Large-Scale, Multiple Level-of-Detail Change Detection from Remote Sensing Imagery Using Deep Visual Feature Clustering

In the era of big data, where massive amounts of remotely sensed imagery can be obtained from various satellites accompanied by the rapid change in the surface of the Earth, new techniques for large-scale change detection are necessary to facilitate timely and effective human understanding of natural and human-made phenomena. In this research, we propose a chip-based change detection method that is enabled by using deep neural networks to extract visual features. These features are transformed into deep orthogonal visual features that are then clustered based on land cover characteristics. The resulting chip cluster memberships allow arbitrary level-of-detail change analysis that can also support irregular geospatial extent based agglomerations. The proposed methods naturally support cross-resolution temporal scenes without requiring normalization of the pixel resolution across scenes and without requiring pixel-level coregistration processes. This is achieved with configurable spatial locality comparisons between years, where the aperture of a unit of measure can be a single chip, a small neighborhood of chips, or a large irregular geospatial region. The performance of our proposed method has been validated using various quantitative and statistical metrics in addition to presenting the visual geo-maps and the percentage of the change. The results show that our proposed method efficiently detected the change from a large scale area.