Abstract
This paper presents a fast semi-automatic semantic object tracking algorithm for digital video. The proposed method consists of two steps, namely, intraframe object extraction and the inter-frame object tracking. For the intra-frame segmentation, we try to minimize the human intervention by exploiting the automatic homogenous region segmentation. Then, to achieve a fast inter-frame object tracking, we propose to use a 1-D projected motion estimation and an improved flooding method for the watershed algorithm.
| Original language | English |
|---|---|
| Pages (from-to) | 356-357 |
| Number of pages | 2 |
| Journal | Digest of Technical Papers - IEEE International Conference on Consumer Electronics |
| State | Published - 2000 |
| Event | ICCE 2000 - International Conference on Consumer Electronics - Los Angeles, CA, USA Duration: 13 Jun 2000 → 15 Jun 2000 |
Fingerprint
Dive into the research topics of 'Fast object tracking in digital video'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver