Abstract
Aim. The introduction of the full paper reviews a number of papers in the open literature and then proposes the research mentioned in the title. Starting from Ref. 11, sections 1,2 and 3 explain our exploration. Section 1 briefs the APT of Ref. 11. Section 2 not only applies APT to scene matching but also deems it necessary to add three technical measures to make scene matching more effective than previously possible: (1) a new similarity measure is designed using a threshold; (2) a fast circular sub-image location method is used by creating an index template; (3) a pixel-jump searching method combined with a multi-resolution imaging technique is used to reduce the computational load. Section 3 analyzes the complexity of our scene matching algorithm and we believe we have made some progress in making it possess real-time capability. Simulation results, presented in Table 1, and their analysis show preliminarily that our scene matching algorithm is better than the conditional LPT based scene matching algorithm for real time and robustness.
Original language | English |
---|---|
Pages (from-to) | 702-708 |
Number of pages | 7 |
Journal | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University |
Volume | 29 |
Issue number | 5 |
State | Published - Oct 2011 |
Keywords
- Adaptive polar transform (APT)
- Algorithms
- Computer vision
- Image processing
- Index template
- Log-polar transform (LPT)
- Pixel-jump searching