Event-Based Object Detection and Tracking for Space Situational Awareness

Abstract

In this work, we present an optical space imaging dataset using a range of event-based neuromorphic vision sensors. The unique method of operation of event-based sensors makes them ideal for space situational awareness (SSA) applications due to the sparseness inherent in space imaging data. These sensors offer significantly lower bandwidth and power requirements making them particularly well suited for use in remote locations and space-based platforms. We present the first publicly-accessible event-based space imaging dataset including recordings using sensors from multiple providers, greatly lowering the barrier to entry for other researchers given the scarcity of such sensors and the expertise required to operate them for SSA applications. The dataset contains both day time and night time recordings, including simultaneous co-collections from different event-based sensors. Recorded at a remote site, and containing 572 labeled targets with a wide range of sizes, trajectories, and signal-tonoise ratios, this real-world event-based dataset represents a challenging detection and tracking task that is not readily solved using previously proposed methods. We propose a highly optimized and robust feature-based detection and tracking method, designed specifically for SSA applications, and implemented via a cascade of increasingly selective event filters. These filters rapidly isolate events associated with space objects, maintaining the high temporal resolution of the sensors. The results from this simple yet highly optimized algorithm on the space imaging dataset demonstrate robust high-speed event-based detection and tracking which can readily be implemented on sensor platforms in space as well as terrestrial environments.

Real-Time Event-Based Unsupervised Feature Consolidation and Tracking for Space Situational Awareness

“…Various optical flow estimation algorithms (Benosman et al, 2013) have also been proposed, which can be used to form the basis of a tracking algorithm. Machine learning approaches to tracking by detection have also been proposed, largely using GNN strategies or learned associations with supervised and unsupervised feature extraction for measurement detection (Lagorce et al, 2015;Afshar et al, 2019b). These algorithms operate on various representations of events, such as integrated frames, volumes (Wes Baldwin et al, 2021), graphs (Bi et al, 2020), and "time-surfaces" (Clady et al, 2015;Afshar et al, 2019a).…”

The State of the Art of Information Integration in Space Applications

“…For examples, Gamba et al [21] developed passive acoustic sensors to measure temperature in an aboard space platform remotely; no battery was needed to operate such sensors in extreme environment. Afshar et al [22] developed a neuromorphic vision senor to detect events for space situational awareness. The developed sensor offered low bandwidth and low power consumption; it is particularly suitable to remote locating and space-based platforms.…”

e-TLD: Event-Based Framework for Dynamic Object Tracking

“…Similarly, the robot goalie application [25] and [26] take advantage of the stationary DVS camera for tracking multiple objects. Recently, [27] proposed an event-based algorithm that can perform tasks such as detection and tracking designed specifically for space situational awareness applications.…”