November 20, 2018: Most content in the UA Campus Repository is not accessible using the search/browse functions due to a performance bug; we are actively working to resolve this issue. If you are looking for content you know is in the repository, but cannot get to it, please email us at firstname.lastname@example.org with your questions and we'll make sure to get the content to you.
Anomaly Detection and Target Prioritization in Planetary Imagery via the Automated Global Feature Analyzer (TM) (AGFA (TM)): Progress Towards a Driver for Autonomous (CISR)-I-4 Missions
AffiliationUniv Arizona, Coll Engn, Visual & Autonomous Explorat Syst Res Lab
KeywordsAutonomous decision making
objective anomaly detection
principal components analysis
autonomous (CISR)-I-4 systems
multi-tiered robotic exploration architectures
MetadataShow full item record
PublisherSPIE-INT SOC OPTICAL ENGINEERING
CitationWolfgang Fink, Alexander J.-W. Brooks, Mark A. Tarbell, "Anomaly detection and target prioritization in planetary imagery via the automated global feature analyzer (AGFA): Progress towards a driver for autonomous C4ISR missions," Proc. SPIE 10639, Micro- and Nanotechnology Sensors, Systems, and Applications X, 106391Z (14 May 2018); doi: 10.1117/12.2303795
Rights© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).
Collection InformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at email@example.com.
AbstractThe Automated Global Feature Analyzer (TM) (AGFA (TM)) is a generically applicable automated sensor-data-fusion, feature extraction, feature vector clustering, anomaly detection, and target prioritization framework. AGFA (TM) operates in the respective feature space delivered by the sensor(s). In this paper we provide an overview of the inner workings of AGFA (TM) and apply AGFA (TM) to planetary imagery, representative of past, current, and future planetary missions, to demonstrate its automated and objective (i.e., unbiased) anomaly detection and target prioritization (i.e., region-of interest delineation) capabilities. Imaged operational areas are locally processed via a cascade of image segmentation, visual and geometric feature extraction, agglomerative clustering, and principal components analysis. Resulting clusters are labeled based on relative size and location in feature space. Anomalous regions may be considered immediate targets for follow-up in-situ investigation by local robotic agents, which can be directed via autonomous telecommanding, e.g., as part of a Tier-Scalable Reconnaissance mission architecture. These capabilities will be essential for driving fully autonomous (CISR)-I-4 missions of the future, since the speed of light prohibits "real time" Earth-controlled conduct of planetary exploration beyond the Moon.
VersionFinal published version
SponsorsEdward & Maria Keonjian Endowment at the University of Arizona; NASA via Arizona Space Grant Consortium (AZSGC) [NNX15AJ17H]