大视场域的目标检测与识别算法综述 下载: 2026次
李唐薇, 童官军, 李宝清, 卢晓洋. 大视场域的目标检测与识别算法综述[J]. 激光与光电子学进展, 2020, 57(12): 120002.
Tangwei Li, Guanjun Tong, Baoqing Li, Xiaoyang Lu. Review on Object Detection and Recognition in Large Field of View[J]. Laser & Optoelectronics Progress, 2020, 57(12): 120002.
[2] 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.
[3] SaezA, Bergasa LM, RomeralE, et al. CNN-based fisheye image real-time semantic segmentation[C]∥2018 IEEE Intelligent Vehicles Symposium (IV), June 26-30, 2018. Changshu. IEEE, 2018: 1039- 1044.
[4] ZhangM, YaoJ, Xia MH, et al. Line-based multi-label energy optimization for fisheye image rectification and calibration[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015. Boston, MA, USA. IEEE, 2015: 4137- 4145.
[5] Yin XQ, Wang XC, YuJ, et al.FishEyeRecNet: A multi-context collaborative deep network for fisheye image rectification[M] ∥Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 475- 490.
[6] 鞠默然, 罗海波, 王仲博, 等. 改进的YOLO V3算法及其在小目标检测中的应用[J]. 光学学报, 2019, 39(7): 0715004.
[7] Wang JQ, ChenK, YangS, et al. Region proposal by guided anchoring[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019. Long Beach, CA, USA. IEEE, 2019: 2965- 2974.
[8] Cai ZW, VasconcelosN. Cascade R-CNN: delving into high quality object detection[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018. Salt Lake City, UT. IEEE, 2018: 6154- 6162.
[9] LiuL, Ouyang WL, Wang XG, et al. ( 2019-08-22)[2019-10-10]. https: ∥arxiv. org/abs/1809. 02165[LinkOut]
[10] 李显杰, 冯大伟, 向阳. 折衍混合环带式全景光学系统设计[J]. 激光与光电子学进展, 2019, 56(18): 182201.
[11] ZhangW, Cong MY, Wang LP. Algorithms for optical weak small targets detection and tracking: review[C]∥International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003, December 14-17, 2003. Nanjing. IEEE, 2003: 643- 647.
[12] Rees D W. Panoramic television viewing system: US3505465[P].1970-04-07.
[13] BoultT, MichealsR, ErkanA, et al. Frame-rate multi-body tracking for surveillance[C]∥Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999: 1106- 1112.
[14] Rybski PE, de la TorreF, PatilR, et al. CAMEO: camera assisted meeting event observer[C]∥IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004, April 26-May 1, 2004. New Orleans, LA, USA. IEEE, 2004.
[15] 曾吉勇, 苏显渝. 水平场景无畸变的折反射全景成像系统[J]. 光学学报, 2003, 23(5): 636-640.
[16] 陈立栋, 王炜, 张茂军, 等. 双反射面互补结构的折反射全向成像系统设计[J]. 光学学报, 2010, 30(12): 3487-3494.
[17] 赵琪, 石鑫, 龚薇, 等. 基于并行波前校正算法的大视场深穿透光学显微成像[J]. 中国激光, 2018, 45(12): 1207001.
[18] 李立鸿, 施鹏飞, 赵群飞. 基于多分辨率技术的快速全景图图像匹配算法[J]. 中国图象图形学报, 2006, 11(9): 1271-1275.
Li L H, Shi P F, Zhao Q F. A multi-resolution based image registration method for panorama[J]. Journal of Image and Graphics, 2006, 11(9): 1271-1275.
[19] ZhangZ. Flexible camera calibration by viewing a plane from unknown orientations[C]∥Proceedings of the Seventh IEEE International Conference on Computer Vision, September 20-27, New York: IEEE, 1999: 666- 673.
[20] 吴军, 王玲容, 黄明益, 等. 多几何约束下的鱼眼相机单像高精度标定[J]. 光学学报, 2018, 38(11): 1115001.
[22] Jeong JS, Kim HT, KimB, et al. Wide rear vehicle recognition using a fisheye lens camera image[C]∥2016 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), October 25-28, 2016. Jeju, South Korea. IEEE, 2016: 691- 693.
