利用角点进行高分辨率遥感影像居民地检测方法

传统的城区检测方法大多是基于影像的全局特征，如纹理、光谱、形状等。当影像出现尺度、光照等条件变化时，将导致这些特征出现变化，造成算法的稳健性下降。而局部不变特征（例如，角点）却不易受到这些因素的影响。为此，本文提出一种无监督的基于角点特征的高分辨率遥感影像城区检测方法。该方法首先在传统的Harris算子的基础上，加入局部和全局约束准则检测影像中的角点，然后根据影像中角点的分布情况，自适应地构建似然函数来度量影像中每一个像素点属于城区的概率，最后采用二值分割的方法提取影像中的城市区域。实验结果表明：该方法可以快速、可靠地检测到影像中的城市区域，具有较高的实际应用价值。

Unsupervised urban detection from High-Resolution Remote-Sensing Imagery based on Improved Harris corner detector

Traditional urban detection methods are mainly based on global image feature, such as texture, spectrum and shape etc. However, these features are not invariant to scale and illumination changes, which consequently reduce the robust of the existing algorithms. To solve this problem, we propose the use of local feature for urban detection from high-resolution remote-sensing imagery. The proposed method consists of three steps: First, we extract a large set of local feature point by Harris corner detector. In order to achieve a reliable extraction of corners from urban areas, we further propose two criterions to validate and filter them. Afterwards, we incorporate the extracted corners into a likelihood function, and use it to measure the possibility of each pixel belonging to the urban area. Finally, we extract urban area by an adaptive binary segmentation method. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy.