作者: M. Irani , S. Peleg
关键词:
摘要: A method for detecting and tracking multiple moving objects, using both a large spatial region temporal region, without assuming motion constancy is described. When the of analysis has parameters locations objects are computed one object after another. segmenting image plane into differently computing their motions two frames presented. The detected integration algorithms enhancement tracked by filling-in occluded regions improving resolution imaged >