深度学习的目标检测算法改进综述

doi:10.3778/j.issn.1002-8331.2209-0312

摘要/Abstract

摘要： 目标检测是当下计算机视觉领域的研究热点，随着深度学习的发展，基于深度学习的目标检测算法的应用越来越多，性能也不断被提升，通过总结目标检测过程中遇到的常见难题以及相应的改进方法，梳理了基于深度学习的目标检测方法的最新研究进展，重点针对基于深度学习目标检测算法的两大类型进行综述。此外还从注意力机制、轻量型网络、多尺度检测等方面对目标检测算法的最新改进思路进行总结梳理。针对当前目标检测领域存在的问题，对其未来的发展趋势进行展望，并提出可行的解决方案，以期为该领域后续的研究工作提供可借鉴的思路和方向。

关键词: 目标检测, 深度学习, 计算机视觉, 注意力机制, 多尺度检测

Abstract: Object detection is currently a research hotspot in the field of computer vision. With the development of deep learning, object detection algorithms based on deep learning are increasingly applied and their performance is constantly improved. This paper summarizes the latest research progress of object detection methods based on deep learning by summarizing common problems encountered in the process of object detection and corresponding improvement methods. This paper focuses on two types of object detection algorithms based on deep learning. In addition, the latest improvement ideas of target detection algorithms are summarized from the aspects of attention mechanism, lightweight network, multi-scale detection. Finally, in view of the current problems in the field of target detection, the future development trend is prospected. And the feasible solution is put forward in order to provide reference ideas and directions for the follow-up research work in this field.

Key words: object detection, deep learning, computer vision, attention mechanism, multi-scale detection

杨锋, 丁之桐, 邢蒙蒙, 丁波. 深度学习的目标检测算法改进综述[J]. 计算机工程与应用, 2023, 59(11): 1-15.

YANG Feng, DING Zhitong, XING Mengmeng, DING Bo. Review of Object Detection Algorithm Improvement in Deep Learning[J]. Computer Engineering and Applications, 2023, 59(11): 1-15.

参考文献

[1] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Trans Pattern Anal Mach Intell，2015，39（6）：1137-1149.
[2] 罗会兰，陈鸿坤.基于深度学习的目标检测研究综述[J].电子学报，2020，48（6）：1230-1239.
LUO H L，CHEN H K.Survey of object detection based on deep learning[J].Acta Electronica Sinica，2020，48（6）：1230-1239.
[3] 许德刚，王露，李凡.深度学习的典型目标检测算法研究综述[J].计算机工程与应用，2021，57（8）：10-25.
XU D G，WANG L，LI F.Review of typical object detection algorithms for deep learning[J].Computer Engineering and Applications，2021，57（8）：10-25.
[4] FEI-FEI L，FERGUS R，PERONA P.Learning generative visual models from few training examples：an incremental Bayesian approach tested on 101 object categories[C]//2004 Conference on Computer Vision and Pattern Recog-nition Workshop，2004.
[5] GRIFFIN G，HOLUB A，PERONA P.Caltech-256 object category dataset[R].California Institute of Technology，2007.
[6] EVERINGHAM M，VAN GOOL L，WILLIAMS C K I，et al.The pascal visual object classes（VOC） challenge[J].International Journal of Computer Vision，2010，88（2）：303-338.
[7] EVERINGHAM M，ESLAMI S M A，VAN GOOL L，et al.The pascal visual object classes challenge：a retrospective[J].International Journal of Computer Vision，2015，111（1）：98-136.
[8] RUSSAKOVSKY O，DENG J，SU H，et al.Imagenet large scale visual recognition challenge[J].International Journal of Computer Vision，2015，115（3）：211-252.
[9] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO：common objects in context[C]//European Conference on Computer Vision.Cham：Springer，2014：740-755.
[10] KRASIN I，DUERIG T，ALLDRIN N，et al.OpenImages：a public dataset for large-scale multi-label and multiclass image classification[EB/OL].[2020-05-10].https：//github.Com/openimages.
[11] XIA G S，BAI X，DING J，et al.DOTA：a large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：3974-3983.
[12] ZHU Z，LIANG D，ZHANG S，et al.Traffic-sign detection and classification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：2110-2118
[13] GEIGER A，LENZ P，URTASUN R.Are we ready for autonomous driving? the kittivision benchmark suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition，2012：3354-3361.
[14] YU X，GONG Y，JIANG N，et al.Scale match for tiny person detection[C]//2020 IEEE Winter Conference on Applications of Computer Vision（WACV），2020.
[15] GHOJAVAND K，DERAKHTIAN M，BIGUESH M.Rao-based detectors for adaptive target detection in the presence of signal-dependent interference[J].IEEE Transactions on Signal Processing，2020，68（99）：1662-1672.
[16] ZHANG H，ZHOU Z.Small target detection based on automatic ROI extraction and local directional gray & entropy contrast map[J].Infrared Physics & Technology，2020，107（4）：103290.
[17] LAN T Y，BENDORY T，BOUMAL N，et al.Multi-target detection with an arbitrary spacing distribution[J].IEEE Transactions on Signal Processing，2020，68：1589-1601.
[18] DU J，LU H，HU M，et al.CNN-based infrared dim small target detection algorithm using target-oriented shallow deep features and effective small anchor[J].IET Image Processing，2021，15：1-15.
[19] ZHAO T，WU X Q.Pyramid feature attention network for saliency detection[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition，Long Beach，Jun 16-20，2019.Washington：IEEE Computer Society，2019：3085-3094.
[20] DAI J，LI Y，HE K，et al.R-FCN：object detection via region-based fully convolutional networks[C]//Neural Information Processing Systems，2016：379-387.
[21] ZHOU T，YU Z，CAO Y，et al.Study on an infrared multi-target detection method based on the pseudo-two-stage model[J].Infrared Physics & Technology，2021，118：103883.
[22] ZHANG S，WEN L，BIAN X，et al.Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4203-4212.
[23] XIAO Y，TIAN Z，YU J，et al.A review of object detection based on deep learning[J].Multimedia Tools and Applications，2020，79（33）：23729-23791.
[24] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10781-10790.
[25] 曹磊，王强，史润佳，等.基于改进RPN的Faster R-CNN网络SAR图像车辆目标检测方法[J].东南大学学报（自然科学版），2021，51（1）：87-91.
CAO L，WANG Q，SHI R J，et al.Vehicle target detection method based on improved RPN in Faster R-CNN network SAR image[J].Journal of Southeast University（Natural Science Edition），2021，51（1）：87-91.
[26] 王忠塬.基于改进Faster R-CNN的小目标检测技术研究[D].长春：长春理工大学，2021.
WANG Z Y.Research on small target detection technology based on improved Faster R-CNN[D].Changchun：Changchun University of Technology，2021.
[27] BODLA N，SINGH B，CHELLAPPA R，et al.Soft NMS—improving object detection with one line of code[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5561-5569.
[28] HE Y，ZHU C，WANG J，et al.Bounding box regression with uncertainty for accurate object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：2888-2897.
[29] CHEN C，HE C，HU C，et al.A deep neural network based on an attention mechanism for sar ship detection in multiscale and complex scenarios[J].IEEE Access，2019，7：104848-104863.
