Abstract | ||
---|---|---|
image registration is a fundamental task in both image processing and computer vision. Here, we present a novel method for local image registration based on adaptive filtering techniques. We utilize an adaptive filter to estimate and track correspondences among multiple images containing overlapping views of common scene regions. Image pixels are traversed in an order established by space-filling curves, to preserve the contiguity and hence track locally varying registration changes. The algorithm differs from pre-existing work on image registration in that it requires only local information and relatively low computational effort. These characteristics render the method suitable for deployment in imaging sensor networks, toward which the current work is directed. We evaluate the performance of the proposed algorithm using images captured with a digital camera in various real-world scenarios. Experimental results show that the proposed method can significantly improve accuracy and robustness over a global 2-D parametric registration and can also outperform the local registration algorithm based on the Lucas-Kanade [1] optical flow technique. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICASSP.2005.1415547 | 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING |
Keywords | Field | DocType |
image sensor,image sensors,layout,optical imaging,computer vision,lucas kanade,adaptive filters,optical flow,image processing,image registration,parameter estimation,pixel,adaptive filter | Computer vision,Image sensor,Pattern recognition,Computer science,Image processing,Robustness (computer science),Digital camera,Adaptive filter,Pixel,Artificial intelligence,Optical flow,Image registration | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.36 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gulcin Caner | 1 | 21 | 1.66 |
A. Murat Tekalp | 2 | 2603 | 278.04 |
Gaurav Sharma | 3 | 640 | 56.64 |
Wendi Heinzelman | 4 | 3772 | 236.43 |