计算机与现代化

• 数据库与数据挖掘 • 上一篇    下一篇

基于图像轮廓分析的室内窗户检测

  

  1. (杭州电子科技大学计算机学院,浙江杭州310018)
  • 出版日期:2018-04-28 发布日期:2018-05-02
  • 作者简介:孔倩倩(1993),女,山东济宁人,杭州电子科技大学计算机学院硕士研究生,研究方向:图像处理; 赵辽英(1970),女,教授,博士,研究方向:图像处理与模式识别; 张莉(1979),女,讲师,博士,研究方向:视频信号处理。
  • 基金资助:
    浙江省自然科学基金青年基金资助项目(LQ16f010008)

Indoor Window Detection Based on Image Contour Analysis

  1. (School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China)
  • Online:2018-04-28 Published:2018-05-02

摘要: 针对室内窗户检测的问题,提出一种基于图像轮廓分析的室内窗户检测方法。对预处理后的图像进行阈值分割和形态学处理;然后采用基于拓扑结构分析的边界跟踪算法,提取边界轮廓的一系列坐标点,根据窗户轮廓特点筛选出符合条件的轮廓,求各轮廓的最小外接矩形,计算两两最小外接矩形间的距离;最后利用最小生成树对各个矩形分类合并,确定窗户区域。实验结果表明,所提出的方法能有效地实现不同室内场景中窗户的检测。

关键词: 窗户检测, 阈值分割, 二值图像, 轮廓提取, 最小生成树

Abstract: Aiming to the problem of indoor window detection, this paper proposed an approach of indoor window detection based on image contour analysis. The image is preprocessed and a binary image is obtained by threshold segmentation and morphological processing. Then, the contours of the image are extracted by the border tracking based on the topology structure analysis, and stored as the sequence points. The contours of the qualifying conditions are selected according to the characteristics of the window contours. The minimum enclosing rectangles of each contour are figured up and the shortest distance between each two rectangles are calculated. Finally, the rectangles are classified and merged by the minimum spanning tree to obtain the position of the window. Experiment results show that the proposed method can effectively detect the windows in different indoor scenes.

Key words: window detection, threshold segmentation, binary image, contours extraction, minimum spanning tree

中图分类号: