CRATER DETECTION USING TEXTURE FEATURE AND RANDOM PROJECTION DEPTH FUNCTION
- 1Shanghai Key Laboratory for Planetary Mapping and Remote Sensing for Deep Space Exploration1239 Siping Road, Shanghai 200092, P. R. China
- 2College of Surveying and Geo-informatics, Tongji University, 1239 Siping Road, Shanghai 200092, P. R. China
- 3College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, P. R. China
- 4School of Electronic and Computer Engineering, Mississippi State University, USA
Keywords: Crater Detection, Gray Level Co-occurrence Matrix, Grade Level Co-occurrence Matrix, Random Projection Depth Function, Anomaly Detection
Abstract. In this paper, a novel automatic crater detection algorithm (CDA) based on traditional texture feature and random projection depth function has been proposed. By using traditional texture feature, mathematical morphology is used to identify crater initially. To further reduce the false detection rate, random projection depth function is used. For this purpose, firstly, gray level co-occurrence matrix and a novel grade level co-occurrence matrix are both used to further obtain the texture features of these candidate craters. Secondly, based on the above collected features, random projection depth function is used to refine the crater candidate detection results. LRO Narrow Angle Camera (NAC) mosaic images (1 m/pixel) and Wide-angle Camera (WAC) mosaic images (100 m/pixel) are used to test the accuracy of proposed method. The experimental results indicate our proposed method is robust to detect craters located in different terrains.