Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation

2025-05-28

AI Summary

To address the challenges of fine-grained object segmentation and strong interference from complex backgrounds in Power Transmission Corridor Hazardous Segmentation (PTCHS), this paper proposes ELE-SAM: a novel framework featuring a context-aware prompt adapter that enables collaborative global–local feature guidance, and a high-fidelity mask decoder integrating multi-granularity feature reconstruction with high-resolution upsampling. We introduce ELE-40K—the first large-scale, real-world PTCHS dataset comprising 44,094 image–mask pairs. On ELE-40K, ELE-SAM achieves absolute improvements of +16.8% in mIoU and +20.6% in mBIoU over prior methods. On the HQSeg-44K benchmark, it surpasses state-of-the-art approaches by +2.9% mIoU and +3.8% mBIoU. These results significantly advance the practical deployment of intelligent hazard identification in power transmission infrastructure.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Hardware-aware ML

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Power transmission corridor hazard segmentation (PTCHS) aims to separate transmission equipment and surrounding hazards from complex background, conveying great significance to maintaining electric power transmission safety. Recently, the Segment Anything Model (SAM) has emerged as a foundational vision model and pushed the boundaries of segmentation tasks. However, SAM struggles to deal with the target objects in complex transmission corridor scenario, especially those with fine structure. In this paper, we propose ELE-SAM, adapting SAM for the PTCHS task. Technically, we develop a Context-Aware Prompt Adapter to achieve better prompt tokens via incorporating global-local features and focusing more on key regions. Subsequently, to tackle the hazard objects with fine structure in complex background, we design a High-Fidelity Mask Decoder by leveraging multi-granularity mask features and then scaling them to a higher resolution. Moreover, to train ELE-SAM and advance this field, we construct the ELE-40K benchmark, the first large-scale and real-world dataset for PTCHS including 44,094 image-mask pairs. Experimental results for ELE-40K demonstrate the superior performance that ELE-SAM outperforms the baseline model with the average 16.8% mIoU and 20.6% mBIoU performance improvement. Moreover, compared with the state-of-the-art method on HQSeg-44K, the average 2.9% mIoU and 3.8% mBIoU absolute improvements further validate the effectiveness of our method on high-quality generic object segmentation. The source code and dataset are available at https://github.com/Hhaizee/ELE-SAM.

Problem

• Adapt SAM for power transmission corridor hazard segmentation
• Improve segmentation of fine structures in complex backgrounds
• Develop a large-scale dataset for PTCHS benchmarking

Innovation

• Context-Aware Prompt Adapter for better tokens
• High-Fidelity Mask Decoder for fine structures
• ELE-40K benchmark for large-scale PTCHS