Abstract | ||
---|---|---|
The recovery of 3D human pose with monocular camera is an inherently ill-posed problem due to the large number of possible projections from the same 2D image to 3D space. Aimed at improving the accuracy of 3D motion reconstruction, we introduce the additional built-in knowledge, namely height-map, into the algorithmic scheme of reconstructing the 3D pose/motion under a single-view calibrated camera. Our novel proposed framework consists of two major contributions. Firstly, the RGB image and its calculated height-map are combined to detect the landmarks of 2D joints with a dual-stream deep convolution network. Secondly, we formulate a new objective function to estimate 3D motion from the detected 2D joints in the monocular image sequence, which reinforces the temporal coherence constraints on both the camera and 3D poses. Experiments with HumanEva, Human3.6M, and MCAD dataset validate that our method outperforms the state-of-the-art algorithms on both 2D joints localization and 3D motion recovery. Moreover, the evaluation results on HumanEva indicates that the performance of our proposed single-view approach is comparable to that of the multiview deep learning counterpart. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46493-0_2 | COMPUTER VISION - ECCV 2016, PT IV |
Keywords | Field | DocType |
Human pose estimation, Height-map | Computer vision,Computer science,Convolution,Human motion,Monocular camera,Coherence (physics),Artificial intelligence,Monocular image,Deep learning,Motion recovery,Motion reconstruction | Conference |
Volume | ISSN | Citations |
9908 | 0302-9743 | 23 |
PageRank | References | Authors |
0.75 | 28 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Du | 1 | 65 | 10.11 |
Yongkang Wong | 2 | 377 | 29.30 |
Yonghao Liu | 3 | 23 | 0.75 |
Feilin Han | 4 | 25 | 3.61 |
Yilin Gui | 5 | 23 | 0.75 |
Zhen Wang | 6 | 24 | 1.43 |
Mohan Kankanhalli | 7 | 3825 | 299.56 |
Weidong Geng | 8 | 162 | 21.81 |