Computer Science ›› 2017, Vol. 44 ›› Issue (Z11): 221-224.doi: 10.11896/j.issn.1002-137X.2017.11A.046

Previous Articles     Next Articles

Pedestrian Detection Based on DCT of Multi-channel Feature

LIU Chun-yang, WU Ze-min, HU Lei and LIU Xi   

  • Online:2018-12-01 Published:2018-12-01

Abstract: In pedestrian detection,multi-channel feature detection has the defect of incomplete using features.In this paper,an algorithm of multi-channel feature detection based on discrete cosine transform (DCT) was proposed.We used a two-layer convolution network for arranging the image information after DCT to build a new channel in the frequency domain.This channel can describe complex textures about pedestrian.Combined with the features of the histogram of gradient and the color space as well as the DCT frequency domain,a low cost multi-channel pedestrian detector has been trained based on the Adaboost algorithm.Experiments on popular pedestrian databases show that the proposed method improves the accuracy of detection,and the effect is remarkable in low false positive per image.

Key words: Pedestrian detection,DCT,Multi-channel feature

[1] IKEUCHI K.Computer Vision:A Reference Guide[M].Sprin-ger Publishing Company,Incorporated,2014.
[2] 苏松志,李绍滋,陈淑媛,等.行人检测技术综述[J].电子学报,2012,40(4):814-820.
[3] CAO J,PANG Y,LI X.Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry[J].IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society,2016,5(12):5538.
[4] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNetClassification with Deep Convolutional Neural Networks[J].Advances in Neural Information Processing Systems,2012,25(2):2012.
[5] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥CVPR’14.2014:580-587.
[6] REDMON J,DIiVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]∥CVPR’16.2016:779-788.
[7] DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2005:886-893.
[8] ZHANG S,BAUCKHAGE C,CREMERS A B.Informed Haar-Like Features Improve Pedestrian Detection[C]∥IEEE Confe-rence on Computer Vision and Pattern Recognition.2014:947-954.
[9] WANG X G.Deep learning in image recognition[J].Communications of the CCF,2015,11(8):15-23.
[10] DOLLR P,TU Z,PERONA P,et al.Integral Channel Features[C]∥British Machine Vision Conference,BMVC 2009.London,UK,2009.
[11] ZHANG S,BENESON R,OMRAN M,et al.How Far are We from Solving Pedestrian Detection?[C]∥ CVPR’16.2016:1259-1267.
[12] DOLLAR P,APPEL R,BELONGIE S,et al.Fast Feature Pyramids for Object Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,36(8):1532-1545.
[13] FARINELLA G M,RAV D,et al.Representing scenes for real-time context classification on mobile devices[J].Pattern Recognition,2015,48(4):1086-1100.
[14] WALLACE G K.The JPEG still picture compression standard[J].Communications of the ACM,1991,34(4):30-44.
[15] STURGESS P,ALAHARI K,LADICKY L,et al.CombiningAppearance and Structure from Motion Features for Road Scene Understanding[C]∥British Machine Vision Conference,BMVC 2009.London,UK,2009.
[16] BATTIATO S,MANCUSO M,BOSCO A,et al.Psychovisualand Statistical Optimization of Quantization Tables for DCT Compression Engines[C]∥International Conference on Image Analysis and Processing.IEEE Computer Society,2001:602-606.
[17] PETERSON H A,PENG H,MORGAN J H,et al.Quantization of color image components in the DCT domain[C]∥Proceedings of SPIE-The International Society for Optical Engineering.1991:210-222.
[18] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based lear-ning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2232.

No related articles found!
Full text



No Suggested Reading articles found!