A Modified Mahalanobis Distance for Human Detection in Out-door Environments

摘要：

This paper proposes a novel method for human detection from static images based on pixel structure of input images. Each image is divided into four parts, and a weight is assigned to each part of the image. In training stage, all sample images including human images and non-human images are used to construct a Mahalanobis distance map through statistically analyzing the difference between the different blocks on each original image. A projection matrix will be created with Linear Discriminant Method (LDM) based on the Mahalanobis distance map. This projection matrix will be used to transform multidimensional feature vectors into one dimensional feature domain according to a pre-calculated threshold to distinguish human figures from nonhuman figures. In comparison with the method without introducing weights, the proposed method performs much better. Encouraging experimental results have been obtained based on MIT dataset and our own dataset.

作者: Yan Chen Qiang Wu Xiangjian He Wenjing Jia Tom Hintz

作者单位: Faculty of Information Technology,University of Technology,Sydney

会议类型: 国际会议

会议名称: The First IEEE International Conference on Ubi-Media Coputing and Workshops(第一届泛媒体处理国际会议)

会议地点: 兰州

会议语种:英文

在线出版日期: 2008-07-15（万方平台首次上网日期，不代表论文的发表时间）