[30] LIU S，HUANG D，WANG Y.Adaptive NMS：refining pedestrian detection in a crowd[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：6459-6468.
[31] BOLYA D，ZHOU C，XIAO F，et al.YOLACT：real-time instance segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9157-9166.
[32] ZHENG Z，WANG P，REN D，et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J].IEEE Transactions on Cybernetics，2022，52：8574-8586.
[33] 戴海能，茅耀斌.一种改进的基于R-FCN模型的人脸检测算法[J].计算机与现代化，2018（8）：12-15.
DAI H N，MAO Y B.An improved face detection algothrim based on R-FCN[J].Computer and Moderni-zation，2018（8）：12-15.
[34] 赵振兵，崔雅萍，戚银城，等.基于改进的R-FCN航拍巡线图像中的绝缘子检测方法[J].计算机科学，2019，46（3）：159-163.
ZHAO Z B，CUI Y P，QI Y C，et al.Detection method of insulator in aerial inspection image based on modified R-FCN[J].Computer Science，2019，46（3）：159-163.
[35] HE D，QIU Y，MIAO J，et al.Improved Mask R-CNN for obstacle detection of rail transit[J].Measurement，2022（190）：110728.
[36] 廖延娜，豆丹阳.基于Mask RCNN的桥梁裂缝检测方法设计及研究[J].应用光学，2022，43（1）：100-105.
LIAO Y N，DOU D Y.Design and research of bridge cracks detection method based on Mask RCNN[J].Journal of Applied Optics，2022，43（1）：100-105.
[37] ADAMDAD.Keras-YOLOv3-MobileNet[Z].2019.
[38] GONG J，ZHAO J，LI F，et al.Vehicle detection in thermal images with an improved YOLOv3-tiny[C]//2020 IEEE International Conference on Power，Intelligent Computing and Systems（ICPICS），2020：253-256.
[39] LI Y，Lü C.SS-YOLO：an object detection algorithm based on YOLOv3 and ShuffleNet[C]//2020 IEEE 4th Information Technology，Networking，Electronic and Automation Control Conference（ITNEC），2020：769-772.
[40] 王波，冯旭鹏，刘利军，等.基于改进YOLO算法的肺部CT图像中结节检测研究[J].北京生物医学工程，2020，39（6）：7-13.
WANG B，FENG X P，LIU L J，et al.Study on nodule detection in lung CT images based on improved YOLO algorithm[J].Beijing Biomedical Engineering，2020，39（6）：7-13.
[41] ZHANG T，ZHANG X.High-speed ship detection in SAR images based on a grid convolutional neural network[J].Remote Sensing，2019，11（10）：1206.
[42] 刘肯，何姣姣，张永平，等.改进YOLO的车辆检测算法[J].现代电子技术，2019，42（13）：47-50.
LIU K，HE J J，ZHANG Y P，et al.Improved YOLO vehicle detection algorithm[J].Modern Electronics Technique，2019，42（13）：47-50.
[43] CHANG Y L，ANAGAW A，CHANG L，et al.Ship detection based on YOLOv2 for SAR imagery[J].Remote Sensing，2019，11（7）：786.
[44] 李珣，时斌斌，刘洋，等.基于改进YOLOv2模型的多目标识别方法[J].激光与光电子学进展，2020，57（10）：113-122.
LI X，SHI B B，LIU Y，et al.Multi-target recognition method based on improved YOLOv2 model[J].Laser & Optoelectronics Progress，2020，57（10）：113-122.
[45] XU C J，YE Q，LIU J X，et al.Research on vehicle detection based on YOLOv3[C]//2nd International Conference on Information Technology and Computer Application（ITCA），2020：433-436.
[46] WANG S.Research towards YOLO-series algorithms：comparison and analysis of object detection models for realtime UAV applications[J].Journal of Physics：Conference Series，2021，1948（1）：012021.
[47] 李航，朱明.基于深度卷积神经网络的小目标检测算法[J].计算机工程与科学，2020，42（4）：649-657.
LI H，ZHU M.A small object detection algorithm based on deep convolutional neural network[J].Computer Engineering and Science，2020，42（4）：649-657.
[48] ZHANG Y，SONG C，ZHANG D.Deep learning-based object detection improvement for tomato disease[J].IEEE Access，2020，8：56607-56614.
[49] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[50] ZHU G，WEI Z，LIN F.An object detection method combining multi-level feature fusion and region channel attention[J].IEEE Access，2022，9：25101-25109.
[51] 陈旭，彭冬亮，谷雨.基于改进YOLOv5s的无人机图像实时目标检测[J].光电工程，2022，49（3）：69-81.
CHEN X，PENG D L，GU Y.Real time target detection of UAV image based on improved YOLOv5s[J].Opto-Electronic Engineering，2022，49（3）：69-81.
[52] WANG C，WANG H，YU F，et al.A high-precision fast smoky vehicle detection method based on improved YOLOv5 network[C]//IEEE International Conference on Artificial Intelligence and Industrial Design（AIID），2022：255-259.
[53] 乔延婷，陈万培，张涛.基于SSD的轻量级车辆检测网络[J].无线电工程，2020，50（11）：926-931.
QIAO Y T，CHEN W P，ZHANG T.A lightweight vehicle detection network based on SSD[J].Radio Engineering，2020，50（11）：926-931.
[54] 宋世奇，李旭，祝雪芬.基于改进SSD的航拍城市道路车辆检测方法[J].传感器与微系统，2021，40（1）：114-117.
SONG S Q，LI X，ZHU X F，et al.Urban road vehicle detetion method by aerial photography based on improved SSD[J].Transducer and Miscrosystem Technologies，2021，40（1）：114-117.
[55] 鞠默然，罗海波，刘广琦，等.采用空间注意力机制的红外弱小目标检测网络[J].光学精密工程，2021，29（4）：843-853.
JU M R，LUO H B，LIU G Q，et al.Infrared dim and small target detection network based on spatial attention mechanism[J].Optics and Precision Engineering，2021，29（4）：843-853.
[56] 陈静怡.基于多任务学习的乳腺医学图像目标检测算法研究[D].哈尔滨：哈尔滨工程大学，2021.
