Action Recognition from Pose Signature in Static Image
| Autor: | I-fan Shen, Wenbin Chen, Yinzhong Qian |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Structure (mathematical logic)
business.industry Constrained optimization Context (language use) Pattern recognition 02 engineering and technology 010501 environmental sciences 3D pose estimation 01 natural sciences Signature (logic) Articulated body pose estimation Image (mathematics) Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Computer Vision and Pattern Recognition Artificial intelligence business Global optimization Software 0105 earth and related environmental sciences Mathematics |
| Zdroj: | International Journal of Pattern Recognition and Artificial Intelligence. 30:1655010 |
| ISSN: | 1793-6381 0218-0014 |
| DOI: | 10.1142/s0218001416550107 |
| Popis: | This paper addresses the problem of action recognition from body pose. Detecting body pose in static image faces great challenges because of pose variability. Our method is based on action-specific hierarchical poselet. We use hierarchical body parts each of which is represented by a set of poselets to demonstrate the pose variability of the body part. Pose signature of a body part is represented by a vector of detection responses of all poselets for the part. In order to suppress detection error and ambiguity we explore to use part-based model (PBM) as detection context. We propose a constrained optimization algorithm for detecting all poselets of each part in context of PBM, which recover neglected pose clue by global optimization. We use a PBM with hierarchical part structure, where body parts have varying granularity from whole body steadily decreasing to limb parts. From the structure we get models with different depth to study saliency of different body parts in action recognition. Pose signature of an action image is composed of pose signature of all the body parts in the PBM, which provides rich discriminate information for our task. We evaluate our algorithm on two datasets. Compared with counterpart methods, pose signature has obvious performance improvement on static image dataset. While using the model trained from static image dataset to label detected action person on video dataset, pose signature achieves state-of-the-art performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|