Abstract
This paper presents a simple, yet powerful local descriptor, so-called the histograms of space–time dominant orientations (HiSTDO). Specifically, our HiSTDO is composed of two main components, i.e., the dominant orientation and its coherence, which represents how intensively gradients in the local region are distributed along the space–time dominant orientation. By incorporating them into the histogram, we define it as our HiSTDO descriptor. In contrast to previous methods vulnerable to the presence of the background clutter and the camera noise, our HiSTDO greatly encodes the space–time shape of underlying structures even under such challenging conditions, and it can thus be efficiently applied to various applications (e.g., object and action detection). Experimental results on diverse datasets demonstrate that the proposed descriptor is effective for human action as well as object detection.
| Original language | English |
|---|---|
| Pages (from-to) | 49-59 |
| Number of pages | 11 |
| Journal | Machine Vision and Applications |
| Volume | 28 |
| Issue number | 1-2 |
| DOIs | |
| State | Published - 1 Feb 2017 |
Keywords
- Coherence
- Dominant orientation
- HiSTDO
- Object and action detection
- Space–time descriptor
Fingerprint
Dive into the research topics of 'Directional coherence-based spatiotemporal descriptor for object detection in static and dynamic scenes'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver