653.Google Scholar
- LUO Hui-lan;CHEN Hong-kun. Survey of Object Detection Based on Deep Learning [J]. Acta Electronica Sinica,2020,48(06):1230-1239.Google Scholar
- WANG Xinran;TIAN Qichuan;ZHANG Dong. Review of Research on Face Mask Wearing Detection [J]. Computer Engineering and Applications,2022,58(10):13-26.Google Scholar
- Liu,,Yueping A Coarse-to-Fine Detection Method of Pantograph-Catenary Contact Points Using DCNNs[],2019.Google Scholar
- Zhang,,Xiaoguo An Approach to Improve SSD through Skip Connection of Multiscale Feature Maps[J].COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE,2020,2020:2936920.Google Scholar
- Chengshuo, Yuan Jie. Mask-Wearing Detection Method Based on YOLO-Mask[J]. Laser & Optoelectronics Progress,2021,58(08):211-218.Google Scholar
- Zhang Xiubao,Lin Ziyuan,Tian Wanxin,et al.Mask-wearing recognition in the wild[J]. Scientia Sinica(Informationis),2020,50(07):1110-1120.Google Scholar
- Wang H, Li Z, Ji X, Face R-CNN. arXiv preprint arXiv:1706, 01061, 2017Google Scholar
- Wang J, Yuan Y and Yu G. Face attention network: An effective face detector for occluded faces. arXiv preprint arXiv:1711.07246, 2017Google Scholar
- Tang X, Du D K, He Z, Pyramidbox: A context-assisted single shot face detector. Proceedings of European Conference on Computer Vision (ECCV), 2018Google ScholarDigital Library
- Pang Y W, Xie J, Khan M H, Mask-Guided Attention Network for Occluded Pedestrian Detection. 2019 IEEE International Conference on Computer Vision (ICCV), 2019: 4966-4974Google Scholar
- Xie J, Shao L. PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection. arXiv preprint arXiv:2001.09252, 2020Google Scholar
- WANG Yihao;DING Hongwei;LI Bo, et al. Mask Wearing Detection Algorithm Based on Improved YOLOv3 in Complex Scenes [J]. Computer Engineering,2020,46(11):12-22.DOI:10.19678/j.issn.1000-3428.0058802.Google ScholarCross Ref
- ZENG Cheng;JIANG Yu;ZHANG Yin-ren. Improved YOLOv3 detection algorithm for mask wearing [J]. Computer Engineering and Design,2021,42(5):1455-1462.Google Scholar
- CHENG Ke-Xin;WANG Yu-De. Algorithm of Mask Wearing Detection in Natural Scenes Based on Improved YOLOv3 [J]. Computer Systems & Applications,2021,30(2):231-236.Google Scholar
- WANG Yifei;HE Lile;HE Lin. Design of lightweight mask wearing detection model based on YOLOv4 [J]. Journal of Northwest University(Natural Science Edition),2023,53(02):265-273.DOI:10.16152/j.cnki.xdxbzr.2023-02-012.Google ScholarCross Ref
- Cheng HaoRan,Wang XinTao,Li JunRan,et al.Improved YOLOv4-tiny epidemic collaborative mask wearing detection method [J/OL]. Computer Engineering and Applications:1-16[2023-09-19].http://kns.cnki.net/kcms/detail/11.2127.TP.20220812.1448.010.htmlGoogle Scholar
- TAN Shilei;BIE Xiongbo;LU Gonglin等. Real-time detection for mask-wearing of personnel based on YOLOv5 network model [J]. Laser Journal,2021,42(02):147-150.DOI:10.14016/j.cnki.jgzz.2021.02.147.Google ScholarCross Ref
- DUAN Bichong;MA Mingtao. Research on Improved Mask Detection Method Based on YOLOv5 Algorithm [J]. Computer Engineering and Applications,2023,59(16):223-231.Google Scholar
- Guo,,Shuyi,et al.Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5[J].SENSORS,2022,22(13).Google Scholar
- FU Hui-chen;GAO Jun-wei;CHE Lu-yang. Mask wearing detection based on improved YOLOv7 [J]. Chinese Journal of Liquid Crystals and Displays,2023,38(08):1139-1147.Google Scholar
- Xiong EnJie,Zhang RongFen,Liu YuHong等. Ghost-YOLOv8 detection algorithm for traffic signs [J/OL]. Computer Engineering and Applications:1-11[2023-09-19].http://kns.cnki.net/kcms/detail/11.2127.TP.20230811.1059.002.htmlGoogle Scholar
- Xinghai Hou. Multi-class Object Detection Technique for Complex Large-field Optical Satellite Remote Sensing Images [D]. North China University of Technology,2023.DOI:10.26926/d.cnki.gbfgu.2022.000137.Google ScholarCross Ref
- YE Yuwei;REN Yan;GAO Xiaowen, et al. Remote sensing image target detection based on improved YOLOv4 [J]. Journal of Optoelectronics·Laser,2022,33(06):607-613.DOI:10.16136/j.joel.2022.06.0724.Google ScholarCross Ref
- ZHANG Ruifang;DONG Feng;CHENG Xiaohui. Application of Improved YOLOv5s Algorithm in Non-motorized Helmet Wearing Detection [J]. Journal of Henan University of Science And Technology:Natural Science,2023,44(01):44-53+7.DOI:10.15926/j.cnki.issn1672-6871.2023.01.007.Google ScholarCross Ref
- HUANG Zijie1 , OU Yang2 , JIANG Degang1等. Lightweight deep learning algorithm orienting for weld seam surface quality inspection of traction seat [J/OL]. Journal of Computer Applications:1-9[2023-09-13]Google Scholar
- DUAN Bichong;MA Mingtao. Research on Improved Mask Detection Method Based on YOLOv5 Algorithm [J]. Computer Engineering and Applications,2023,59(16):223-231.Google Scholar
Index Terms
- Research on Mask Detection Method Based on Yolov8
Recommendations
Research on Target Detection Method Based on Improved YOLOv5
Web Information Systems and ApplicationsAbstractAt present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data ...
Research on improved YOLOv8 algorithm for insulator defect detection
AbstractWith the rapid advancement of artificial intelligence technologies, drone aerial photography has gradually become the mainstream method for defect detection of transmission line insulators. To address the issues of slow recognition speed and low ...
Research on small target Detection Algorithm of UAV based on Mask R-CNN
CNIOT '23: Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of ThingsThe purpose of this paper is to improve the detection accuracy of UAV small target in the high-voltage tower scene. Firstly, this paper constructs the small target data set of UAV with three different models and enhances the data set. Then, Mask R-CNN ...
Comments