Visual Event Detection over AI-Edge LEO Satellites with AoI Awareness

2025-12-20

AI Summary

In AI-enabled low Earth orbit (LEO) satellite networks, stringent link budgets and severe path loss degrade visual event detection performance. To address this, we propose an AI-native semantic communication framework. Our method introduces: (1) a novel task-oriented deep joint source-channel coding (DJSCC) scheme, directly optimizing end-to-end detection accuracy rather than conventional reconstruction fidelity; and (2) a misclassification-aware Age of Information (AoMI) metric, coupled with threshold-based AoI analysis, jointly characterizing semantic freshness and inference reliability. Experimental results demonstrate that, compared to traditional separate source and channel coding (SSCC), our framework significantly improves detection accuracy, reduces average AoMI, and markedly increases the proportion of users meeting stringent semantic freshness thresholds. This work establishes a verifiable technical pathway for 6G+ onboard semantic communication systems.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Search and Optimization: Learning to Search
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Non terrestrial networks (NTNs), particularly low Earth orbit (LEO) satellite systems, play a vital role in supporting future mission critical applications such as disaster relief. Recent advances in artificial intelligence (AI)-native communications enable LEO satellites to act as intelligent edge nodes capable of on board learning and task oriented inference. However, the limited link budget, coupled with severe path loss and fading, significantly constrains reliable downlink transmission. This paper proposes a deep joint source-channel coding (DJSCC)-based downlink scheme for AI-native LEO networks, optimized for goal-oriented visual inference. In the DJSCC approach, only semantically meaningful features are extracted and transmitted, whereas conventional separate source-channel coding (SSCC) transmits the original image data. To evaluate information freshness and visual event detection performance, this work introduces the age of misclassified information (AoMI) metric and a threshold based AoI analysis that measures the proportion of users meeting application specific timeliness requirements. Simulation results show that the proposed DJSCC scheme provides higher inference accuracy, lower average AoMI, and greater threshold compliance than the conventional SSCC baseline, enabling semantic communication in AI native LEO satellite networks for 6G and beyond.

Problem

• Optimizes downlink for AI-native LEO satellite networks
• Addresses limited link budget and transmission reliability issues
• Enhances visual event detection with semantic communication

Innovation

• DJSCC transmits semantic features for visual inference
• AoMI metric evaluates information freshness and detection performance
• Threshold-based AoI analysis measures timeliness compliance