ABSTRACT
In this paper, a lightweight network based on improved YOLOv4 is proposed to solve the problems of complex model structure and unsatisfactory performance of detection speed in fast-moving situations. Firstly, the inverted residual blocks (IRB) based on Mobilenetv2 are adopted into the backbone feature extraction network to reduce the complexity of the model structure. Then, the feature fusion network based on the depth-wise separable convolution is applied to minimize model calculations and parameters. Experimental results show that the proposed model has the advantages of high accuracy, fast detection speed, and lightweight, which has satisfied the requirements of real-time detection of mask-wearing in fast-moving situations.
- CHENG V C C, WONG S C, CHUANG V W M, The role of community-wide wearing of face mask for control of coronavirus disease 2019 (COVID-19) epidemic due to SARS-CoV-2. Journal of Infection, 2020, 81(1), 107-114.Google ScholarCross Ref
- GIRSHICK R, DONAHUE J, DARRELL T, Rich feature hierarchies for accurate object detection and semantic segmentatio. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, 580-587.Google ScholarDigital Library
- GIRSHICK R. Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, 2015, 1440-1448.Google ScholarDigital Library
- REN S, HE K, GIRSHICK R, Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6), 1137-1149.Google ScholarDigital Library
- HE K, GKIOXARI G, DOLLÁR P, Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision. 2017, 2961-2969.Google Scholar
- HE K, ZHANG X, REN S, Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9), 1904-1916.Google Scholar
- REDMON J, DIVVALA S, GIRSHICK R, You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 779-788.Google ScholarCross Ref
- LIU W, ANGUELOV D, ERHAN D, SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, 2016, 21-37.Google ScholarCross Ref
- CHAVDA A, DSOUZA J, BADGUJAR S, Multi-stage CNN architecture for face mask detection. Proceedings of the IEEE International Conference for Convergence in Technology, 2021, 1-8.Google Scholar
- GUPTA P, SHARMA V, VARMA S. A novel algorithm for mask detection and recognizing actions of human. Expert Systems with Applications, 2022, 198, 1-10.Google Scholar
- WU P, LI H, ZENG N, FMD-Yolo: An efficient face mask detection method for COVID-19 prevention and control in public. Image and Vision Computing, 2022, 117, 104341.Google ScholarDigital Library
- NAGRATH P, JAIN R, MADAN A, SSDMNV2: A real-time DNN-based face mask detection system using single shot multibox detector and MobileNetV2 [J]. Sustainable cities and society, 2021, 66, 102692.Google Scholar
- BOCHKOVSKIV A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection. ArXiv Preprint, arXiv:2004.10934, 2020.Google Scholar
- SANDLER M, HOWARD A, ZHU M, Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, 4510-4520.Google ScholarCross Ref
- HOWARD A G, ZHU M, CHEN B, Mobilenets: Efficient convolutional neural networks for mobile vision applications. ArXiv Preprint, ArXiv:1704.04861, 2017.Google Scholar
Index Terms
- A Method of Mask-Wearing Detection Based on Improved YOLOv4
Recommendations
CALYOLOv4: lightweight YOLOv4 target detection based on coordinated attention
AbstractThe current deep learning-based target detection algorithm YOLOv4 has a large number of redundant convolutional computations, resulting in much consumption of memory and computational resources, making it difficult to apply on mobile devices with ...
Deep learning-based lightweight radar target detection method
AbstractFor target detection tasks in complicated backgrounds, a deep learning-based radar target detection method is suggested to address the problems of a high false alarm rate and the difficulties of achieving high-performance detection by conventional ...
Scratch Detection of Aircraft Bell Tube Based on Improved YOLOv4 Framework
SPML '21: Proceedings of the 2021 4th International Conference on Signal Processing and Machine LearningTo solve the problems of low accuracy, false detection, and high rate of missed detection, a surface scratch detection framework for aircraft bell tubes based on an improved YOLOv4 algorithm is proposed. First, we construct a scratch dataset on the ...
Comments