Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking

Abstract

Deep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. This paper presents a target-aware deep feature compression for power intelligent inspection tracking. First, a negative balance loss function is designed to mine channel features suitable for the current inspection scene by shrinking the contribution of pure background negative samples and enhancing the impact of difficult negative samples. Based on this, the deep feature compression model is combined with Siamese tracking framework to achieve real-time and robust tracking. Finally, we evaluate the proposed method on real application scenarios and general data to prove the practicability of the proposed method.

Data Fusion and Ensemble Learning for Advanced Anomaly Detection Using Multi-Spectral RGB and Thermal Imaging of Small Wind Turbine Blades

“…They also be used for sagging lines, vegetation encroachments, or damaged insulators [22]. The primary advantage of employing deep learning in these applications is its ability to process large volumes of data quickly and consistently, providing valuable insights for timely maintenance and repairs [23]. As the energy industry continues to evolve, integrating deep learning into regular inspection routines promises significant improvements in the safety, efficiency, and longevity of critical infrastructure [24].…”