基于改进Hough变换的建筑目标搜索与识别

汪哲慎; 李翠华

doi:10.11834/jig.20050493

学术论文与技术报告 | 浏览量 : 0 下载量: 182 CSCD: 0

PDF
导出
分享
收藏
专辑

基于改进Hough变换的建筑目标搜索与识别
Improved Classical Hough Transform Applied to Building Detection and Recognition
2005年10卷第4期页码：463
纸质出版：2005
DOI： 10.11834/jig.20050493
稿件说明：

移动端阅览

汪哲慎, 李翠华. 基于改进Hough变换的建筑目标搜索与识别[J]. 中国图象图形学报, 2005,10(4):463. DOI： 10.11834/jig.20050493.

Improved Classical Hough Transform Applied to Building Detection and Recognition[J]. Journal of Image and Graphics, 2005, 10(4): 463. DOI： 10.11834/jig.20050493.

摘要

结合建筑物搜索与识别的实例，运用改进的Hough变换算法，对经过预处理的图像进行检测，提出了优化、合并、分组的线条分析策略和针对目标的排伪策略以确定目标可能出现的区域，进而排除虚假目标，最终获得目标准确的定位区域。实验结果表明，改进的Hough算法以及线条分析和排伪策略应用在实际的检测识别系统中时，对不同比例、不同视角、不同拍摄时间和条件、目标被部分遮挡的情况以及出现马赛克现象的各种实验图像都具有较好的识别效果。

Abstract

In this paper

taking building detection and recognition as an instance

by using improved Hough transform

several line analysis strategies and measures to remove the inveracious targets are presented. The experimental results show that the approach with these methods can get acceptable results when image processing with scaling

different angles of view

various conditions of sunlight and mosaic phenomenon involved.