The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 1437–1441, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-1437-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 1437–1441, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-1437-2019

  05 Jun 2019

05 Jun 2019

ANOMALY DETECTION PERFORMANCE COMPARISON ON ANOMALY-DETECTION BASED CHANGE DETECTION ON MARTIAN IMAGE PAIRS

A. R. D. Putri, P. Sidiropoulos, and J.-P. Muller A. R. D. Putri et al.
  • Imaging Group, Mullard Space Science Laboratory, Dept. of Space and Climate Physics, University College London, Holmbury St Mary, Surrey, RH5 6NT, UK

Keywords: change detection, Martian surface dynamics, mars, machine learning

Abstract. The surface of Mars has been imaged in visible wavelengths for more than 40 years since the first flyby image taken by Mariner 4 in 1964. With higher resolution from orbit from MOC-NA, HRSC, CTX, THEMIS, and HiRISE, changes can now be observed on high-resolution images from different instruments, including spiders (Piqueux et al., 2003) near the south pole and Recurring Slope Lineae (McEwen et al., 2011) observable in HiRISE resolution. With the huge amount of data and the small number of datasets available on Martian changes, semi-automatic or automatic methods are preferred to help narrow down surface change candidates over a large area.

To detect changes automatically in Martian images, we propose a method based on a denoising autoencoder to map the first Martian image to the second Martian image. Both images have been automatically coregistered and orthorectified using ACRO (Autocoregistration and Orthorectification) (Sidiropoulos and Muller, 2018) to the same base image, HRSC (High-Resolution Stereo Camera) (Neukum and Jaumann, 2004; Putri et al., 2018) and CTX (Context Camera) (Tao et al., 2018) orthorectified using their DTMs (Digital Terrain Models) to reduce the number of false positives caused by the difference in instruments and viewing conditions. Subtraction of the codes of the images are then inputted to an anomaly detector to look for change candidates. We compare different anomaly detection methods in our change detection pipeline: OneClassSVM, Isolation Forest, and, Gaussian Mixture Models in known areas of changes such as Nicholson Crater (dark slope streak), using image pairs from the same and different instruments.