HOG即histogram of oriented gradient, 是用于目标检测的特征描述子，该技术将图像局部出现的方向梯度次数进行计数，该方法和边缘方向直方图、scale-invariant feature transform类似，不同的是hog的计算基于一致空间的密度矩阵来提高准确率。Navneet Dalal and Bill Triggs首先在05年的CVPR中提出HOG，用于静态图像or视频的行人检测。-HOG i.e. histogram of oriented gradien

The code below is implementation of HOG (Histogram-of-Oriented Gradients) descr iptor and object detection, introduced by Navneet Dalal and Bill Triggs. The computed feature vectors are compatible with the INRIA Object Detection and Localization