Human action recognition in still images using action poselets and a two-layer classification model. (June 2015)

• Record Type: Journal Article
• Authors: Ko, ByoungChul; Hong, JuneHyeok; Nam, Jae-Yeal
• Is Part Of: Journal of visual languages & computing. Volume 28(2015)
• Page Start: 163
• Page End: 175
• Publication Date: 2015-06
• Subjects: Action recognition -- Two-layer classification model -- Spatial poselet activation vector -- OCS-LBP -- Random forest; Visual programming languages (Computer science) -- Periodicals; Visual programming (Computer science) -- Periodicals; Programming languages (Electronic computers) -- Semantics -- Periodicals; Langages de programmation visuelle -- Périodiques; Programmation visuelle -- Périodiques; Langages de programmation -- Sémantique -- Périodiques; Programming languages (Electronic computers) -- Semantics; Visual programming (Computer science); Visual programming languages (Computer science); Periodicals; Electronic journals; 005
• DOI: 10.1016/j.jvlc.2015.01.003
• Languages: English
• ISSNs: 1045-926X

Abstract

Abstract: Human action recognition in still images provides useful information for use in a wide range of computer vision applications. Because motion information cannot be estimated from a single image, action recognition in still images remains a challenging problem. In this paper, we propose poselet based action recognition methods to infer human action using a two-layer classification model. First, poselets are built using the annotated data of joint locations of people and the proposed Hausdorff distance. Each poselet, consisting of a feature vector, is trained using the first-layer classifier based on random forest classification to find the proper location. From trained poselet detectors, we construct spatial poselet activation vectors (SPAVs) using the voting scores of poselets. A second-layer classifier, which takes aggregating SPAVs of the first-layer classifiers as input, trains a final multi-class classifier. During the testing phase, the input window, which includes a human region, is applied to the first-layer classifier; the aggregating output of the first-layer is applied to the second-layer classifier. After calculating scores for all the c -action classes, the final action class is selected as the one that has the maximum score. Experimental results showed that the recognition performance and processing times of the proposed method was better than those of previous methods. Highlights: We propose poselet selection based on the modified Hausdorff distance. Poselet training and detection are performed using a random forest classifier. We introduce spatial poselet activation vectors considering poselet location. We propose a two-layer classification model for action recognition.