Domain Adaptation and Multi-view Attention for Learnable Landmark Tracking with Sparse Data
By: Timothy Chase Jr, Karthik Dantu
Potential Business Impact:
Helps spaceships land safely on new planets.
The detection and tracking of celestial surface terrain features are crucial for autonomous spaceflight applications, including Terrain Relative Navigation (TRN), Entry, Descent, and Landing (EDL), hazard analysis, and scientific data collection. Traditional photoclinometry-based pipelines often rely on extensive a priori imaging and offline processing, constrained by the computational limitations of radiation-hardened systems. While historically effective, these approaches typically increase mission costs and duration, operate at low processing rates, and have limited generalization. Recently, learning-based computer vision has gained popularity to enhance spacecraft autonomy and overcome these limitations. While promising, emerging techniques frequently impose computational demands exceeding the capabilities of typical spacecraft hardware for real-time operation and are further challenged by the scarcity of labeled training data for diverse extraterrestrial environments. In this work, we present novel formulations for in-situ landmark tracking via detection and description. We utilize lightweight, computationally efficient neural network architectures designed for real-time execution on current-generation spacecraft flight processors. For landmark detection, we propose improved domain adaptation methods that enable the identification of celestial terrain features with distinct, cheaply acquired training data. Concurrently, for landmark description, we introduce a novel attention alignment formulation that learns robust feature representations that maintain correspondence despite significant landmark viewpoint variations. Together, these contributions form a unified system for landmark tracking that demonstrates superior performance compared to existing state-of-the-art techniques.
Similar Papers
Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation
CV and Pattern Recognition
Helps robots in space know where they are.
Domain Adaptive Object Detection for Space Applications with Real-Time Constraints
CV and Pattern Recognition
Helps space cameras see real things better.
Landmarks Are Alike Yet Distinct: Harnessing Similarity and Individuality for One-Shot Medical Landmark Detection
CV and Pattern Recognition
Helps doctors find body parts in X-rays better.