Fine-grained spatial-temporal perception for gas leak segmentation

TL;DR

This paper introduces FGSTP, a novel end-to-end algorithm that captures spatial-temporal motion cues and refines object features for accurate gas leak segmentation, addressing the challenge of detecting concealed and irregularly shaped leaks.

Contribution

The paper presents a new fine-grained perception method with a correlation volume and a custom dataset for gas leak segmentation, improving accuracy over existing models.

Findings

FGSTP outperforms SOTA models in gas leak segmentation accuracy.

Constructed GasVid dataset enables effective training and evaluation.

Model effectively segments non-rigid, concealed gas leaks.

Abstract

Gas leaks pose significant risks to human health and the environment. Despite long-standing concerns, there are limited methods that can efficiently and accurately detect and segment leaks due to their concealed appearance and random shapes. In this paper, we propose a Fine-grained Spatial-Temporal Perception (FGSTP) algorithm for gas leak segmentation. FGSTP captures critical motion clues across frames and integrates them with refined object features in an end-to-end network. Specifically, we first construct a correlation volume to capture motion information between consecutive frames. Then, the fine-grained perception progressively refines the object-level features using previous outputs. Finally, a decoder is employed to optimize boundary segmentation. Because there is no highly precise labeled dataset for gas leak segmentation, we manually label a gas leak video dataset, GasVid. Experimental results on GasVid demonstrate that our model excels in segmenting non-rigid objects such as gas leaks, generating the most accurate mask compared to other state-of-the-art (SOTA) models.