TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Framework

TL;DR

This paper introduces TowerDataset, a large-scale, fine-grained benchmark for transmission corridor segmentation, and proposes a global-local fusion framework to effectively utilize global context and local details in complex scenes.

Contribution

The paper provides a new heterogeneous dataset with detailed taxonomy and a novel fusion framework that improves segmentation by combining global and local cues.

Findings

The dataset contains 661 real-world scenes with 2.466 billion points.

The proposed framework outperforms existing methods on TowerDataset and public benchmarks.

The benchmark highlights the challenge of transmission corridor segmentation in complex environments.

Abstract

Fine-grained semantic segmentation of transmission-corridor point clouds is fundamental for intelligent power-line inspection. However, current progress is limited by realistic data scarcity and the difficulty of modeling global corridor structure and local geometric details in long, heterogeneous scenes. Existing public datasets usually provide only a few coarse categories or short cropped scenes which overlook long-range structural dependencies, severe long-tail distributions, and subtle distinctions among safety-critical components. As a result, current methods are difficult to evaluate under realistic inspection settings, and their ability to preserve and integrate complementary global and local cues remains unclear. To address the above challenges, we introduce TowerDataset, a heterogeneous benchmark for transmission-corridor segmentation. TowerDataset contains 661 real-world scenes and about 2.466 billion points. It preserves long corridor extents, defines a fine-grained 22-class taxonomy, and provides standardized splits and evaluation protocols. In addition, we present a global-local fusion framework which preserves and fuses whole-scene and local-detail information. A whole-scene branch with NoCrop training and prototypical contrastive learning captures long-range topology and contextual dependencies. A block-wise local branch retains fine geometric structures. Both predictions are then fused and refined by geometric validation. This design allows the model to exploit both global relationships and local shape details when recognizing rare and confusing components. Experiments on TowerDataset and two public benchmarks demonstrate the challenge of the proposed benchmark and the robustness of our framework in real, complex, and heterogeneous transmission-corridor scenes. The dataset will be released soon at https://huggingface.co/datasets/tccx18/Towerdataset/tree/main.