Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (11): 3231-3237.DOI: 10.11772/j.issn.1001-9081.2017.11.3231

Previous Articles     Next Articles

Foreground extraction with genetic mechanism and difference of Guassian

CHEN Kaixing, LIU Yun, WANG Jinhai, YUAN Yubo   

  1. College of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
  • Received:2017-05-11 Revised:2017-05-26 Online:2017-11-10 Published:2017-11-11
  • Supported by:
    This work is partially supported by the National High Technology Research and Development Program (863 Program) of China (2014AA020107).

基于遗传机制和高斯变差的自动前景提取方法

陈凯星, 刘赟, 王金海, 袁玉波   

  1. 华东理工大学 信息科学与工程学院, 上海 200237
  • 通讯作者: 袁玉波
  • 作者简介:陈凯星(1992-),男,福建福安人,硕士研究生,主要研究方向:计算机视觉、智能监控、数据挖掘;刘赟(1989-),男,山西太原人,硕士研究生,主要研究方向:计算机视觉、智能监控、数据挖掘;王金海(1995-),男,河南信阳人,硕士研究生,主要研究方向:计算机视觉、智能监控、数据挖掘;袁玉波(1976-),男,云南宣威人,教授,博士生导师,博士,主要研究方向:智能监控、机器人视觉、大数据分析与优化建模、机器学习。
  • 基金资助:
    国家863计划项目(2014AA020107)。

Abstract: Aiming at the difficult problem of unsupervised or automatic foreground extraction, an automatic foreground extraction method based on genetic mechanism and difference of Gaussian, named GFO, was proposed. Firstly, Gaussian variation was used to extract the relative important regions in the image, which were defined as candidate seed foregrounds. Secondly, based on the edge information of the original image and the candidate seed foregrounds, the contour of foreground object contour was generated according to connectivity and convex sphere principle, called star convex contour. Thirdly, the adaptive function was constructed, the seed foreground was selected, and the genetic mechanism of selection, crossover and mutation was used to obtain the accurate and valid final foreground. The experimental results on the Achanta database and multiple videos show that the performance of the GFO method is superior to the existing automatic foreground extraction based on difference of Gaussian (FMDOG) method, and have achieved a good extraction effect in recognition accuracy, recall rate and Fβ index.

Key words: image processing, video surveillance, foreground extraction, difference of Gaussian, genetic algorithm

摘要: 针对无监督或全自动前景提取这一技术难点问题,提出了一种基于遗传机制和高斯变差的自动前景提取(GFO)方法。首先,利用高斯变差提取图像中的相对重要区域,定义为候选种子前景;之后,利用原始图像和候选种子前景的边沿信息,根据连通性和凸球原则生成前景目标区域轮廓,称之为星凸轮廓;最后,构造适应性函数,选择种子前景,利用选择、交叉及变异的遗传机制,得到精确且有效的最终前景。在Achanta数据库和多个视频上的实验结果表明,GFO方法的性能优于已有的基于高斯变差的自动前景提取(FMDOG)方法,且在识别的准确率、召回率以及Fβ指标上都取得了较好的抽取效果。

关键词: 图像处理, 视频监控, 前景提取, 高斯变差, 遗传算法

CLC Number: