PL-UNeXt: Per-stage Edge Detail and Line Feature Guided Segmentation for Power Line Detection

TL;DR

PL-UNeXt is a novel power line segmentation model that leverages edge detail and line features with a booster training strategy to improve accuracy and maintain real-time performance in aerial imagery.

Contribution

The paper introduces PL-UNeXt, a power line segmentation model that incorporates edge detail and line feature guidance with a booster training strategy for enhanced accuracy.

Findings

Achieves 70.6 F1 score on TTPLA dataset.

Attains 68.41 mIoU on VITL dataset.

Operates in real-time with few inference parameters.

Abstract

Power line detection is a critical inspection task for electricity companies and is also useful in avoiding drone obstacles. Accurately separating power lines from the surrounding area in the aerial image is still challenging due to the intricate background and low pixel ratio. In order to properly capture the guidance of the spatial edge detail prior and line features, we offer PL-UNeXt, a power line segmentation model with a booster training strategy. We design edge detail heads computing the loss in edge space to guide the lower-level detail learning and line feature heads generating auxiliary segmentation masks to supervise higher-level line feature learning. Benefited from this design, our model can reach 70.6 F1 score (+1.9%) on TTPLA and 68.41 mIoU (+5.2%) on VITL (without utilizing IR images), while preserving a real-time performance due to few inference parameters.