CAOYuanjie,GAO Yuxiang,DU Xinchang,et al.Tiny-YOLOv3 Model Algorithm is Optimized for Mask Wearing Recognition[J].Journal of Chengdu University of Information Technology,2021,36(02):154-158.[doi:10.16836/j.cnki.jcuit.2021.02.005]
口罩佩戴识别中的Tiny-YOLOv3模型算法优化
- Title:
- Tiny-YOLOv3 Model Algorithm is Optimized for Mask Wearing Recognition
- 文章编号:
- 2096-1618(2021)02-0154-05
- 分类号:
- TP183
- 文献标志码:
- A
- 摘要:
- 针对深度学习网络(Tiny-YOLOv3)算法准确率不高以及更改网络模型后实时性的问题,提出一种网络改进方案和基于BN层剪枝的优化算法。将Tiny-YOLOv3的前四层池化层改为两步长的卷积层进行下采样以及增加特征的提取,将后两层池化层和第六个卷积层改为一个残差结构层,再利用BN层剪枝算法,将网络进行压缩和BN层合并来加速网络。改进优化后的模型算法相比原始Tiny-YOLOv3网络,在口罩佩戴识别的平均精确率(mAP)提升了14%,模型体积只有19.2 MB,压缩了42%; 平均每秒传输帧数(FPS)增加了17%。实验结果表明,改进优化后的模型有更好的精确性和实时性。
- Abstract:
- Aiming at the low accuracy of deep learning network(Tiny-YOLOv3)algorithm and the instantaneity after changing the network model, a network improvement scheme and an optimization algorithm based on BN layer pruning are proposed. In this method, the first four pooling layers of Tiny-Yolov3 are replaced by a two-step convolutional layer for down-sampling and feature extraction, and the latter two pooling layers and the sixth convolutional layer are changed into a residual structure layer. Then the BN layer pruning algorithm is used to compress the network and combine the BN layer to accelerate the network. Compared with the original Tiny-YOLOv3 network, the improved and optimized model algorithm improves the mean accuracy rate(mAP)of mask wearing recognition by 14%. The model volume is only 19.2 MB, which is compressedby 42%. The average number of frames per second(FPS)increased by 17%.The experimental results show that the improved and optimized model has better accuracy and real-time performance.
参考文献/References:
[1] 肖俊杰.基于YOLOv3和YCrCb的人脸口罩检测与规范佩戴识别[J].软件,2020,41(7):164-169.
[2] He K M,Zhang X Y,Ren S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[3] Girshick R.Fast R-CNN [C].IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1440-1448.
[4] Redmon J,Divvala S,Girshick R,et al.You Only Look Once:Unified,Real-Time Object Detection[C].IEEE Conference on Computer Vision and Pattern Recognition(CVPR),IEEE,2016:779-788.
[5] J Farhadi A.YOLO9000:Better,Faster,Stronger[C].IEEE Conference on Computer Vision & Pattern Recognition.IEEE,2017:6517-6525.
[6] Girshick R,Donahue J,Darrell T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C].CVPR.IEEE,2014:580-587.
[7] Liu W,Anguelov D,Erhan D,et al.SSD:Single Shot MultiBox Detector[J].Lecture Notes in Computer Science,2016(1):21-27.
[8] Redmon J,Farhadi A.An Incremental Improvement[J].arXiv e-prints,2018(3).
[9] Xiao D,Shan F,Li Z,et al.A Target Detection Model Based on Improved Tiny-yolov3 Under the Environment of Mining Truck[J].IEEE Access,2019,(99):1.
[10] 马立,巩笑天,欧阳航空.Tiny YOLOV3目标检测改进[J].光学精密工程,2020,28(4):988-995.
[11] 姚巍巍,张洁.基于模型剪枝和半精度加速改进YOLOv3-tiny算法的实时司机违章行为检测[J].计算机系统应用,2020,29(4):41-47.
[12] Ioffe S,Szegedy C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[J].arxiv,2015(2).
[13] Duan J,Zhang R X,Huang J,et al.The Speed Improvement by Merging Batch Normalization into Previously Linear Layer in CNN[C].2018 International Conference on Audio,Language and Image Processing(ICALIP).2018.
[14] Xu Z F,Jia R S,Liu Y B,etal.Fast Method of Detecting Tomatoes in a Complex Scene for Picking Robots[J].IEEE Access,2020,(99):1.
相似文献/References:
[1]张 斌,王 强.一种改进型卷积神经网络的图像分类方法[J].成都信息工程大学学报,2019,(01):39.[doi:10.16836/j.cnki.jcuit.2019.01.009]
ZHANG Bin,WANG Qiang.An Improved Convolution Neural Network Image Classification Method[J].Journal of Chengdu University of Information Technology,2019,(02):39.[doi:10.16836/j.cnki.jcuit.2019.01.009]
[2]唐明轩,李孝杰,周激流.基于Dense Connected深度卷积神经网络的
自动视网膜血管分割方法[J].成都信息工程大学学报,2018,(05):525.[doi:10.16836/j.cnki.jcuit.2018.05.007
]
TANG Ming-xuan,LI Xiao-jie,ZHOU Ji-liu.Automatic Retinal Vascular Segmentation Method based on
Densely Connected Convolution Neural Network[J].Journal of Chengdu University of Information Technology,2018,(02):525.[doi:10.16836/j.cnki.jcuit.2018.05.007
]
[3]蔡姣姣,何 嘉.基于混合自动编码器的分类应用[J].成都信息工程大学学报,2016,(增刊1):1.
[4]任 波,王录涛,邓 旭,等.一种改进深度学习网络结构的英文字符识别[J].成都信息工程大学学报,2017,(03):259.[doi:10.16836/j.cnki.jcuit.2017.03.005]
REN Bo,WANG Lu-tao,DENG Xu,et al.An Improved Deep Learning Network Structure for English Character Recognition[J].Journal of Chengdu University of Information Technology,2017,(02):259.[doi:10.16836/j.cnki.jcuit.2017.03.005]
[5]冯金慧,陶宏才.基于注意力的深度协同在线学习资源推荐模型[J].成都信息工程大学学报,2020,35(02):151.[doi:10.16836/j.cnki.jcuit.2020.02.005]
FENG Jinhui,TAO Hongcai.An Attention-based Deep Collaborative Filtering Model for Online Course Recommendation[J].Journal of Chengdu University of Information Technology,2020,35(02):151.[doi:10.16836/j.cnki.jcuit.2020.02.005]
[6]杨 铭,文 斌.一种改进的YOLOv3-Tiny目标检测算法[J].成都信息工程大学学报,2020,35(05):531.[doi:10.16836/j.cnki.jcuit.2020.05.009]
YANG Ming,WEN Bin.An Improved YOLOv3-Tiny Target Detection Algorithm[J].Journal of Chengdu University of Information Technology,2020,35(02):531.[doi:10.16836/j.cnki.jcuit.2020.05.009]
[7]曹远杰,高瑜翔,刘海波,等.基于YOLOv4-Tiny模型剪枝算法[J].成都信息工程大学学报,2021,36(06):610.[doi:10.16836/j.cnki.jcuit.2021.06.005]
CAO Yuanjie,GAO Yuxiang,LIU Haibo,et al.Model Pruning Algorithm based on YOLOv4-Tiny[J].Journal of Chengdu University of Information Technology,2021,36(02):610.[doi:10.16836/j.cnki.jcuit.2021.06.005]
[8]晏美娟,魏 敏,文 武.一种高分辨率卫星图像道路提取方法[J].成都信息工程大学学报,2022,37(01):46.[doi:10.16836/j.cnki.jcuit.2022.01.008]
YAN Meijuan,WEI Min,WEN Wu.A Method of Road Extraction for High-Resolution Satellite Images[J].Journal of Chengdu University of Information Technology,2022,37(02):46.[doi:10.16836/j.cnki.jcuit.2022.01.008]
备注/Memo
收稿日期:2020-10-15
基金项目:四川省教育厅高校创新团队资助项目(15TD0022)