Advanced Search
Advances in Soft Computing
Wachs, J., Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Be'er-Sheva 84105, Israel
Stern, H., Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Be'er-Sheva 84105, Israel
Burks, T., Agricultural and Biological Engineering, University of Florida, Gainesville, FL 110570, United States
Alchanatis, V., Institute of Agricultural Engineering Volcani Center, Bet-Dagan 50250, Israel
In this paper we compare similarity measures used for multi-modal registration, and suggest an approach that combines those measures in a way that the registration parameters are weighted according to the strength of each measure. The measures used are: (1) cross correlation normalized, (2) correlation coefficient, (3) correlation coefficient normalized, (4) the Bhattacharyya coefficient, and (5) the mutual information index. The approach is tested on fruit tree registration using multiple sensors (RGB and infra-red). The combination method finds the optimal transformation parameters for each new pair of images to be registered. The method uses a convex linear combination of weighted similarity measures in its objective function. In the future, we plan to use this methodology for an on-tree fruit recognition system in the scope of robotic fruit picking. © 2009 Springer-Verlag Berlin Heidelberg.
Powered by ClearMash Solutions Ltd -
Volcani treasures
About
Terms of use
Multi-modal registration using a combined similarity measure
52
Wachs, J., Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Be'er-Sheva 84105, Israel
Stern, H., Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Be'er-Sheva 84105, Israel
Burks, T., Agricultural and Biological Engineering, University of Florida, Gainesville, FL 110570, United States
Alchanatis, V., Institute of Agricultural Engineering Volcani Center, Bet-Dagan 50250, Israel
Multi-modal registration using a combined similarity measure
In this paper we compare similarity measures used for multi-modal registration, and suggest an approach that combines those measures in a way that the registration parameters are weighted according to the strength of each measure. The measures used are: (1) cross correlation normalized, (2) correlation coefficient, (3) correlation coefficient normalized, (4) the Bhattacharyya coefficient, and (5) the mutual information index. The approach is tested on fruit tree registration using multiple sensors (RGB and infra-red). The combination method finds the optimal transformation parameters for each new pair of images to be registered. The method uses a convex linear combination of weighted similarity measures in its objective function. In the future, we plan to use this methodology for an on-tree fruit recognition system in the scope of robotic fruit picking. © 2009 Springer-Verlag Berlin Heidelberg.
Scientific Publication
You may also be interested in