Abstract
In this paper, we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view 2D image sequence. In contrast to prior motion-based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology via a successive iterative merging strategy. The iterative merge process is guided by a density weighted skeleton map which is generated from a novel object boundary generation method from sparse 2D feature points. Our main contributions can be summarised as follows: (i) An unsupervised complex articulated kinematic structure estimation method that combines motion segments with skeleton information. (ii) An iterative fine-to-coarse merging strategy for adaptive motion segmentation and structural topology embedding. (iii) A skeleton estimation method based on a novel silhouette boundary generation from sparse feature points using an adaptive model selection method. (iv) A new highly articulated object dataset with ground truth annotation. We have verified the effectiveness of our proposed method in terms of computational time and estimation accuracy through rigorous experiments. Our experiments show that the proposed method outperforms state-of-the-art methods both quantitatively and qualitatively.
Original language | English |
---|---|
Pages (from-to) | 2165-2179 |
Number of pages | 15 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 40 |
Issue number | 9 |
Early online date | 3 Sept 2017 |
DOIs | |
Publication status | Published - 1 Sept 2018 |
Keywords
- Highly articulated kinematic structure estimation
- adaptive motion segmentation
- density weighted silhouette generation from sparse points
- adaptive kernel selection