Local Surface Geometric Feature for 3D human action recognition

详细信息    查看全文

• 作者：Erhu Zhang^a ; ^{eh-zhang@xaut.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Wanjun Chen^a ; ^{wjchen@xaut.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Zhuomin Zhang^bAuthor Vitae ; Yan Zhang^a ; ^cAuthor Vitae
• 关键词：Human action recognition ; Depth map ; Skeleton joint ; Local Surface Geometric Feature (LSGF) ; Covariance descriptor
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：5 October 2016
• 年：2016
• 卷：208
• 期：Complete
• 页码：281-289
• 全文大小：1892 K

文摘

This paper presents a novel Local Surface Geometric Feature (LSGF) for human action recognition from video sequences captured by a depth camera. The LSGF is extracted from each skeleton joint in point cloud space to capture the static appearance and pose cues, which includes joint position, normal, and local curvature. A temporal pyramid of covariance matrix is exploited to model both pairwise relations of features instead of features themselves and the temporal evolution. Finally, Fisher vector encoding is imported as a global representation for a video sequence and SVM classifier is used for classification. In the extensive experiments, we achieve classification results superior to most of previous published results on three public benchmark datasets, i.e., MSR-Action3D, MSR DailyActivity3D, and UTKinect Action.