Abstract
A new real-time tracking algorithm is proposed for tracking airborne target in the terminal of infrared imaging tracking. In this algorithm, a small set of feature points are extracted from an IR (infrared) image using the Harris arithmetic operators of image processing. Therefore we can select the reference template according to these points, and then we can obtain the edge points by using the edge detection arithmetic operators. By measuring the improved Hausdorff distance between the feature points template and IR image, we can track the target in real-time. In this paper, the principle of selecting template and improving real-time performance of the tracking algorithm is explained in detail. The experimental and simulation results show that our tracking algorithm can well overcome the two shortcomings of the existing algorithm: (1) the sliding of tracking point, (2) the locked frame excursion. Consequently, our algorithm can satisfy the requirement of real-time tracking and tracking stability.
| Original language | English |
|---|---|
| Pages (from-to) | 331-335 |
| Number of pages | 5 |
| Journal | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University |
| Volume | 26 |
| Issue number | 3 |
| State | Published - Jun 2008 |
Keywords
- Hausdorff distance
- Image processing
- Infrared imaging
- Target tracking
- Template matching