摘要
为了快速准确地分割视频运动对象,提出一种新的自适应遗传视频运动对象分割算法。该算法通过完善进化机制,引进自适应初代个体、自适应选择算子、自适应调整交叉率和变异率以及终止判决等,有效解决了遗传算法收敛速度慢和群体过早成熟的问题。实验结果表明,新算法不但缩短了分割时间,而且取得了良好的分割效果。
In order to rapidly and accurately segment video motion object,an improved adaptive genetic segmentation algorithm based on video motion object is proposed.Through consummating the evolve mechanism,introducing adaptive initially individual,selection operator,adaptive cross over rate and mutation rate,judgments of termination,the problems of poor astringency and premature occurrence in genetic algorithm are resolved.The experiment results show that the new segmentation method can greatly improve the speed of segmentation and acquire good segmentation results.
出处
《电视技术》
北大核心
2010年第8期26-28,32,共4页
Video Engineering
基金
陕西省教育厅专项基金项目(07JK295)
关键词
视频对象
遗传算法
自适应
分割
video object
genetic algorithm
adaptive
segmentation
