计算机科学 ›› 2021, Vol. 48 ›› Issue (10): 233-238.doi: 10.11896/jsjkx.200900172

• 计算机图形学&多媒体 • 上一篇    下一篇

面向小目标检测的改进RetinaNet模型及其应用

罗月童, 江佩峰, 段昶, 周波   

  1. 合肥工业大学可视化与协同计算研究室 合肥230601
  • 收稿日期:2020-09-24 修回日期:2021-02-02 出版日期:2021-10-15 发布日期:2021-10-18
  • 通讯作者: 周波(zhoubo810707@163.com)
  • 作者简介:ytluo@hfut.edu.cn
  • 基金资助:
    国家自然科学基金(61602146);国家重点基础研究发展计划(2017YFB1402200);安徽省科技攻关计划(1604d0802009)

Small Object Detection Oriented Improved-RetinaNet Model and Its Application

LUO Yue-tong, JIANG Pei-feng, DUAN Chang, ZHOU Bo   

  1. Visualization & Cooperative Computing,Hefei University of Technology,Hefei 230601,China
  • Received:2020-09-24 Revised:2021-02-02 Online:2021-10-15 Published:2021-10-18
  • About author:LUO Yue-tong,born in 1978,Ph.D,professor,is a member of Chinese Compu-ter Society,Computer Aided Design and Graphics Committee.His main research interests include image processing and scientific visualization.
    ZHOU Bo,born in 1981,Ph.D,associate professor.His main research interests include digital terrain analysis and object detection.
  • Supported by:
    National Natural Science Foundation of China(61602146),National Basic Research Program of China(2017YFB1402200) and Key Science and Technology Program of Anhui Province,China(1604d0802009).

摘要: 基于深度学习的目标检测算法广泛应用于工业检测,RetinaNet算法因兼具速度与精度两方面的优势而备受关注,但对于小于32×32像素的小目标,该算法的检测精度不能满足工业检测的要求。为此,文中以增强小目标的训练为基本思路,针对RetinaNet算法进行了如下改进:在采样阶段,将低层特征图P2添加到FPN中,以确保小目标能被充分采样,同时引入自适应训练样本选择策略,以保证增加特征层之后仍能保持足够快的检测速度;在训练后期采用了损失权重调整策略,用于提高小目标中困难样本的拟合度。针对公共数据集MS COCO 2017及实际应用中的LED点胶工业数据集,改进后的方法使小于32×32目标的检测精度分别提高了4.1%和10.7%,这表明改进后的方法能显著提升小目标检测的水平。

关键词: RetinaNet, 深度学习, 小目标检测, 自适应采样

Abstract: Object detection algorithms based on deep learning are widely used in industrial detection.The RetinaNet algorithm has attracted much attention because of its advantages in both speed and accuracy.However,for small objects smaller than 32×32 pixels,the detection accuracy of this algorithm cannot meet the requirements of industrial detection.To this end,this article takes the enhancement of small object training as the basic idea,and makes the following improvements to the RetinaNet algorithm:in the sampling phase,the low-level feature map P2 is added to the FPN to ensure that the small object can be fully sampled,and adaptive training sample selection(ATSS) strategy is introduced to ensure that the detection speed is still fast enough after the feature layer is increased;the loss weight adjustment strategy is adopted in the later training stage to improve the fit of difficult samples in small objects.For the public data set MS COCO 2017 and the LED dispensing industrial data set in practical applications,the detection accuracy of this method for objects smaller than 32×32 increases by 4.1% and 10.7%,respectively,indicating that this method can significantly improve the detection ability of small objects.

Key words: Adaptive sampling, Deep learning, RetinaNet, Small object detection

中图分类号: 

  • TP391
[1]HU G X,YANG Z,HU L,et al.Small object detection withmultiscale features[J].International Journal of Digital Multimedia Broadcasting,2018(2):1-10.
[2]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:580-587.
[3]GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448.
[4]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems.2015:91-99.
[5]UIJLINGS J R R,VAN DE SANDE K E A,GEVERS T,et al.Selective search for object recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[6]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788.
[7]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//European Conference on Computer Vision.Springer,Cham,2016:21-37.
[8]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988.
[9]SINGH B,DAVIS L S.An analysis of scale invariance in object detection snip[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3578-3587.
[10]SINGH B,NAJIBI M,DAVIS L S.SNIPER:Efficient multi-scale training[C]//Advances in Neural Information Processing Systems.2018:9310-9320.
[11]HU P,RAMANAN D.Finding tiny faces[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:951-959.
[12]LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8759-8768.
[13]QIN Z,LI Z,ZHANG Z,et al.ThunderNet:Towards Real-Time Generic Object Detection on Mobile Devices[C]//Proceedings of the IEEE International Conference on Computer Vision.2019:6718-6727.
[14]PANG J,CHEN K,SHI J,et al.Libra r-cnn:Towards balanced learning for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:821-830.
[15]BAI Y,ZHANG Y,DING M,et al.Sod-mtgan:Small object detection via multi-task generative adversarial network[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:206-221.
[16]LI J,LIANG X,WEI Y,et al.Perceptual generative adversarial networks for small object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1222-1230.
[17]NOH J,BAE W,LEE W,et al.Better to Follow,Follow to Be Better:Towards Precise Supervision of Feature Super-Resolution for Small Object Detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2019:9725-9734.
[18]ZHU C,TAO R,LUU K,et al.Seeing Small Faces from Robust Anchor's Perspective[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:5127-5136.
[19]ZHANG S,CHI C,YAO Y,et al.Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection[J].arXiv:1912.02424,2019.
[20]CHEN Y,ZHANG P,LI Z,et al.Stitcher:Feedback-driven Data Provider for Object Detection[J].arXiv:2004.12432,2020.
[21]YU X,GONG Y,JIANG N,et al.Scale Match for Tiny Person Detection[C]//The IEEE Winter Conference on Applications of Computer Vision.2020:1257-1265.
[22]KISANTAL M,WOJNA Z,MURAWSKI J,et al.Augmentation for small object detection[J].arXiv:1902.07296,2019.
[23]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125.
[24]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[25]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[26]DUAN K,DU D,QI H,et al.Detecting small objects using a channel-aware deconvolutional network[C]//IEEE Transactions on Circuits and Systems for Video Technology.2019.
[27]LI B,LIU Y,WANG X.Gradient harmonized single-stage detector[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33:8577-8584.
[28]CHEN K,WANG J,PANG J,et al.MMDetection:Open mmlab detection toolbox and benchmark[J].arXiv:1906.07155,2019.
[1] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[5] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[6] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[7] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[9] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[10] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[11] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[12] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[13] 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋.
改进Faster R-CNN的光学遥感飞机目标检测
Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN
计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[14] 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤.
不同数据增强方法对模型识别精度的影响
Influence of Different Data Augmentation Methods on Model Recognition Accuracy
计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210
[15] 毛典辉, 黄晖煜, 赵爽.
符合监管合规性的自动合成新闻检测方法研究
Study on Automatic Synthetic News Detection Method Complying with Regulatory Compliance
计算机科学, 2022, 49(6A): 523-530. https://doi.org/10.11896/jsjkx.210300083
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!