200 likes | 906 Views
Histograms of Oriented Gradients for Human Detection. Navneet Dalal and Bill Triggs French National Institute for Research in Computer Science and Control (INRIA ) CVPR 05. OpenCV implement. peopledetect.cpp. Introduction. Challenge: variable appearance and the wide range of poses
E N D
Histograms of Oriented Gradients for Human Detection NavneetDalal and Bill Triggs French National Institute for Research in Computer Science and Control (INRIA) CVPR 05
OpenCV implement • peopledetect.cpp
Introduction • Challenge: variable appearance and the wide range of poses • Histogram of Oriented Gradients (HOG) are feature descriptors used in computer vision and image processing for the purpose of object detection. • Basic idea : local object appearance and shape can be characterized rather well by the distribution of local intensity gradients or edge directions. • Similar with edge orientation histograms [4,5], SIFT descriptors [12] and shape contexts [1]
Dataset(1/2) 64x128
Dataset(2/2) • INRIA negative images (64x128 samples)
An overview of our feature extraction and object detection chain Person / non-person classification http://quyanyun.com/Files/Viso/%E7%AC%AC%E5%9B%9B%E8%AE%B2Dalal-phd-slides.pdf
Implementation(1/7) • Color / gamma normalization • Grayscale, RGB and LAB color spaces optionally with power law (gamma) equalization • Not obvious effect • Gradient Computation • 1-D point derivatives : uncentred [-1, 1], centred[-1, 0, 1] and cubic-corrected [1,-8, 0, 8,-1] • 3*3 Sobelmasks • 2*2 diagonal ones • Gaussian smoothing with σ • 1-D at σ =0 work best • The simplest scheme turns out to be the best DET(Detection Error Tradeoff)
Implementation(2/7) • Creating the orientation histograms • Weighted vote for an edge orientation histogram over cells. • Unsigned gradients used in conjunction with 9 histogram channels performed best in their human detection experiments • Weight: gradient magnitude itself, or some function of the magnitude (square, square root, clipped) • Gradient magnitude itself generally produces the best results. cell
Implementation(3/7) • Normalization and descriptor blocks • Owing to local variations of illumination and foreground-background contrast • Group cells into larger, spatially connected blocks and normalize each block separately • Two main block geometries : rectangular R-HOG blocks and circular C-HOG blocks. • R-HOG : 3 parameter • # of cells per block • # of pixels per cell • # of channels per cell histogram • Optimal : 3x3 cell blocks of 6x6 pixel cells with 9 channels. • Gaussian spatial weight
Implementation(4/7) • Normalization and descriptor blocks • C-HOG : 4 parameter • # of angular bins • # of radial bins • The radius of the center bin • The expansion factor for the radius of additional radial bins • Optimal: 4,2,4,2, Gaussian spatial weight is not need • Block Normalization schemes • L2-norm : • L2-Hys : L2-norm ,clip (limit v<=0.2) and renormalize • L1-norm : • L1-sqrt :
Implementation(6/7) • R/C-HOG give near perfect separation on MIT database • Have 1-2 order lower false positives than other descriptors
Implementation(7/7) • Feed the descriptors into some recognition system :SVM classifier
Summary Histograms of edge orientations 8*8 cell size edge [-1, 0, 1] gradient filter with no smoothing 8*16 cells 9 unsighted bins=> 9 dimension vector Gaussian spatial window with = 8 R-HOG, 2*2 block size => 36 dimension vector L2-Hys 7*15blocks => descriptor: 3780 dimension vector overlap=1/2
Conclusion • We show experimentally that dense grids of Histograms of Oriented Gradient (HOG) descriptors significantly outperform existing feature sets for human detection. • We study the influence of each stage of the computation on performance.