Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Chathuranga M. Wijerathna Basnayaka, Haeyoung Lee, Pandelis Kourtessis, John M. Senior, Vishalya P. Sooriarachchi, Dushantha Nalin K. Jayakody, Marko Beko, Seokjoo Shin

TL;DR

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.

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.

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

TL;DR

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.

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.
Paper Structure (5 sections, 20 equations, 5 figures)

This paper contains 5 sections, 20 equations, 5 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Age of Information Analysis
  4. Numerical Results and Performance Analysis
  5. Conclusion

Figures (5)

  • Figure 1: System architecture of the proposed LEO satellite communication system. The satellite captures images and transmits them to $U$ ground users (GUs) via DJSCC.
  • Figure 2: (a) DJSCC transceiver; (b) SSCC transceiver. The DJSCC encoder maps images directly to channel symbols; the decoder performs classification without reconstruction. The SSCC chain comprises BPG compression, LDPC coding, QAM modulation, demodulation, LDPC decoding, BPG decompression, and classification.
  • Figure 3: Average classification accuracy vs. transmission power for DJSCC and conventional LDPC+BPG at 400 km and 1000 km orbit heights.
  • Figure 4: Network AAoMI ($\alpha_{\text{avg}}^{\text{net}}$) vs. transmission power characteristics for DJSCC and conventional LDPC+BPG at 400 km and 1000 km orbit heights.
  • Figure 5: Threshold Compliance Ratio $\Gamma$ vs. transmission power characteristics for DJSCC and conventional LDPC+BPG at 400 km and 1000 km orbit heights, with AoMI threshold $\eta_{\text{aomi}} = 2$ seconds.