Co-evolutionary-based active contour models in tracking of movingobstacles

摘要

A new symbiotic genetic algorithm (SGA)-based active contour model(Snake) is proposed to track the B-spline contour of obstacles. Itexploits the local control properties of the B-spline to decompose thecontour into subcontours and optimizes each subcontour in separategenetic algorithms (GA). Unlike GA-based Snake, a SGASnake can track theobstacles outline more robustly. Application-specific inter-populationgenetic operators are introduced to reinforce the symbiotic relationshipvia migration of genetic material. The use of symbiosis dramaticallyreduces the combinatorics of the search space, when compared to GA.Results of tracking objects in real road scenarios demonstrate itsrobustness to noise and stability of convergence when compared to its GAcounterpart