[23] DalalN, TriggsB. Histograms of oriented gradients for human detection[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), June 20-25, 2005, San Diego, CA, USA. IEEE, 2005: 886- 893.
[24] SilbersteinS, LeviD, KoganV, et al. Vision-based pedestrian detection for rear-view cameras[C]∥2014 IEEE Intelligent Vehicles Symposium Proceedings, June 8-11, 2014. MI, USA. IEEE, 2014: 853- 860.
[25] LeviD, SilbersteinS. Tracking and motion cues for rear-view pedestrian detection[C]∥2015 IEEE 18th International Conference on Intelligent Transportation Systems, September 15-18, 2015. Gran Canaria, Spain. IEEE, 2015: 664- 671.
[26] BertozziM, CastangiaL, CattaniS, et al. 360° detection and tracking algorithm of both pedestrian and vehicle using fisheye images[C]∥2015 IEEE Intelligent Vehicles Symposium (IV), June 28-July 1, 2015. Seoul, South Korea. IEEE, 2015: 132- 137.
[27] YangB, Yan JJ, LeiZ, et al. Aggregate channel features for multi-view face detection[C]∥IEEE International Joint Conference on Biometrics, September 29-October 2, 2014. Clearwater, FL, USA. IEEE, 2014: 1- 8.
[28] Suhr J K, Jung H G. Rearview camera-based backover warning system exploiting a combination of pose-specific pedestrian recognitions[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1122-1129.
[29] FelzenszwalbP, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model[C]∥2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2008. Anchorage, AK, USA. IEEE, 2008: 1- 8.
[30] 于红绯, 刘威, 袁淮, 等. 基于子块运动补偿的运动目标检测[J]. 电子学报, 2017, 45(1): 173-180.
Yu H F, Liu W, Yuan H, et al. Moving object detection based on sub-block motion compensation[J]. Acta Electronica Sinica, 2017, 45(1): 173-180.
[31] MartinezE, del Pobil AP. A panoramic vision system for human-robot interaction[C]∥2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI), March 2-5, 2010. Osaka. IEEE, 2010: 171- 172.
[32] 丁莹, 权巍, 韩成. 局部视角无畸变的运动目标检测加速算法[J]. 科学技术与工程, 2016, 16(6): 70-75.
Ding Y, Quan W, Han C. A motion detection accelerated algorithm based on distortion correcting of local field angle[J]. Science Technology and Engineering, 2016, 16(6): 70-75.
[33] ViolaP, JonesM. Rapid object detection using a boosted cascade of simple features[C]∥Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, December 8-14, San Diego, CA, USA, 2001: 511- 518.
[34] 张宝峰, 马志军, 朱均超, 等. 基于DSP的鱼眼图像实时校正系统的实现[J]. 激光与红外, 2015, 45(2): 181-184.
Zhang B F, Ma Z J, Zhu J C, et al. Implementation of fisheye image real-time correction based on DSP[J]. Laser & Infrared, 2015, 45(2): 181-184.
[35] 吴泽俊, 吴庆阳, 张佰春. 一种新的基于球面模型的鱼眼镜头标定方法[J]. 中国激光, 2015, 42(5): 0508006.
[36] YoshimiK, TakahashiK. Warping approach for rearview pedestrian detection with fish eye cameras[C]∥2017 IEEE International Conference on Vehicular Electronics and Safety (ICVES), June 27-28, 2017. Vienna, Austria. IEEE, 2017: 121- 126.
[37] 蔡成涛, 吴科君, 刘秋飞, 等. 基于改进YOLO算法的全景多目标实时检测[J]. 计算机工程与设计, 2018, 39(10): 3259-3264, 3271.
Cai C T, Wu K J, Liu Q F, et al. Panoramic multi-object real-time detection based on improved YOLO algorithm[J]. Computer Engineering and Design, 2018, 39(10): 3259-3264, 3271.
[38] 徐佳, 杨鸿波, 宋阳, 等. 基于鱼眼摄像头的一种人脸识别技术[J]. 信息通信, 2018, 31(1): 131-132.
