Automated detection of block falls in the north polar region of Mars
This work addresses the need for efficient monitoring of geological changes on Mars for planetary scientists, but it is incremental as it applies existing machine learning methods to a specific dataset.
The researchers tackled the problem of automatically detecting ice block falls on Mars using HiRISE images, achieving a true positive rate of ~75% for blocks larger than 0.7 m and a false discovery rate of ~8.5%.
We developed a change detection method for the identification of ice block falls using NASA's HiRISE images of the north polar scarps on Mars. Our method is based on a Support Vector Machine (SVM), trained using Histograms of Oriented Gradients (HOG), and on blob detection. The SVM detects potential new blocks between a set of images; the blob detection, then, confirms the identification of a block inside the area indicated by the SVM and derives the shape of the block. The results from the automatic analysis were compared with block statistics from visual inspection. We tested our method in 6 areas consisting of 1000x1000 pixels, where several hundreds of blocks were identified. The results for the given test areas produced a true positive rate of ~75% for blocks with sizes larger than 0.7 m (i.e., approx. 3 times the available ground pixel size) and a false discovery rate of ~8.5%. Using blob detection we also recover the size of each block within 3 pixels of their actual size.