 |
    |
Human Detection Using Learned Part Alphabet and Pose Dictionary
Cong Yao1, Xiang Bai1, Wenyu Liu1, and Longin Jan Latecki2
1Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China
yaocong2010@gmail.com
xbai@hust.edu.cn
liuwy@hust.edu.cn
2Department of Computer and Information Sciences, Temple University, USA
latecki@temple.edu
Abstract. As structured data, human body and text are similar in many aspects. In this paper, we make use of the analogy between human body and text to build a compositional model for human detection in natural scenes. Basic concepts and mature techniques in text recognition are introduced into this model. A discriminative alphabet, each grapheme of which is a mid-level element representing a body part, is automatically learned from bounding box labels. Based on this alphabet, the flexible structure of human body is expressed by means of symbolic sequences, which correspond to various human poses and allow for robust, efficient matching. A pose dictionary is constructed from training examples, which is used to verify hypotheses at runtime. Experiments on standard benchmarks demonstrate that the proposed algorithm achieves state-of-the-art or competitive performance.
Keywords: Human detection, mid-level elements, part alphabet, pose dictionary, matching
LNCS 8693, p. 251 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014