Matt Brown, Rocket Lab; William Bidle, Rocket Lab; D. Brandon Knape, Rocket Lab; Brandon Whitchurch, Rocket Lab; Skip Williams, Rocket Lab
Keywords: Machine Learning, Deep Neural Network, SDA, Detection, Classification, RSO, Ellipse
Abstract:
We report on an artificial intelligence (AI) approach for real-time, single-shot detection and classification of unresolved resident space objects (RSO) with sub-pixel localization via implicit ellipse regression. Deep-neuralnetwork (DNN) machine learning achieves state-of-the-art performance in virtually all modern video objectdetection domains where large-scale training datasets are available. However, in domains where training data is limited, overfitting and lack of generalization is a major concern. To navigate this challenge for RSO detection, we developed a comprehensive simulation framework to synthesize images of far-field point objects (stars and RSOs), spanning a wide range of brightness, point spread function (PSF), and motion blur (0-500 pixels streaks) to train our network. We demonstrate robust generalization on real ground-based telescope data. In a single pass of an image through the network, the model detects each far-field point object consistent with the simulated PSF and fits a subpixel-accurate ellipse. These vectorized analytics allow flexible discrimination between stars and RSO across a variety of missions. We present results and timings for our deep neural network deployed on an NVIDIA Jetson AGX Orin™ edge computer and on a space-grade Xilinx Versal™ VC1902 system-on-chip (SoC).
Date of Conference: September 16-19, 2025
Track: Machine Learning for SDA Applications