基于支持向量机的显著性建筑物检测  

Salient Building Detection Based on SVM

作　　者：曲延云[1,2] 郑南宁[1] 李翠华[3] 袁泽剑[1] 叶聪颖[3] 

机构地区：[1]西安交通大学人工智能与机器人研究所 [2]厦门大学计算机科学系厦门361005 [3]厦门大学计算机科学系

出　　处：《计算机研究与发展》2007年第1期141-147,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60635050;60405004);国家自然科学创新研究群体基金项目(60021302)

摘　　要：提出了一种针对自然图像中显著性建筑物的检测方法.首先,采用自底向上的注意力机制,对图像进行Haar小波分解,对得到的HL,LH分量进行平方求和,得到增强图像,然后对该增强图像在垂直方向上进行侧投影,基于得到的投影曲线进行多层阈值分割,找到显著性建筑物候选区域.进而,利用Sobel算子进行水平边缘与垂直边缘的检测,并统计较长的水平边缘与垂直边缘的数目,组成特征矢量.最后利用线性支持向量机对特征进行分类.实验证明了所提算法的有效性.This paper focuses on detecting salient buildings in a scenery image. A method based on bottomup attention mechanism is proposed to detect salient buildings. Firstly, Haar wavelet decomposition is used to obtain the enhanced image which is the sum of the square of LH sub-image and HL sub-image. Secondly, the enhanced image is projected in the vertical direction to obtain the projection profile, and building candidates are separated from the background based on multi-level thresholding. Thirdly, the structure statistic features of buildings are extracted based on Sobel operator. The feature vector is formed by the number of long horizontal edges and that of vertical edges. Finally, linear support vector machines are used to classify buildings and the others. The proposed approach has been experimented on many realworld images with promising results.

关 键 词：建筑物检测 自底向上的注意力机制 Haar小波分解 支持向量机 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]