Combinatorial optimization: algorithms and complexity
Combinatorial optimization: algorithms and complexity
Genetic algorithms + data structures = evolution programs (3rd ed.)
Genetic algorithms + data structures = evolution programs (3rd ed.)
Constraint, optimization, and hierarchy: reviewing stereoscopic correspondence of complex features
Computer Vision and Image Understanding
A dense disparity map of stereo images
Pattern Recognition Letters
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Artificial Life
Evolving descriptors for texture segmentation
Pattern Recognition
A new object motion estimation technique for video images, based on a genetic algorithm
IEEE Transactions on Consumer Electronics
| Hi-index | 0.00 |
This work presents a new way of enforcing figural continuity in feature-based stereo matching, without the ordering constraint. We model the problem of finding the best decision for each epipolar as a weighted bipartite graph by using a match functional based on fuzzy logic. A matcher based on a set of Genetic Algorithms (GAs), which searches for optimum intra-row match decisions is configured. These independent GAs are then modified to a set of cooperative Symbiotic GAs (SGAs) whose search is twofold. They seek matchings that maximise the local intra-row similarities and simultaneously try to maintain consistency at the global inter-row level. The performance of the system is exemplified and compared with dynamic programming and bipartite matching.