Xu J, Yang H B, Song Y, et al. A face recognition technology based on fisheye camera[J]. Information & Communications, 2018, 31(1): 131-132.
[39] BagherinezhadH, RastegariM, FarhadiA. LCNN: lookup-based convolutional neural network[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017. Honolulu, HI. IEEE, 2017: 7120- 7129.
[40] 邓军, 秦学斌, 王伟峰. 一种基于深度学习模型的火焰识别方法: CN106845410A[P].2017-06-13.
DengJ, Qin XB, Wang W F. A method of flame recognition based on deep learning: CN106845410A[P].2017-06-13.
[41] Yang WY, Qian YL, Kamarainen JK, et al. Object detection in equirectangular panorama[C]∥2018 24th International Conference on Pattern Recognition (ICPR), August 20-24, 2018. Beijing. IEEE, 2018: 2190- 2195.
[42] Deng FC, Zhu XR, Ren JM. Object detection on panoramic images based on deep learning[C]∥2017 3rd International Conference on Control, Automation and Robotics (ICCAR), April 24-26, 2017. Nagoya, Japan. IEEE, 2017: 375- 380.
[43] 王志旋, 钟若飞, 谢东海. 球面全景影像自动测量路灯坐标的方法[J]. 中国图象图形学报, 2018, 23(9): 1371-1381.
Wang Z X, Zhong R F, Xie D H. Automatically measuring the coordinates of streetlights in vehicle-borne spherical images[J]. Journal of Image and Graphics, 2018, 23(9): 1371-1381.
[44] Fu JL, Alvar SR, Bajic IV, et al. ( 2019-02-07)[2019-07-19]. https: ∥arxiv. org/abs/1902. 02777v1.
[45] CohenT, WellingM. Group equivariant convolutional networks[C]∥International Conference on Machine Learning, June 19-24, 2016. New York,IEEE, 2016: 2990- 2999.
[46] Worrall DE, Garbin SJ, TurmukhambetovD, et al. Harmonic networks: deep translation and rotation equivariance[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017. Honolulu, HI. IEEE, 2017: 5028- 5037.
[47] Su YC, Grauman K. Learning spherical convolution for fast features from 360 imagery[EB/OL]. ( 2018-11-07)[2019-07-19]. https: ∥arxiv.org/abs/1708. 00919 .
[48] TatenoK, NavabN, TombariF. Distortion-aware convolutional filters for dense prediction in panoramic images[M] ∥Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 732- 750.
[49] CoorsB, Condurache AP, GeigerA. SphereNet: learning spherical representations for detection and classification in omnidirectional images[M] ∥Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 525- 541.
[50] LeeY, JeongJ, YunJ, et al. SpherePHD: applying CNNs on a spherical PolyHeDron representation of 360° images[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019. Long Beach, CA, USA. IEEE, 2019: 9173- 9181.
[51] Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981, 17(1/2/3): 185-203.
[52] Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12(1): 43-77.
[53] Haritaoglu I, Harwood D, Davis L S. W 4: real-time surveillance of people and their activities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
[54] McKenna S J, Jabri S, Duric Z, et al. Tracking groups of people[J]. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[55] Collins RT, Lipton AJ, KanadeT, et al. A system for video surveillance and monitoring[R]. Carnegie Mellon University, 2000: 1- 68.
[56] StratmannI. Omnidirectional imaging and optical flow[C]∥Proceedings of the IEEE Workshop on Omnidirectional Vision 2002. Held in conjunction with ECCV'02, June 2,2002, Copenhagen, Denmark. IEEE Comput. Soc, 2002: 104- 111.
[57] Anandan P. A computational framework and an algorithm for the measurement of visual motion[J]. International Journal of Computer Vision, 1989, 2(3): 283-310.
[58] Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981, 17(1/2/3): 185-203.
[59] LucasB, Kanade T. An iterative technique of image registration and its application tostereo[EB/OL]. ( 1981-01-01)[2019-07-19] https: ∥www. researchgate. net/publication/239061443_An_iterative_technique_of_image_registration_and_its_application_to_stereo.
[60] Fleet D J, Jepson A D. Computation of component image velocity from local phase information[J]. International Journal of Computer Vision, 1990, 5(1): 77-104.
