Object-Oriented Remote Sensing Image Change Detection Based on Color Co-Occurrence Matrix

Aiming at the problem of misdetection caused by the traditional texture characteristic extraction model, which does not describe the correlation among multiple bands, an object-oriented remote sensing image change detection method based on a color co-occurrence matrix is proposed. First, the image is divided into multi-scale objects by graph-based superpixel segmentation, and the optimal scale is determined by the overall goodness F-measure (OGF). Then, except for the extraction of the spectral features, the multi-channel texture features based on the color co-occurrence matrix (CCM) are extracted to consider the correlation among multiple bands. To accurately find the representative features to overcome the impact of feature redundancy, a cumulative backward search strategy (CBSS) is further designed. Finally, the change detection is completed by inputting the difference image of dual time points to the trained random forest model. Taking Shenzhen and Dapeng as the study areas, with Sentinel-2 and Skysat images under different spatial resolutions, and the forest-bareland change type as an example, the effectiveness of the proposed algorithm is verified by qualitative and quantitative analyses. They show that the proposed algorithm can obtain higher detection accuracy than the texture features without band correlation.

Automated summary

A object-oriented remote sensing image change detection method based on a color co-occurrence matrix is proposed to address the misdetection problem caused by the lack of correlation among multiple bands in traditional texture characteristic extraction model. The image is divided into multi-scale objects by graph-based superpixel segmentation, and the multi-channel texture features based on the color co-occurrence matrix (CCM) are extracted. A cumulative backward search strategy (CBSS) is designed to find representative features to overcome feature redundancy. The proposed algorithm achieves higher detection accuracy than texture features without band correlation, as demonstrated through qualitative and quantitative analyses using Sentinel-2 and Skysat images in Shenzhen and Dapeng.