计算机科学 ›› 2017, Vol. 44 ›› Issue (3): 182-186.doi: 10.11896/j.issn.1002-137X.2017.03.039
张永良,张智勤,吴鸿韬,董灵平,周冰
ZHANG Yong-liang, ZHANG Zhi-qin, WU Hong-tao, DONG Ling-ping and ZHOU Bing
摘要： 监控系统已经成为周界入侵防范的重要手段之一,但是目前局限于被动式监视。对此,提出一种通过对监控系统传回的视频图像进行人体目标识别进而实现主动周界入侵检测的方法。针对目前人体目标检测算法场景适用性较差的问题,提出一种基于改进卷积神经网络的行人检测算法,该方法在深层特征的基础上融入浅层特征,利用浅层特征校正深层特征在识别目标过小时的局限性,最后利用Softmax进行分类。实验结果证实,改进后的卷积神经网络对行人的姿态和适用场景都具有较高的鲁棒性,并且在INRIA库上的识别率为98.82%, 在NICTA库上的识别率为99.82%,在CVC库上的识别率为94.50%,在Daimler库上的识别率为99.92%。
| [1] XIN D S.Perimeter alarm detector selection principle and discuss technology trends[J].China Security,2008(3):67-70.(in Chinese) 辛东升.周界报警探测器选择原则与技术发展趋势探讨[J].中国安防,2008(3):67-70. [2] MIU X,QIAN L B,ZHANG Y,et al.Perimeter intrusion detection alarm system on the market [J].China Security & Protection,2013(10):96-100.(in Chinese) 缪璇,钱六宝,章骅,等.周界入侵探测报警系统市场浅析[J].中国安防,2013(10):96-100. [3] GE Y.Systematic review of outdoor perimeter protection [J].China Security & Protection,2004(5):49-54.(in Chinese) 葛妍.户外周界防护系统综述[J].中国安防产品信息,2004(5):49-54. [4] YAN Z Q,LIU Y J.Surrounding infrared burglar alarm system [J].Security Technology,2007,28(4):1-3.(in Chinese) 阎子勤,刘一江.周边红外防盗报警系统[J].安防科技,2007,28(4):1-3. [5] CHEN Y Z.Application of Intelligent Video Analysis Technology in Perimeter Surveillance and Monitoring System[J].Process Automation Instrumentation,2009,30(11):14-19.(in Chinese) 陈育智.智能视频分析技术在周界报警系统中的应用[J].自动化仪表,2009,30(11):14-19. [6] HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507. [7] IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]∥32nd International Conference on Machine Learning(ICML).2005 . [8] SZARVAS M,YOSHIZAWA A,YAMAMOTO M,et al.Pedestrian detection with convolutional neural networks[C]∥Intelligent Vehicles Symposium,2005.IEEE,2005:224-229. [9] TIAN Y,LUO P,WANG X,et al.Pedestrian detection aided by deep learning semantic tasks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:5079-5087. [10] AHED E,JONES M,MARKST K.An improved deep learning architecture for person re-identification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3908-3916. [11] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems.2012:1097-1105. [12] LO S C B,CHAN H P,LIN J S,et al.Artificial convolution neural network for medical image pattern recognition[J].Neural networks,1995,8(7):1201-1214. [13] MURPHY K,TORRALBA A,EATON D,et al.Object detection and localization using local and global features[M]∥Toward Category-Level Object Recognition.Springer Berlin Heidelberg,2006:382-400. [14] LIN C T,HSU S C,LEE J F,et al.Boosted Vehicle Detection Using Local and Global Features[J].Journal of Signal and Information Processing,2013(4):243-252. [15] RAHMATULLAH B,PAPAGEORGHIOU A T,NOBLE J A.Integration of local and global features for anatomical object detection in ultrasound[M]∥Medical Image Computing and Computer-Assisted Intervention-MICCAI 2012.Springer Berlin Heidelberg,2012:402-409. [16] DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005,1:886-893. [17] WU B,NEVATIA R.Detection of multiple,partially occludedhumans in a single image by bayesian combination of edgelet part detectors[C]∥Tenth IEEE International Conference on Computer Vision,2005(ICCV 2005).IEEE,2005,1:90-97. [18] DOLLAR P,WOJEK C,SCHIELE B,et al.Pedestrian detec-tion:An evaluation of the state of the art[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):743-761. [19] http://pascal.inrialpes.fr/data/human. [20] http://nicta.com.au/research/projects/AutoMap/computer_vi-sion_datasets. [21] http://www.gavrila.net/Research/Pedestrian_Detection/Daim-ler_Pedestrian_Benchmark_D/Dai-mler_Mono_Ped__Detection_Be/daimler_mono_ped__detection_be.html. [22] http://www.cvc.uab.es/adas/site. |
| No related articles found! |
|
||
首页