Transmission Line Foreign Object Suspension Detection Dataset

With the increasing demands on inspections in the power industry, traditional manual inspection methods face challenges such as low efficiency and high error rates. Although existing video surveillance technology can provide broad coverage, it still falls short in the precision and real-time detection of foreign objects. This dataset aims to address the detection of foreign object suspension on transmission lines, meeting the needs for automated inspections. The data are sourced from drone line inspection videos and power inspection images, strictly annotated and screened to ensure high-quality samples. Data collection uses high-resolution camera equipment under various weather conditions, covering multiple geographic locations. Quality control is ensured through multiple rounds of annotation and expert review to maintain annotation consistency. The data are stored in MP4 format, organized as video sequences for easy subsequent processing and analysis.