计算机应用 ›› 2012, Vol. 32 ›› Issue (11): 3214-3217.DOI: 10.3724/SP.J.1087.2012.03214

• 图形图像处理 • 上一篇    下一篇

基于Blob分析和贝叶斯决策的水下目标提取方法

施小成,郝丽超,张伟,吴迪   

  1. 哈尔滨工程大学 自动化学院,哈尔滨 150001
  • 收稿日期:2012-05-16 修回日期:2012-06-27 发布日期:2012-11-12 出版日期:2012-11-01
  • 通讯作者: 郝丽超
  • 作者简介:施小成(1957-),男,黑龙江哈尔滨人,教授,博士生导师,主要研究方向:无人水下航行器;郝丽超(1986-),女,河北高碑店人,硕士研究生,主要研究方向:机器视觉、无人水下航行器智能控制;张伟(1978-),男,黑龙江哈尔滨人,副教授,主要研究方向:无人水下航行器;吴迪(1988-),男,吉林舒兰人,博士研究生,主要研究方向:无人水下航行器智能控制。
  • 基金资助:
    中央高校基金资助项目(HEUCF110433)

Underwater targets extraction method based on Blob analysis and Bayesian design-making

SHI Xiao-cheng,HAO Li-chao,ZHANG Wei,WU Di   

  1. College of Automation, Harbin Engineering University, Harbin Heilongjiang 150001, China
  • Received:2012-05-16 Revised:2012-06-27 Online:2012-11-12 Published:2012-11-01
  • Contact: HAO Li-chao

摘要: 由于水下环境复杂多变,造成目标与伪目标的高混合度,某种单一的分割方法通常不能提取出理想的目标区域,因此提出一种基于Blob分析和贝叶斯决策的水下目标提取方法。首先,利用改进的二维OTSU算法计算出最佳阈值,并根据该阈值对图像进行阈值分割,经过连通性分析得到闭合的初始分割区域;然后,采用7种Blob算子对闭合区域进行7维向量描述,并基于贝叶斯决策准则剔除伪目标区域;最后,利用数学形态学算子去除目标区域边界的毛刺和干扰,得到理想的目标区域。通过对水池实验抓取的水下图像进行处理,结果表明该方法能够准确、有效地提取出真目标区域。

关键词: 水下目标提取, OTSU算法, Blob分析, 贝叶斯决策, 数学形态学

Abstract: As it is known that the underwater environment is quite complicated and changeable, as a result, targets and pseudo targets always have a high degree of mixing, and one single segmentation method usually could not abstract ideal target regions. Therefore, this paper proposed a new segmentation method based on Blob analysis and Bayesian design-making. Firstly, the optimistic thresholds were calculated by the improved OTSU algorithm, and then the image was segmented according to this threshold. Through analyzing the connectivity characters, closed contours of regions were achieved. Secondly, the connected regions were described using 7 dimensions of Blob operators and pseudo-target regions were eliminated based on Bayesian decision-making rules. Finally, burrs and disturbances were wiped off through the usage of mathematical morphology operators and ideal target regions were achieved. Through dealing with the images grabbed during the pool experiments using the above method, accuracy and efficiency of the method were verified and the real target regions were acquired.

Key words: underwater targets extraction, OTSU algorithm, Blob analysis, Bayesian design-making, mathematical morphology

中图分类号: