An efficient neuromorphic approach for collision avoidance combining Stack-CNN with event cameras

2025-06-19

AI Summary

To address the on-orbit collision risk posed by space debris, this paper proposes a novel real-time Space Situational Awareness (SSA) and Space Traffic Management (STM) paradigm integrating event cameras with a Stack-CNN architecture. Methodologically, we pioneer the adaptation of Stack-CNN to the event camera domain, designing a lightweight neuromorphic model that jointly exploits temporal dynamics of spike streams and embedded real-time inference optimization—specifically tailored for detecting faint, fast-moving objects under high temporal resolution and low signal-to-noise ratio (SNR) conditions. Experimental results on ground-simulated data demonstrate significant SNR enhancement for weak targets, meeting stringent onboard requirements of millisecond-level latency and milliwatt-level power consumption. Key contributions include: (1) the first algorithm–hardware co-design framework unifying event cameras and Stack-CNN for SSA/STM; and (2) a lightweight, real-time robust neuromorphic model enabling efficient in-orbit processing.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Space debris poses a significant threat, driving research into active and passive mitigation strategies. This work presents an innovative collision avoidance system utilizing event-based cameras - a novel imaging technology well-suited for Space Situational Awareness (SSA) and Space Traffic Management (STM). The system, employing a Stack-CNN algorithm (previously used for meteor detection), analyzes real-time event-based camera data to detect faint moving objects. Testing on terrestrial data demonstrates the algorithm's ability to enhance signal-to-noise ratio, offering a promising approach for on-board space imaging and improving STM/SSA operations.

Problem

• Develop collision avoidance system for space debris
• Use event cameras and Stack-CNN for detection
• Improve signal-to-noise ratio in space imaging

Innovation

• Stack-CNN algorithm for collision detection
• Event-based cameras for space awareness
• Enhances signal-to-noise ratio effectively