ROCKSTER (Rock Segmentation Through Edge Regrouping) is a rock detection algorithm that analyzes 2D geologic scenes and identifies rocks and other targets of interest. A multicore ROCKSTER enables long-range autonomous rover traverse science to be performed efficiently and to make use of multicore or parallel computing capabilities.
ROCKSTER initially locates partial boundary contours of rocks using a procedure similar to the well-known Canny edge detector. In particular, an intensity gradient is calculated over the image; ridges in the intensity gradient are linked together using non-maximum suppression, hysteresis thresholding, and edge-following, yielding a set of raw contours.
This initial set of contours must then be further processed to provide a usable segmentation of rocks from the background. ROCKSTER performs this step by splitting the initial contours into low-curvature fragments. Potential T-junctions that were missed by the edge detector are identified and used to split fragments further into even smaller pieces. A gap-filling mechanism is then applied to add new contour fragments between existing fragment end-points. The final step is to regroup the edge fragments into coherent contours, which is accomplished through background flooding. Conceptually, water is poured into the image from the sides, but the water is not allowed to cross over any edge fragments; thus, regions that are totally enclosed by edge fragments remain “dry” while other areas become “wet.” Extracting contours around the dry areas yields the final rock segmentation.
Multicore ROCKSTER provides data parallelization of ROCKSTER by first dividing the image to analyze into tiles or strips. ROCKSTER is then run on each image tile using a separate processor core. Once all cores finish, rock detections are aggregated.
This work was done by Benjamin J. Bornstein, Paul L. Springer, Bradley J. Clement, Tara A. Estlin, and William K. Reinholtz of Caltech for NASA’s Jet Propulsion Laboratory.
This software is available for commercial licensing. Please contact Dan Broderick at
This Brief includes a Technical Support Package (TSP).
Multicore ROCKSTER
(reference NPO47880) is currently available for download from the TSP library.
Don't have an account?
Overview
The document outlines NASA's Jet Propulsion Laboratory (JPL) efforts to enhance long-range rover science through the use of multicore computing, specifically focusing on the Multicore ROCKSTER project. The principal investigator, Tara Estlin, along with a team of researchers, aims to adapt and evaluate key rover technologies for execution on multicore processors, which promise significant improvements in processing performance and fault tolerance.
The project targets three high-level autonomy technologies: two for onboard data analysis (rock detection and texture analysis) and one for command sequencing and planning. The adaptation of these technologies to multicore processors is expected to yield an order of magnitude increase in processing speed, particularly in the automated identification of rocks in images captured by the Mars Exploration Rover (MER). This capability is crucial for the rover's autonomous science algorithms, enabling it to efficiently acquire high-quality remote sensing data of scientific interest.
Future work outlined in the document includes improving the scaling and evaluation of the multicore systems, investigating memory I/O bottlenecks, and integrating visual texture analysis using Haar-like filter banks. The team is also focused on developing a fault-tolerant middleware layer and establishing quantifiable quality evaluation metrics, such as precision, recall, and various statistical measures.
The document emphasizes the importance of these advancements for upcoming NASA missions, including the Mars Sample Return (MSR), Mars 2020 (MSL), and potential missions to Titan and Europa. The benefits of multicore computing will be measured through execution time, power requirements, and the number of data products processed per unit time, ultimately enhancing the quality of solutions derived from rover operations.
In summary, the Multicore ROCKSTER project represents a significant step forward in leveraging advanced computing technologies to improve the autonomy and efficiency of space exploration rovers, paving the way for more sophisticated scientific investigations on other planets. The ongoing research and development efforts at JPL aim to ensure that future missions can operate with greater intelligence and adaptability in challenging extraterrestrial environments.
