CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imaging

TL;DR

CarboFormer is a lightweight, efficient semantic segmentation model designed for real-time CO₂ emission detection in optical gas imaging, with novel datasets and strong performance in resource-limited environments.

Contribution

We introduce CarboFormer, a novel lightweight segmentation architecture with specialized features and two new datasets for CO₂ detection, enabling accurate and fast analysis in constrained settings.

Findings

Achieves 84.88% mIoU on CCR dataset.

Operates at 84.68 FPS with only 5.07M parameters.

Outperforms other lightweight models like SegFormer-B0 and SegNeXt.

Abstract

Carbon dioxide (CO$_2$) emissions are critical indicators of both environmental impact and various industrial processes, including livestock management. We introduce CarboFormer, a lightweight semantic segmentation framework for Optical Gas Imaging (OGI), designed to detect and quantify CO$_2$ emissions across diverse applications. Our approach integrates an optimized encoder-decoder architecture with specialized multi-scale feature fusion and auxiliary supervision strategies to effectively model both local details and global relationships in gas plume imagery while achieving competitive accuracy with minimal computational overhead for resource-constrained environments. We contribute two novel datasets: (1) the Controlled Carbon Dioxide Release (CCR) dataset, which simulates gas leaks with systematically varied flow rates (10-100 SCCM), and (2) the Real Time Ankom (RTA) dataset, focusing on emissions from dairy cow rumen fluid in vitro experiments. Extensive evaluations demonstrate that CarboFormer achieves competitive performance with 84.88\% mIoU on CCR and 92.98\% mIoU on RTA, while maintaining computational efficiency with only 5.07M parameters and operating at 84.68 FPS. The model shows particular effectiveness in challenging low-flow scenarios and significantly outperforms other lightweight methods like SegFormer-B0 (83.36\% mIoU on CCR) and SegNeXt (82.55\% mIoU on CCR), making it suitable for real-time monitoring on resource-constrained platforms such as programmable drones. Our work advances both environmental sensing and precision livestock management by providing robust and efficient tools for CO$_2$ emission analysis.