Building Change Detection Using 3-d Texture Model

Texture models are potentially very useful for automated urban data revision. We propose a ‘model-based change detection algorithm’ using three-dimensional urban data. In this algorithm, temporal images are projected on a common three-dimensional geometry model and the latest textures are compared with previous textures to detect an object’s change accurately. In addition, a shadow simulation with three-dimensional data can improve the accuracy of image comparison. Consequentially, the authors show that this algorithm is more reliable than an existing image-based change detection algorithm. Experimentally, using observed environmental temporal data, the authors confirmed that their algorithm could achieve reliable change detection with close to a 100% success rate.