Histograms of Oriented Gradients for Human Detection
这篇论文发表于2005年CVPR,引用次数1W+
作者:Navneet Dalal and Bill Triggs
论文提出了HOG描述算子,结合SVM分类算法,在行人检测中有优越的性能。对各种参数做了测试,concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results。
方法描述:
HOG就是图像不同方向的梯度的直方图统计特征。利用HOG+SVM检测行人的流程如下: