[1] RedmonJ,[\s]{1}DivvalaS,[\s]{1}GirshickR,[\s]{1}et[\s]{1}al.[\s]{1}You[\s]{1}only[\s]{1}look[\s]{1}once:[\s]{1}unified,[\s]{1}real-time[\s]{1}object[\s]{1}detection[C]∥2016[\s]{1}IEEE[\s]{1}Conference[\s]{1}on[\s]{1}Computer[\s]{1}Vision[\s]{1}and[\s]{1}Pattern[\s]{1}Recognition(CVPR),[\s]{1}June[\s]{1}27-30,[\s]{1}2016,[\s]{1}Las[\s]{1}Vegas.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2015:[\s]{1}779-[\s]{1}788.[\s]{1}

[2] 刘华平, 李建民, 胡晓林, 等. 动态场景下的交通标识检测与识别研究进展[J]. 中国图象图形学报, 2013, 18(5): 493-503.

    Liu H P, Li J M, Hu X L, et al. Recent progress in detection and recognition of the traffic signs in dynamic scenes[J]. Journal of Image and Graphics, 2013, 18(5): 493-503.

[3] 高东东, 徐晓婷, 李博. 红外/白光混合补光系统在智能交通中的应用研究[J]. 红外与激光工程, 2018, 47(9): 0918006.

    Gao D D, Xu X T, Li B. Research on application of infrared and white light mixed supplemental lighting system in intelligent transportation[J]. Infrared and Laser Engineering, 2018, 47(9): 0918006.

[4] 徐岩, 韦镇余. 一种改进的交通标志图像识别算法[J]. 激光与光电子学进展, 2017, 54(2): 021001.

    Xu Y, Wei Z Y. An improved traffic sign image recognition algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021001.

[5] YangY,[\s]{1}Wu[\s]{1}FC.[\s]{1}Real-time[\s]{1}traffic[\s]{1}sign[\s]{1}detection[\s]{1}via[\s]{1}color[\s]{1}probability[\s]{1}model[\s]{1}and[\s]{1}integral[\s]{1}channel[\s]{1}features[M][\s]{1}∥Li[\s]{1}S,[\s]{1}Liu[\s]{1}C,[\s]{1}Wang[\s]{1}Y.[\s]{1}Pattern[\s]{1}recognition.[\s]{1}CCPR[\s]{1}2014.[\s]{1}Communications[\s]{1}in[\s]{1}computer[\s]{1}and[\s]{1}information[\s]{1}science.[\s]{1}Berlin,[\s]{1}Heidelberg:[\s]{1}Springer,[\s]{1}2014,[\s]{1}484:[\s]{1}545-[\s]{1}554.[\s]{1}

[6] Wang G Y, Ren G H, Wu Z L, et al. A fast and robust ellipse-detection method based on sorted merging[J]. The Scientific World Journal, 2014, 2014: 481312.

[7] LiangM,[\s]{1}Yuan[\s]{1}MY,[\s]{1}Hu[\s]{1}XL,[\s]{1}et[\s]{1}al.[\s]{1}Traffic[\s]{1}sign[\s]{1}detection[\s]{1}by[\s]{1}ROI[\s]{1}extraction[\s]{1}and[\s]{1}histogram[\s]{1}features-based[\s]{1}recognition[C]∥The[\s]{1}2013[\s]{1}International[\s]{1}Joint[\s]{1}Conference[\s]{1}on[\s]{1}Neural[\s]{1}Networks[\s]{1}(IJCNN),[\s]{1}August[\s]{1}4-9,[\s]{1}2013,[\s]{1}Dallas,[\s]{1}TX,[\s]{1}USA.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2013:[\s]{1}6706810.[\s]{1}

[8] Wang[\s]{1}GY,[\s]{1}Ren[\s]{1}GH,[\s]{1}Wu[\s]{1}ZL,[\s]{1}et[\s]{1}al.[\s]{1}A[\s]{1}hierarchical[\s]{1}method[\s]{1}for[\s]{1}traffic[\s]{1}sign[\s]{1}classification[\s]{1}with[\s]{1}support[\s]{1}vector[\s]{1}machines[C]∥The[\s]{1}2013[\s]{1}International[\s]{1}Joint[\s]{1}Conference[\s]{1}on[\s]{1}Neural[\s]{1}Networks[\s]{1}(IJCNN),[\s]{1}August[\s]{1}4-9,[\s]{1}2013,[\s]{1}Dallas,[\s]{1}TX,[\s]{1}USA.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2013:[\s]{1}6706803.[\s]{1}

[9] Xiao[\s]{1}ZT,[\s]{1}Yang[\s]{1}ZJ,[\s]{1}GengL,[\s]{1}et[\s]{1}al.[\s]{1}Traffic[\s]{1}sign[\s]{1}detection[\s]{1}based[\s]{1}on[\s]{1}histograms[\s]{1}of[\s]{1}oriented[\s]{1}gradients[\s]{1}and[\s]{1}boolean[\s]{1}convolutional[\s]{1}neural[\s]{1}networks[C]∥2017[\s]{1}International[\s]{1}Conference[\s]{1}on[\s]{1}Machine[\s]{1}Vision[\s]{1}and[\s]{1}Information[\s]{1}Technology[\s]{1}(CMVIT),[\s]{1}February[\s]{1}17-19,[\s]{1}2017,[\s]{1}Singapore.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2017:[\s]{1}111-[\s]{1}115.[\s]{1}

[10] GirshickR,[\s]{1}DonahueJ,[\s]{1}DarrellT,[\s]{1}et[\s]{1}al.[\s]{1}Rich[\s]{1}feature[\s]{1}hierarchies[\s]{1}for[\s]{1}accurate[\s]{1}object[\s]{1}detection[\s]{1}and[\s]{1}semantic[\s]{1}segmentation[C]∥2014[\s]{1}IEEE[\s]{1}Conference[\s]{1}on[\s]{1}Computer[\s]{1}Vision[\s]{1}and[\s]{1}Pattern[\s]{1}Recognition,[\s]{1}June[\s]{1}23-28,[\s]{1}2014,[\s]{1}Columbus,[\s]{1}OH,[\s]{1}USA.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2014:[\s]{1}580-[\s]{1}587.[\s]{1}

[11] 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.

[12] GirshickR.[\s]{1}Fast[\s]{1}R-CNN[C]∥2015[\s]{1}IEEE[\s]{1}International[\s]{1}Conference[\s]{1}on[\s]{1}Computer[\s]{1}Vision[\s]{1}(ICCV),[\s]{1}December[\s]{1}7-13,[\s]{1}2015,[\s]{1}Santiago,[\s]{1}Chile.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2015:[\s]{1}1440-[\s]{1}1448.[\s]{1}

[13] 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.

[14] RedmonJ,[\s]{1}FarhadiA.[\s]{1}YOLO9000:[\s]{1}better,[\s]{1}faster,[\s]{1}stronger[C]∥2017[\s]{1}IEEE[\s]{1}Conference[\s]{1}on[\s]{1}Computer[\s]{1}Vision[\s]{1}and[\s]{1}Pattern[\s]{1}Recognition[\s]{1}(CVPR),[\s]{1}July[\s]{1}21-26,[\s]{1}2017,[\s]{1}Honolulu,[\s]{1}HI,[\s]{1}USA.[\s]{1}New[\s]{1}York:[\s]{1}IEEE,[\s]{1}2017:[\s]{1}17355115.[\s]{1}

[15] LiuW,[\s]{1}AnguelovD,[\s]{1}ErhanD,[\s]{1}et[\s]{1}al.[\s]{1}SSD:[\s]{1}single[\s]{1}shot[\s]{1}MultiBox[\s]{1}detector[M][\s]{1}∥Leibe[\s]{1}B,[\s]{1}Matas[\s]{1}J,[\s]{1}Sebe[\s]{1}N,[\s]{1}et[\s]{1}al.[\s]{1}Computer[\s]{1}vision-ECCV[\s]{1}2016.[\s]{1}Lecture[\s]{1}notes[\s]{1}in[\s]{1}computer[\s]{1}science.[\s]{1}Cham:[\s]{1}Springer,[\s]{1}2016,[\s]{1}9905:[\s]{1}21-[\s]{1}37.[\s]{1}

[16] Chang X J, Ma Z G, Yang Y, et al. Bi-level semantic representation analysis for multimedia event detection[J]. IEEE Transactions on Cybernetics, 2017, 47(5): 1180-1197.

[17] Chang X J, Yu Y L, Yang Y, et al. Semantic pooling for complex event analysis in untrimmed videos[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8): 1617-1632.

[18] Chang X J, Yang Y. Semisupervised feature analysis by mining correlations among multiple tasks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2294-2305.

[19] Kuang P, Ma T S, Li F, et al. Real-time pedestrian detection using convolutional neural networks[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2018, 32(11): 1856014.

[20] 谢一德.[\s]{1}基于深度卷积神经网络和图像传感器的道路多目标检测研究[D].[\s]{1}北京:[\s]{1}北京交通大学,[\s]{1}2018:[\s]{1}72-[\s]{1}85.[\s]{1}

    Xie[\s]{1}YD.[\s]{1}Study[\s]{1}on[\s]{1}multi-target[\s]{1}detection[\s]{1}based[\s]{1}on[\s]{1}deep[\s]{1}convolution[\s]{1}neural[\s]{1}network[\s]{1}and[\s]{1}image[\s]{1}sensor[D].[\s]{1}Beijing:[\s]{1}Beijing[\s]{1}Jiaotong[\s]{1}University,[\s]{1}2018:[\s]{1}72-[\s]{1}85

[21] 张淑芳, 朱彤. 一种基于HDR技术的交通标志牌检测和识别方法[J]. 激光与光电子学进展, 2018, 55(9): 091006.

    Zhang S F, Zhu T. A method of traffic sign detection and recognition based on HDR technology[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091006.

[22] 马永杰, 李雪燕, 宋晓凤. 基于改进深度卷积神经网络的交通标志识别[J]. 激光与光电子学进展, 2018, 55(12): 121009.

    Ma Y J, Li X Y, Song X F. Traffic sign recognition based on improved deep convolution neural network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121009.