[1] 尹宏鹏, 陈波, 柴毅, 等. 基于视觉的目标检测与跟踪综述[J]. 自动化学报, 2016, 42(10): 1466-1489.

    Yin H P, Chen B, Chai Y, et al. Vision-based object detection and tracking: a review[J]. Acta Automatica Sinica, 2016, 42(10): 1466-1489.

[2] 张新钰, 高洪波, 赵建辉, 等. 基于深度学习的自动驾驶技术综述[J]. 清华大学学报(自然科学版), 2018, 58(4): 438-444.

    Zhang X Y, Gao H B, Zhao J H, et al. Overview of deep learning intelligent driving methods[J]. Journal of Tsinghua University(Science and Technology), 2018, 58(4): 438-444.

[3] 李汉冰, 徐春阳, 胡超超. 基于YOLOV3改进的实时车辆检测方法[J]. 激光与光电子学进展, 2020, 57(10): 101507.

    Li H B, Xu C Y, Hu C C. Improved real-time vehicle detection method based on YoLOV3[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101507.

[4] 李珣, 时斌斌, 刘洋, 等. 基于改进YOLOv2模型的多车辆目标识别方法[J]. 激光与光电子学进展, 2020, 57(10): 101010.

    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): 101010.

[5] 王得成, 陈向宁, 赵峰, 等. 基于卷积神经网络和RGB-D图像的车辆检测算法[J]. 激光与光电子学进展, 2019, 56(18): 181003.

    Wang D C, Chen X N, Zhao F, et al. Vehicle detection algorithm based on convolutional neural network and RGB-D images[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181003.

[6] Gowsikhaa D, Abirami S, Baskaran R. Automated human behavior analysis from surveillance videos: a survey[J]. Artificial Intelligence Review, 2014, 42(4): 747-765.

[7] 黄凯奇, 陈晓棠, 康运锋, 等. 智能视频监控技术综述[J]. 计算机学报, 2015, 38(6): 1093-1118.

    Huang K Q, Chen X T, Kang Y F, et al. Intelligent visual surveillance: a review[J]. Chinese Journal of Computers, 2015, 38(6): 1093-1118.

[8] 李少波, 杨静, 王铮, 等. 缺陷检测技术的发展与应用研究综述[J/OL]. ( 2019-04-04)[2019-11-26]. https:∥doi.org/10. 16383/j.aas.c180538.

    Li SB, YangJ, WangZ, et al. and application of defect detection technology[J/OL]. ( 2019-04-04)[2019-11-26]. https:∥doi.org/10. 16383/j.aas.c180538.

[9] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

[10] KrizhevskyA, SutskeverI, Hinton GE. ImageNet classification with deep convolutional neural networks[C]∥Proceedings of the 25th International Conference on Neural Information Processing Systems, December 3-6, 2012, Lake Tahoe, Nevada. New York: ACM, 2012, 1: 1097- 1105.

[11] Image data set[Online]. [2019-11-11].http:∥www.image-net.

[12] 杨观赐, 杨静, 李少波, 等. 基于Dopout与ADAM优化器的改进CNN算法[J]. 华中科技大学学报(自然科学版), 2018, 46(7): 122-127.

    Yang G C, Yang J, Li S B, et al. Modified CNN algorithm based on Dropout and ADAM optimizer[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2018, 46(7): 122-127.

[13] NairV, Hinton GE. Rectified linear units improve restricted Boltzmann machines[C]∥Proceedings of the 27th International Conference on Machine Learning(ICML), Haifa, 2010: 807- 814.

[14] Yang J, Li S B, Gao Z, et al. Real-time recognition method for 0.8 cm darning needle and KR22 bearing based on convolution neural network and data increase[J]. Applied Sciences, 2018, 8(10): 1857.

[15] SimonyanK, Zisserman A. Very deep convolutional networks for large-scale image recognition[EB/OL]. ( 2014-09-04)[2019-11-26]. https:∥arxiv.org/abs/1409.1556v1.

[16] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.

[17] RonnebergerO, FischerP, Brox T. U-Net: convolutional networks for biomedical image segmentation[EB/OL]. ( 2015-05-18)[2019-11-26]. https:∥arxiv.org/abs/1505. 04597.

[18] BadrinarayananV, HandaA, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for scene segmentation[EB/OL]. ( 2015-11-01)[2019-11-26]. http:∥de.arxiv.org/pdf/1511. 00561.

[19] SzegedyC, LiuW, JiaY, et al. ( 2014-09-17)[2019-11-26]. https:∥arxiv.org/abs/1409. 4842.

[20] HeK, ZhangX, RenS, et al. ( 2015-12-10)[2019-11-26]. https:∥ arxiv.org/abs/1512. 03385.

[21] HuangG, LiuZ, Laurens V DM, et al.( 2016-08-25)[2019-11-26]. https:∥arxiv.org/abs/1608. 06993.

[22] GirshickR, DonahueJ, DarrellT, et al. and semanticsegmentation[EB/OL]. ( 2013-11-11)[2019-11-26]. https:∥arxiv.org/abs/1311. 2524.

[23] van de Sande K E A, Uijlings J RR, GeversT, et al. Segmentation as selective search for object recognition[C]∥2011 International Conference on Computer Vision, November 6-13, 2011, Barcelona, Spain. IEEE, 2011: 154- 171.

[24] 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.

[25] Girshick R. FastR-CNN[EB/OL]. ( 2015-04-30)[2019-11-26]. https:∥arxiv.org/abs/1504. 08083.

[26] ScholkopfB, PlattJ, Hofmann T. Multi-task feature learning[EB/OL]. ( 2006-12-04)[2019-11-26]. https:∥dl.acm.org/ citation.cfm?id=2976462.

[27] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

[28] Hosang J, Benenson R, Dollar P, et al. What makes for effective detection proposals?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(4): 814-830.

[29] DaiJ, LiY, HeK, et al. ( 2016-05-20)[2019-11-26]. https:∥arxiv.org/abs/1605.06409?context=cs.

[30] AgrawalP, GirshickR, Malik J. Analyzing the performance of multi-layer neural networks for object recognition[EB/OL]. ( 2014-07-07)[2019-11-26]. https:∥arxiv.org/abs/1407. 1610.

[31] Hinton G E, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4): 212-223.

[32] Lin TY, DollarP, GirshickR, et al. ( 2016-12-09)[2019-11-26]. https:∥arxiv.org/abs/1612. 03144.

[33] He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397.

[34] XieS, GirshickR, DollarP, et al. ( 2016-11-16)[2019-11-26]. https:∥arxiv.org/abs/1611. 05431.

[35] PengC, XiaoT, Li ZM, et al. ( 2017-11-20)[2019-11-26]. https:∥arxiv.org/abs/1711. 07240.

[36] Qin L K, Gong Y F, Tang T Q, et al. Training deep nets with progressive batch normalization on multi-GPUs[J]. International Journal of Parallel Programming, 2019, 47(3): 373-387.

[37] GidarisS, Komodakis N. Object detection via a multi-region & semantic segmentation-aware CNN model[EB/OL]. ( 2015-05-07)[2019-11-26]. https:∥arxiv.org/abs/1505. 01749.

[38] KongT, Yao AB, Chen YR, et al. and joint objectdetection[EB/OL]. ( 2016-04-03)[2019-11-26]. https:∥arxiv.org/abs/1604. 00600.

[39] YangB, Yan JJ, ZhenL, et al. ( 2016-04-12)[2019-11-26]. https:∥arxiv.org/abs/1604. 03239.

[40] WangX, ShrivastavaA, Gupta A. A-Fast-RCNN: hard positive generation via adversary for object detection[EB/OL]. ( 2017-04-11)[2019-11-26]. https:∥arxiv.org/abs/1704. 03414.

[41] Li ZM, PengC, YuG, et al. ( 2017-11-20)[2019-11-26]. https:∥arxiv.org/abs/1711. 07264.

[42] Cai ZW, Vasconcelos N. Cascade R-CNN: delving into high quality object detection[EB/OL]. ( 2017-12-03)[2019-11-26]. https:∥arxiv.org/abs/1712. 00726.

[43] SinghB, Davis L S. An analysis of scale invariance in object detection-SNIP[EB/OL]. ( 2017-11-22)[2019-11-26]. https:∥arxiv.org/abs/1711. 08189.

[44] GhiasiG, Lin TY, PangR, et al. ( 2019-04-16)[2019-11-26]. https:∥arxiv.org/abs/1904. 07392.

[45] LiY, ChenY, WangN, et al. ( 2019-01-07)[2019-11-26]. https:∥arxiv.org/abs/1901.01892?context=cs. CV.

[46] SermanetP, EigenD, ZhangX, et al., localization and detection using convolutionalnetworks[EB/OL]. ( 2013-12-21)[2019-11-26]. https:∥arxiv.org/abs/1312. 6229.

[47] RedmonJ, DivvalaS, GirshickR, et al., real-time objectdetection[EB/OL]. ( 2015-06-08)[2019-11-26]. https:∥arxiv.org/abs/1506. 02640.

[48] LiuW, AnguelovD, ErhanD, et al.SSD: single shot MultiBox detector[M] ∥Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21- 37.

[49] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.

[50] Fu CY, LinW, RangaA, et al. ( 2017-01-23)[2019-11-26]. https:∥arxiv.org/abs/1701.06659v1.

[51] RedmonJ, FarhadiA. YOLO9000: better, faster, stronger[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017. Honolulu, HI. IEEE, 2017: 6517- 6525.

[52] Lin TY, GoyalP, GirshickR, et al. ( 2017-08-07)[2019-11-26]. https:∥arxiv.org/abs/1708.02002v2.

[53] RedmonJ, Farhadi A. YOLOv3: an incremental improvement[EB/OL]. ( 2018-04-08)[2019-11-26]. https:∥arxiv.org/abs/1804. 02767.

[54] NajibiM, RastegariM, Davis L S. G-CNN: an iterative grid based object detector[EB/OL]. ( 2015-12-24)[2019-11-26]. https:∥arxiv.org/abs/1512. 07729.

[55] JeongJ, ParkH, Kwak N. Enhancement of SSD by concatenating feature maps for object detection[EB/OL]. ( 2017-05-26)[2019-11-26]. https:∥arxiv.org/abs/1705.09587v1.

[56] Shen ZQ, LiuZ, LiG, et al. ( 2017-08-03)[2019-11-26]. https:∥arxiv.org/abs/1708.01241?context=cs. LG.

[57] KongT, Sun FC, Yao AB, et al. ( 2017-07-06)[2019-11-26]. https:∥arxiv.org/abs/1707.01691?context=cs.

[58] ZhouP, Ni BB, GengC, et al. ( 2019-04-05)[2019-11-26]. http:∥ openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Scale-Transferrable_Object_Detection_CVPR_2018_p- aper.pdf.

[59] Lin TY, DollarP, GirshickR, et al. ( 2016-12-09)[2019-11-26]. https:∥arxiv.org/abs/1612.03144?context=cs.

[60] Zhao QJ, ShengT, Wang YT, et al. ( 2018-11-12)[2019-11-26]. https:∥arxiv.org/abs/1811. 04533.

[61] Zhu CC, He YH, Savvides M. Feature selective anchor-free module for single-shot object detection[EB/OL]. ( 2019-03-02)[2019-11-26]. https:∥arxiv.org/abs/1903.00621v1.

[62] TianZ, Shen CH, ChenH, et al. ( 2019-04-02)[2019-11-26]. https:∥arxiv.org/abs/1904. 01355.

[63] KongT, Sun FC, Liu HP, et al. ( 2019-04-08)[2019-11-26]. https:∥arxiv.org/abs/1904. 03797.

[64] HuangL, YangY, DengY, et al. ( 2015-09-16)[2019-11-26]. https:∥arxiv.org/abs/1509. 04874.

[65] LawH, Deng J. CornerNet: detecting objects as paired keypoints[EB/OL]. ( 2018-08-03)[2019-11-26]. https:∥arxiv. org/abs/1808.01244v1.

[66] Zhou XY, Zhuo JC, Krähenbühl P. Bottom-up object detection by grouping extreme and centerpoints[EB/OL]. ( 2019-01-23)[2019-11-26]. https:∥arxiv.org/abs/1901.08043v1.

[67] Duan KW, BaiS, Xie LX, et al. ( 2019-04-17)[2019-11-26]. https:∥arxiv.org/abs/1904.08189?context=cs.

[68] Yu JH, JiangY, Wang ZY, et al. ( 2016-08-04)[2019-11-26]. https:∥arxiv.org/abs/1608. 01471.

[69] Zhou XY, Wang DQ, KrähenbühlP, et al. Objects as points[EB/OL].( 2019-04-16)[2019-11-26]. https:∥arxiv.org/abs/1904. 07850v1.

[70] LuX, Li BY, Yue YX, et al. ( 2018-11-29)[2019-11-26]. https:∥arxiv.org/abs/1811.12030v1.

[71] LawH, TengY, RussakovskyO, et al. ( 2019-04-180)[2019-11-26]. https:∥arxiv.org/abs/1904. 08900.