电子学报 ›› 2020, Vol. 48 ›› Issue (8): 1493-1501.DOI: 10.3969/j.issn.0372-2112.2020.08.006

• 学术论文 • 上一篇    下一篇

基于量子遗传算法的视觉目标跟踪

金泽芬芬1,2, 侯志强1, 余旺盛1, 王鑫1,3, 寇人可4   

  1. 1. 空军工程大学信息与导航学院, 陕西西安 710077;
    2. 中国人民解放军95959部队, 北京 100195;
    3. 中国人民解放军93665部队, 山西忻州 036200;
    4. 中国人民解放军95084部队, 广东佛山 528226
  • 收稿日期:2016-12-23 修回日期:2020-01-08 出版日期:2020-08-25
    • 通讯作者:
    • 金泽芬芬
    • 作者简介:
    • 侯志强 男,1973年出生于陕西眉县,2005年获西安交通大学工学博士学位,现西安邮电大学计算机学院教授,主要研究方向为图像处理、计算机视觉、无人机应用以及信息融合等. E-mail:hou-zhq@sohu.com
    • 基金资助:
    • 国家自然科学基金 (No.61703423)

An Object Tracking Approach Based on Quantum Genetic Algorithm

JIN Ze-fen-fen1,2, HOU Zhi-qiang1, YU Wang-sheng1, WANG Xin1,3, KOU Ren-ke4   

  1. 1. Institute of Information and Navigation, Air Force Engineering University, Xi'an, Shaanxi 710077, China;
    2. Unit 95959 of Chinese People's Liberation Army, Beijing 100195, China;
    3. Unit 93665 of Chinese People's Liberation Army, Xinzhou, Shanxi 036200, China;
    4. Unit 95084 of Chinese People's Liberation Army, Foshan, Guangdong 528226, China
  • Received:2016-12-23 Revised:2020-01-08 Online:2020-08-25 Published:2020-08-25
    • Corresponding author:
    • JIN Ze-fen-fen
    • Supported by:
    • National Natural Science Foundation of China (No.61703423)

摘要: 针对视觉目标跟踪中传统搜索方法效率不高、难以求取全局最优等问题,利用量子遗传算法的全局寻优能力,提出了一种采用量子遗传算法作为搜索策略的视觉跟踪方法.在量子遗传算法的框架下,将像素点位置作为种群中的个体,提取颜色直方图作为特征,以相似性度量作为目标函数计算个体适应度值,找出相似度最大的像素点位置输出,最终完成跟踪.实验结果表明,本文方法在目标速度快、遮挡和非刚性形变等情况下具有明显优势,且算法运算量小,跟踪速度快.

关键词: 视觉跟踪, 量子遗传算法, 颜色特征

Abstract: Aiming at the problem that traditional search method in visual tracking is not efficient and the global optimization is hard to be solved, as the global optimization ability of quantum genetic algorithm, we put forward a visual tracking method by using quantum genetic algorithm as the search strategy. In the framework of quantum genetic algorithm, regard the pixel positions as the individuals in the population, and extract the color histogram as characteristics. The individual fitness are calculated by taking similarity measure as the objective function. We find out the maximum similarity and output its homologous position, to finish the tracking. The experimental results show that the algorithm has obvious advantages in fast speed, occlusion and non-rigid deformation, and the tracking speed is fast.

Key words: visual tracking, quantum genetic algorithm, color feature

中图分类号: