[2] [2] XU T, LIU H, QIAN Y L, et al. A novel method for people and vehicle classification based on Hough line feature [C ] //Proceedings of International Conference on Information Science and Technology (ICIST ), 2011 ：240-245.

[3] [3] RIVLIN E, RUDZSKY M, GOLDENBERG R, et al. A re-

[4] [4] BOGOMOLOV Y, DROR G, LAPCHEV S, et al. Classification of moving targets based on motion and appearance [C]//Proceedings of British Machine Vision Conference (BMVC), 2003, 2：429-438.

[5] [5] TOYH D, ACH T. Detection and recognition of moving objects using statistical motion detection and Fourier scriptors [ C J//Proceedings of 12th International Conference on Image Analysis and Processing, 2003 ：430-435.

[8] [8] HINTON G, SALAKHUTDINOV R R. Reducing the dimen-sionality o￡ data with neural networks [J]. Science, 2006, 313(5786) ：504-507.

[9] [9] HINTON G E, OSINDERO S, THE Y W. A fast learning algorithm for deep belief nets [ J ]. Neural Computation, 2006, 18(7) ： 1527-1554.

[10] [10] BENGIO Y, COURVILLE A, VINCENT P. Representation learning: a review and new perspective [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8) ： 1798-1828.

[11] [11] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks [C ] //Proceedings of Neural Information and Processing Systems, 2012：1097-1105.

[12] [12] FARABET C, COUPRIEC, NAJMAN L, et al. Learning hi-erarchical features for scene labeling[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8) ： 1915-1929.

[13] [13] BORDES A, GLOROT X, WESTON J, et al. Joint learning of words and meaning representations for open-text semantic parsing[ C] //Proceedings of 15th International

[14] [14] SOCHER R, HUANG E H, PENNINGTON J, et al. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection [ C ] //Proceedings of Neural Information and Processing Systems, 2011 ： 801-809.

[15] [15] 10 Breakthrough Technologies 2013 [ Z]. MIT Technology Review, 2013.

[16] [16] INRIA. INRIA Person Dataset [ EB/OL]. (2005-01-01) [2014-01-01]. http：//pascal, inrialpes. ￡r/data/human/.

[17] [17] MIT. MIT Pedestrian Data[EB/OL]. (2000-01-01) [2014- 01-01 ]. http: //cbcl. mit. edu/software-datasets/Pedestri- anData. html.

[18] [18] Caltech. Caltech Pedestrian Detection Benchmark [ EB/ OL]. (2009-01-01) [2014-01-01 ]. http: //www. vision, caltech. edu/Image_Datasets/ CaltechPedestrians/.

[19] [19] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs fisherfaces: recognition using class specific linear projection] J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7) ：711-720.

[20] [20] JIANG Z LIN Z, DAVIS S. Label consistent K-SVD：learning a discriminative dictionary for recognition [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11) ：2651-2664.