[61] ŠamijaH, Markovi I, Petrovi I. Optical flow field segmentation in an omnidirectional camera image based on known camera motion [C]∥Proceedings of the 34th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2011), May 23-27, 2011, Opatija, Hrvatska, 2011, 165- 169.
[62] HercegD, Markovi I, Petrovi I. Real-time detection of moving objects by a mobile robot with an omnidirectional camera [C]∥2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA), September 4-6, 2011, Dubrovnik, Croatia, IEEE, 2011: 289- 294.
[63] 金敢峰. 基于多特征融合的鱼眼图像行人检测与跟踪[D]. 西安: 西安电子科技大学, 2017: 23- 28.
Jin GF. Pedestrian detection and tracking of fisheye images based on multi-feature fusion [D]. Xi'an:Xidian University, 2017: 23- 28.
[64] 吴健辉, 商橙, 张国云, 等. 基于运动点团的鱼眼图像中多目标检测方法研究[J]. 计算机工程与应用, 2016, 52(24): 158-161, 177.
Wu J H, Shang C, Zhang G Y, et al. Study of moving objects detection in fisheye image based on moving blob method[J]. Computer Engineering and Applications, 2016, 52(24): 158-161, 177.
[65] 吴健辉, 商橙, 张国云, 等. 鱼眼相机与PTZ相机相结合的主从目标监控系统[J]. 计算机工程与科学, 2017, 39(3): 540-546.
Wu J H, Shang C, Zhang G Y, et al. A master-slave object surveillance system based on fisheye camera and PTZ camera[J]. Computer Engineering and Science, 2017, 39(3): 540-546.
[66] BarisI, BastanlarY. Classification and tracking of traffic scene objects with hybrid camera systems[C]∥2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), October 16-19, 2017. Yokohama. IEEE, 2017: 1- 6.
[67] 张力丹, 朱均超, 冯为嘉. 鱼眼图像协同性目标检测方法[J]. 天津理工大学学报, 2017, 33(4): 41-45.
Zhang L D, Zhu J C, Feng W J. Fish-eye lens image co-saliency detection algorithm[J]. Journal of Tianjin University of Technology, 2017, 33(4): 41-45.
[68] SaitoM, KitaguchiK, KimuraG, et al. People detection and tracking from fish-eye image based on probabilistic appearance model[C]∥SICE Annual Conference 2011, September 13-18, 2011, Tokyo, Japan, IEEE, 2011: 435- 440.
[69] Cinaroglu I, Bastanlar Y. A direct approach for object detection with catadioptric omnidirectional cameras[J]. Signal, Image and Video Processing, 2016, 10(2): 413-420.
[70] WangT, Chang CW, Wu YS. Template-based people detection using a single downward-viewing fisheye camera[C]∥2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), November 6-9, 2017. Xiamen, China. IEEE, 2017: 719- 723.
[71] ZengY, Zhuge YZ, Lu HC, et al. Multi-source weak supervision for saliency detection[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019. Long Beach, CA, USA. IEEE, 2019: 6074- 6083.
[72] VardazaryanA, MutterD, MarescauxJ, et al.Weakly-supervised learning for tool localization in laparoscopic videos[M] ∥Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Cham: Springer International Publishing, 2018: 169- 179.
[73] ZhuangZ, Zhang GH, DongW, et al.Intelligent fault detection of high-speed railway turnout based on hybrid deep learning[M] ∥AI 2018: Advances in Artificial Intelligence. Cham: Springer International Publishing, 2018: 98- 103.
[74] Li Y, Fu K, Sun H, et al. An aircraft detection framework based on reinforcement learning and convolutional neural networks in remote sensing images[J]. Remote Sensing, 2018, 10(2): 243.
李唐薇, 童官军, 李宝清, 卢晓洋. 大视场域的目标检测与识别算法综述[J]. 激光与光电子学进展, 2020, 57(12): 120002. Tangwei Li, Guanjun Tong, Baoqing Li, Xiaoyang Lu. Review on Object Detection and Recognition in Large Field of View[J]. Laser & Optoelectronics Progress, 2020, 57(12): 120002.