Pang Yanwei, Yan He, Yuan Yuan, Wang Kongqiao
School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China.
IEEE Trans Syst Man Cybern B Cybern. 2012 Apr;42(2):458-68. doi: 10.1109/TSMCB.2011.2167750. Epub 2011 Nov 18.
Many human-centered image and video management systems depend on robust human detection. To extract robust features for human detection, this paper investigates the following shortcomings of co-occurrence histograms of oriented gradients (CoHOGs) which significantly limit its advantages: 1) The magnitudes of the gradients are discarded, and only the orientations are used; 2) the gradients are not smoothed, and thus, aliasing effect exists; and 3) the dimensionality of the CoHOG feature vector is very large (e.g., 200,000). To deal with these problems, in this paper, we propose a framework that performs the following: 1) utilizes a novel gradient decomposition and combination strategy to make full use of the information of gradients; (2) adopts a two-stage gradient smoothing scheme to perform efficient gradient interpolation; and (3) employs incremental principal component analysis to reduce the large dimensionality of the CoHOG features. Experimental results on the two different human databases demonstrate the effectiveness of the proposed method.
许多以人类为中心的图像和视频管理系统依赖于强大的人体检测技术。为了提取用于人体检测的强大特征，本文研究了方向梯度共生直方图（CoHOGs）的以下缺点，这些缺点显著限制了其优势：1）梯度的幅度被丢弃，仅使用方向；2）梯度未进行平滑处理，因此存在混叠效应；3）CoHOG特征向量的维度非常大（例如200,000）。为了解决这些问题，本文提出了一个框架，该框架执行以下操作：1）利用一种新颖的梯度分解和组合策略来充分利用梯度信息；（2）采用两阶段梯度平滑方案来执行高效的梯度插值；（3）采用增量主成分分析来降低CoHOG特征的高维度。在两个不同的人体数据库上的实验结果证明了所提方法的有效性。
