Using Onboard Clustering to Summarize Remotely Sensed Imagery

Abstract

to distance, visibility constraints, and competing mission downlinks. Long missions and highresolution, multispectral imaging devices easily produce data exceeding the available bandwidth. As an example, the HiRISE camera aboard the Mars Reconnaissance Orbiter produces images of up to 16.4 Gbits in data volume but downlink bandwidth is limited to 6 Mbits per second (Mbps).To address this situation, the Jet Propulsion Laboratory has developed computationally efficient algorithms for analyzing science imagery onboard spacecraft. These algorithms autonomously cluster the data into classes of similar imagery. This enables selective downlink of representatives of each class and a map classifying the imaged terrain rather than the full data set, reducing downlinked data volume. This article demonstrates the method on an Earth-based aerial image data set. We examine a range of approaches including k-means clustering using image features based on color, texture, temporal, and spatial arrangement and compare it to the manual clustering of a fi eld expert. In doing so, we demonstrate the potential for such summarization algorithms to enable effective exploratory science despite limited downlink bandwidth.

Autonomous science during large‐scale robotic survey

“…One‐dimensional models such as time series are relevant to temporal subsampling, such as in spacecraft flybys, lander image sequences, or engineering imagery from spacecraft maneuvers. Two‐dimensional spatial models have obvious applicability for mobile surface exploration but also aerial remote sensing from balloons, airships, and gliders (Fink et al, 2005; Hayden et al, 2010; Noor, Cutts, & Balint, 2007).…”

“…It can prioritize informative locations such as local anomalies, bypassing redundant measurements and quickly surveying large areas (Fink, 2006; McGuire, Ormö, Martínez, Manfredi, Elvira, et al, 2005). Finally, onboard science analysis can select or summarize data for bandwidth‐restricted downlink opportunities (Hayden, Chien, Thompson, & Castano, 2010; Thompson, Smith, & Wettergreen, 2008).…”