Work

Fully Autonomous Real-Time Defect Detection for Power Distribution Towers: A Small Target Defect Detection Method Based on YOLOv11n

Year: 2025

Type: article

Abstract: Drones offer a promising solution for automating distribution tower inspection, but real-time defect detection remains challenging due to limited computational resources and the small size of critical defects. This paper proposes TDD-YOLO, an optimized model based on YOLOv11n, which enhances small defect detection through four key improvements: (1) SPD-Conv preserves fine-grained details, (2) CBAM amplifies defect salience, (3) BiFPN enables efficient multi-scale fusion, and (4) a dedicated high-resolution detection head improves localization precision. Evaluated on a custom dataset, TDD-YOLO achieves an [email protected] of 0.873, outperforming the baseline by 3.9%. When deployed on a Jetson Orin Nano at 640 × 640 resolution, the system achieves an average frame rate of 28 FPS, demonstrating its practical viability for real-time autonomous inspection.

Source: Sensors

DOI: 10.3390/s25206445

Authors: Jingtao Zhang, Siwen Chen, Wei Wang, Qi Wang

Institutions: Nanjing University of Information Science and Technology, Fukushima Institute for Research, Education and Innovation, Nanjing Xiaozhuang University

Language: English

Topic: Power Line Inspection Robots

Subfield: Mechanical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $3,137