Abstract
Usually, 3D spatio-temporal filter bank is designed in 3D frequency domain to detect moving target, but the, design method of the filter is difficult because of too more parameters and design difficulty. A novel moving target detection algorithm in 2D frequency domain is proposed. By decomposing the dynamic images into row and column sequences, the 3D frequency domain is translated into two groups of 2D frequency domain, and the filters design becomes easier. Then an adaptive filter is designed to extract the motion energy and pick out the frequency components of static background and noises, and the moving targets can be detected effectively. Simulation results show the robustness against image noises and matching errors.
| Original language | English |
|---|---|
| Pages (from-to) | 135-138 |
| Number of pages | 4 |
| Journal | Infrared and Laser Engineering |
| Volume | 36 |
| Issue number | 1 |
| State | Published - Feb 2007 |
Keywords
- Dynamic image analysis
- Imaging guidance
- Imaging tracking
- Moving target detection
Fingerprint
Dive into the research topics of 'Moving target detection algorithm in 2D frequency domain'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver