Real-Time Detection and Tracking of Foreign Object Intrusions in Power Systems via Feature-Based Edge Intelligence

2025-09-16

AI Summary

To address real-time detection and tracking of foreign object intrusion (FOI) in power systems, this paper proposes a lightweight three-stage framework: (1) YOLOv7-based instance segmentation; (2) metric learning for feature extraction using a ConvNeXt backbone trained with triplet loss; and (3) an appearance- and IoU-aware feature-assisted multi-object tracking mechanism. The method significantly improves tracking robustness under occlusion and motion interference, enables zero-shot incremental registration of unseen object classes without model retraining—enhancing system scalability—and achieves low-latency deployment on NVIDIA Jetson edge devices via mixed-precision inference optimization. Evaluated on real-world surveillance and UAV-captured video datasets, the framework demonstrates high detection accuracy, stable tracking performance, strong real-time capability, and practical feasibility for edge deployment in power infrastructure monitoring.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper presents a novel three-stage framework for real-time foreign object intrusion (FOI) detection and tracking in power transmission systems. The framework integrates: (1) a YOLOv7 segmentation model for fast and robust object localization, (2) a ConvNeXt-based feature extractor trained with triplet loss to generate discriminative embeddings, and (3) a feature-assisted IoU tracker that ensures resilient multi-object tracking under occlusion and motion. To enable scalable field deployment, the pipeline is optimized for deployment on low-cost edge hardware using mixed-precision inference. The system supports incremental updates by adding embeddings from previously unseen objects into a reference database without requiring model retraining. Extensive experiments on real-world surveillance and drone video datasets demonstrate the framework's high accuracy and robustness across diverse FOI scenarios. In addition, hardware benchmarks on NVIDIA Jetson devices confirm the framework's practicality and scalability for real-world edge applications.

Problem

• Real-time foreign object intrusion detection in power systems
• Robust object tracking under occlusion and motion
• Edge-optimized deployment for low-cost hardware scalability

Innovation

• YOLOv7 segmentation for object localization
• ConvNeXt feature extractor with triplet loss
• Feature-assisted IoU tracker for occlusion