| Paper: | WA-P6.1 |
| Session: | Geosciences and Remote Sensing II |
| Time: | Wednesday, September 19, 09:50 - 12:30 |
| Presentation: |
Poster
|
| Title: |
SAR AND SPOT IMAGE REGISTRATION BASED ON MUTUAL INFORMATION WITH CONTRAST MEASURE |
| Authors: |
Lixia Shu; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences | | |
| | Tieniu Tan; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences | | |
| Abstract: |
In this study, we propose a novel robust mutual information (MI) based method to register SAR and SPOT images. Traditional MI based method can register SAR and SPOT images well. However, its robustness is not satisfying for local spatial information is absent. In our approach, first, local contrast of 5*5 windows centered at each point in both images is calculated, then the contrast value is assigned to each pixel and two contrast images are obtained. Finally, the SAR and SPOT images are registered by maximizing the MI between their contrast images. Experimental results show that compared with traditional MI, our approach is much more robust and acquires comparable or even higher accuracy. Meanwhile, compared with the MI with orientation information based registration (MIOI), another robust MI based method, our algorithm works much faster and more accurately. |
