YANG Ming,WEN Bin.An Improved YOLOv3-Tiny Target Detection Algorithm[J].Journal of Chengdu University of Information Technology,2020,35(05):531-536.[doi:10.16836/j.cnki.jcuit.2020.05.009]
一种改进的YOLOv3-Tiny目标检测算法
- Title:
- An Improved YOLOv3-Tiny Target Detection Algorithm
- 文章编号:
- 2096-1618(2020)05-0531-006
- 关键词:
- 深度学习; 目标检测; YOLOv3-Tiny; IOU
- Keywords:
- deep learning; target detection; YOLOv3-Tiny; IOU
- 分类号:
- TP301.6
- 文献标志码:
- A
- 摘要:
- YOLOv3-Tiny作为YOLOv3目标检测算法的简化版本,拥有检测速度快、体积小、易于在边缘设备上部署等优点,同时也存在着识别精度低,定位不准的问题。由此在该算法的基础上进行改进,首先,对网络结构进行改进,在保证实时性的同时设计一个新的主干网络,提高网络的特征提取能力; 其次改进目标损失函数和特征融合的策略,使用IOU损失函数代替原先边框位置损失函数,提高定位精度。实验结果表明,改进后的YOLOv3-Tiny算法,在保证实时性的情况下明显优于原算法。
- Abstract:
- As a simplified version of YOLOv3 target detection algorithm,YOLOv3-Tiny has the advantages of fast detection speed,small size,easy to deploy on edge devices and so on.At the same time,it also has the problems of low recognition accuracy and inaccurate positioning. In this paper,the algorithm is improved.First of all,the network structure is improved.A new backbone network is designed on the premise of instantaneity,which improves the feature extraction ability of the network.Secondly,target loss function and border matching strategy are improved,and the IOU loss function is used to replace the original frame position loss function to improve the positioning accuracy.The experimental results show that the improved YOLOV3-Tiny algorithm is better than the original algorithm when the instantaneity is guaranteed.
参考文献/References:
[1] Viola P A,Jones M J.Rapid Object Detection using a Boosted Cascade of Simple Features[C].Computer Vision and Pattern Recognition,2001.CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on.IEEE,2001.
[2] Dalal N,Triggs B.Histograms of oriented gradients for human detection[C].Computer Vision and Pattern Recognition,2005.CVPR 2005.IEEE Computer Society Conference on.IEEE,2005:886-893.
[3] Saunders C,Stitson MO,Weston J,et al.Support Vector Machine[J].Computer Science,2002,1(4):1-28.
[4] Pedro F,Felzenszwalb,Ross B,et al.Object detection with discriminatively trained part-based models[J].IEEE transactions on pattern analysis and machine intelligence,2010,32(9):1627-45.
[5] Redmon J,Divvala S,Girshick R,et al.You Only Look Once:Unified,Real-Time Object Detection[C].Computer Vision & Pattern Recognition. IEEE, 2016.
[6] Liu W,Anguelov D,Erhan D,et al.SSD:Single Shot MultiBox Detector[C].European Conference on Computer Vision.Springer International Publishing,2016.
[7] Redmon J,Farhadi A.YOLOv3:An Incremental Improvement[J].arXiv e-prints,2018.
[8] Lin T Y,Dollár,Piotr,Girshick R,et al.Feature Pyramid Networks for Object Detection[J].arXiv e-prints,2016.
[9] Ren S,He K,Girshick R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149.
[10] Jiang B,Luo R,Mao J,et al.Acquisition of Localization Confidence for Accurate Object Detection[J].arXiv e-prints,2018.
[11] 李昕,赵猛,董修武,等.基于改进YOLOV3算法的遥感图像油罐检测[J].中国科技论文,2020(3):267-273.
[12] Bazarevsky V,Kartynnik Y,Vakunov A,et al.BlazeFace:Sub-millisecond Neural Face Detection on Mobile GPUs[J].arXiv e-prints,2019.
[13] Chollet F.Xception:Deep Learning with Depthwise Separable Convolutions[J].arXiv e-prints,2016.
[14] Ronneberger O,Fischer P,Brox T.U-Net:Convolutional Networks for Biomedical Image Segmentation[J].arXiv e-prints,2015.
[15] Zhang Z,Zhang X,Peng C,et al.ExFuse:Enhancing Feature Fusion for Semantic Segmentation[J].arXiv e-prints,2018.
[16] Rezatofighi H,Tsoi N,Gwak J Y,et al.Generalized Intersection Over Union:A Metric and a Loss for Bounding Box Regression[C].2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020.
[17] 孙晓凯,倪卿元,陈文强.图像增强方法在深度学习图像识别场景应用中的可行性研究[J].电信科学,2020,36(S1):172-179.
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,(05):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,(05):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,(05):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(05):151.[doi:10.16836/j.cnki.jcuit.2020.02.005]
[6]曹远杰,高瑜翔,杜鑫昌,等.口罩佩戴识别中的Tiny-YOLOv3模型算法优化[J].成都信息工程大学学报,2021,36(02):154.[doi:10.16836/j.cnki.jcuit.2021.02.005]
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(05):154.[doi:10.16836/j.cnki.jcuit.2021.02.005]
[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(05):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(05):46.[doi:10.16836/j.cnki.jcuit.2022.01.008]
[9]岳 希,梁云浩,何 磊.基于改进YOLO算法的船舰目标检测DT-YOLO方法研究[J].成都信息工程大学学报,2022,37(05):533.[doi:10.16836/j.cnki.jcuit.2022.05.008]
YUE Xi,LIANG Yunhao,HE Lei.Research on DT-YOLO Method of Ship Target Detection based on Improved YOLO Algorithm[J].Journal of Chengdu University of Information Technology,2022,37(05):533.[doi:10.16836/j.cnki.jcuit.2022.05.008]
备注/Memo
收稿日期:2020-06-27