CHEN J Y.Research on target detection algorithm of breast medical image based on multi task learning[D].Harbin：Harbin Engineering University，2021.
[57] SHEN Z Q，LIU Z，LI J G，et al.DSOD：learning deeply supervised object detectors from scratch[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision，Venice，Oct 22-29，2017.Washington：IEEE Computer Society，2017：1937-1945.
[58] 奚琦，张正道，彭力.基于改进密集网络与二次回归的小目标检测算法[J].计算机工程，2021，47（4）：241-247.
XI Q，ZHANG Z D，PENG L.Small object detection algorithm based on improved dense network and quadratic regression[J].Computer Engineering，2021，47（4）：241-247.
[59] LU X，KANG X，NISHIDE S，et al.Object detection based on SSD-ResNet[C]//2019 IEEE 6th International Conference on Cloud Computing and Intelligence Systems（CCIS），2019：89-92.
[60] 郑儒楠，仇晓兰.结合置信度的多通道星载SAR在轨舰船低虚警快速检测[J].遥感学报，2022，26（3）：516-527.
ZHENG R N，QIU X L.Fast detection method for low false alarm of multi-channel spaceborne SAR image combined with confidence calculation[J].Journal of Remote Sensing，2022，26（3）：516-527.
[61] 蒋晨，钱永明，姚兴田等.基于可变形卷积改进SSD算法的目标检测方法[J].电子测量技术，2022，45（16）：116-122.
JIANG C，QIAN Y M，YAO X T，et al.Target detection method based on deformable convolution improved SSD algorithm[J].Electronic Measurement Technology，2022，45（16）：116-122.
[62] LIU S，HUANG D，WANG Y H.Receptive field block net for accurate and fast object detection[C]//Proceedings of ECCV 2018，2018：404-419.
[63] 陈家栋，雷斌.基于改进SSD轻量化的交通路口目标检测[J].传感器与微系统，2022，41（10）：117-121.
CHEN J D，LEI B.Traffic intersection target detection based on improved SSD lightweight[J].Sensors and Microsystems，2022，41（10）：117-121.
[64] 刘鑫，黄进，杨涛，等.改进CenterNet的无人机小目标捕获检测方法[J].计算机工程与应用，2022，58（14）：96-104.
LIU X，HUANG J，YANG T，et al.Improved small object detection for UAV acquisition based on CenterNet[J].Computer Engineering and Applications，2022，58（14）：96-104.
[65] PAN H，CHEN G，JIANG J.Adaptively dense feature pyramid network for object detection[J].IEEE Access，2019，7：81132-81144.
[66] 张海涛，张梦.引入通道注意力机制的SSD目标检测算法[J].计算机工程与应用，2020，46（8）：264-270.
ZHANG H T，ZHANG M.SSD target detection algorithm with channel attention mechanism[J].Computer Engineering and Applications，2020，46（8）：264-270.
[67] 陈灏然，彭力，李文涛，等.加权网络下的小目标检测算法[J].计算机科学与探索，2022，16（9）：2143-2150.
CHEN H R，PENG L，LI W T，et al.Small object detection algorithm based on weighted network[J].Journal of Frontiers of Computer Science and Technology，2022，16（9）：2143-2150.
[68] 李文涛，彭力.多尺度通道注意力融合网络的小目标检测算法[J].计算机科学与探索，2021，15（12）：2390-2400.
LI W T，PENG L.Small objects detection algorithm with multi-scale channel attention fusion network[J].Journal of Frontiers of Computer Science and Technology，2021，15（12）：2390-2400.
[69] LIN T，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（2）：318-327.
[70] HU H，BAI S，LI A，et al.Dense relation distillation with context-aware aggregation for few shot object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2021：10185-10194.
[71] SUN B，LI B，CAI S，et al.FSCE：few-shot object detection via contrastive proposal encoding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2021：7352-7362.
[72] IANDOLA F N，HAN S，MOSKEWICZ M W，et al.SqueezeNet：AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[J].arXiv：1602. 07360，2016.
[73] 薛远亮，金国栋，侯笑晗，等.融合注意力机制与改进SSD算法的SAR舰船目标检测方法[J].计算机应用研究，2022，39（1）：35-41.
XUE Y L，JIN G D，HOU X H，et al.SAR ship target detection method combining attention mechanism and improved SSD algorithm[J].Computer Application Research，2022，39（1）：35-41.
[74] KIM K H，HONG S，ROH B，et al.PVANET：deep but lightweight neural networks for real-time object detection[J].arXiv：1608.08021，2016.
[75] XIE S，ZHENG H，LIU C，et al.SNAS：stochastic neural architecture search[J].arXiv：1812.09926，2018.
[76] XING M.SAR target detection based on improved SSD with saliency map and residual network[J].Remote Sensing，2022，14：180.
[77] ZHAO Q，SHENG T，Wang Y，et al.M2Det：a single-shot object detector based on multi-level feature pyramid network[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019，33（1）：9259-9266.
[78] ZHANG S，CHI C，YAO Y，et al.Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：9759-9768.
[79] DAI X，YUAN X，WEI X.Data augmentation for thermal infrared object detection with cascade pyramid generative adversarial network[J].Applied Intelligence，2021，52（6）：1-15.
[80] YANG Y，MA C，FAN B，et al.Photonics-based simultaneous angle of arrival and frequency measurement system with multiple-target detection capability[J].Journal of Lightwave Technology，2021，39（24）：7656-7663.
[81] ZHANG S，XIE Y，WAN J，et al.WiderPerson：a diverse dataset for dense pedestrian detection in the wild[J].IEEE Transactions on Multimedia，2020，22（2）：380-393.
[82] SHI W，BAO S，TAN D.FFESSD：an accurate and efficient single-shot detector for target detection[J].Applied Sciences，2019，9（20）：4276.