Autonomous Craters Detection from Planetary Image

Abstract

As development of deep space exploration, the Guidance, Navigation and Control (GNC) technology of spacecraft or probe is becoming more important than ever. Vision-based navigation (optical navigation) is a good method to achieve autonomous landing of spacecraft. Therefore, the landmark has to be detected for Vision-based navigation. Craters are commonly found on the surface of planets, satellites, asteroids and other solar system bodies. Currently, the most of optical landmark navigation algorithm are built on the craters detection and tracking. The focus of this paper is to present an algorithm for autonomous crater detection. The whole course of crater detection can be divided into two steps, Multi-resolution feature points extraction and crater detection. The first step can be further divided into Multi-resolution window-based feature points' extraction and crater candidate area choice. The second step can be further divided into region growing, pixels of crater edge extraction, ellipse detection and obtaining craters. Experimental studies demonstrate that the detection rate of this algorithm is higher than 90% for image where the distribution of craters is discrete. Cao Yun-feng received M.E in School of

Automated quantitative measurements and associated error covariances for planetary image analysis

“…These include the mapping of small lunar craters as part of the MoonZoo (Joy et al, 2011) and Moon Mappers projects (Robbins et al, 2012), and the mapping of seasonal carbon dioxide 'fans' on Mars via Planet Four (Hansen et al, 2013). Automated approaches to crater counting (Salamuniccar and Loncaric, 2010;Ding et al, 2010;Bandeira et al, 2010;Burl et al, 2001;Kim et al, 2005;Simpson et al, 2008;Bauer et al, 2011;Sawabe et al, 2005;Ding et al, 2008;Kamarudin et al, 2012;Wetzler et al, 2005), and valley and channel network mapping (Wei and Stepinski, 2009;Wei and Stepinski, 2006;Molloy and Stepinski, 2007) have also been tested with some success. Automated approaches tend to follow the same general design pattern: raw image data is encoded using a higherlevel descriptive format (edge strings, Haar transform, texture descriptors, templates, etc.…”

Crater detection from commercial satellite imagery to estimate unexploded ordnance in Cambodian agricultural land

“…Previous attempts to detect bomb craters borrow from well-established methods in the meteor crater literature, which scan satellite images for large, circular craters on planetary surfaces in outer space [12][13][14][15]. Key differences between bomb craters and meteor craters may result in these methods undercounting the bomb craters on satellite images.…”

Elliptical Object Detection by a Modified RANSAC with Sampling Constraint from Boundary Curves' Clustering

“…The dotted block in Fig. 5 (d) is an example against condition (5). That is, t 2 is found by the clockwise search from p i along p i 's boundary curve, but t 1 is not found by the counterclockwise search from p i , because the counterclockwise search from p i encounters the discontinuity of p i 's curve.…”

“…Therefore, in Fig. 5 (d)'s dotted block, t 1 is found also by the clockwise search from p i only after the search encounters t 2 ; so that this case does not satisfy condition (5).…”

“…As computing hardware and theories have improved, in recent years a wide range of ellipseestimation applications, including defect detection for industrial products [24], ellipse extraction from remote sensing images [5], [14], [39], biological and biomedical analysis [2], [12], [18], intelligent transportation systems [25], [32], human pupil monitoring [17], human face recognition and tracking [7], [10], [22], [38], [40], video surveillance [27], [35], [36], and others [37], has been achieved. In addition, since the ellipse is a fundamental shape primitive, ellipse detection can facilitate more advanced object recognition tasks by providing significant appearance features.…”