Translator Disclaimer
26 October 2016 Gas detection by using transmittance estimation and segmentation approaches
Author Affiliations +
Hyperspectral imaging for gas detection applications is an under-researched topic. The same gas model is used in most of the gas detection studies in the literature. This model aims to formulate the scene covering the gas emission as well as the background and the atmosphere. Therefore, the model requires prior knowledge on transmittance, emissivity, and temperature values of the components in the scene. The commonly used approaches to estimate these parameters include atmospheric modeling and statistical inference. However, accessing such information is costly in remote detection applications. Some studies avoid background characterization by decomposing the scene using spectral-spatial information.

There are several studies in the literature using this model. They aim to detect various types of gases on different parts of electromagnetic spectrum. Most of these studies use hyperspectral radiance information regarding the scene. However, using brightness temperature map of the data instead of radiance data is more suitable for direct analysis. For this reason, we used brightness temperature spectrum in this study.

On the other hand, the detection algorithms are generally based on pixel based investigation. Since the emission of the gas is sourced by a pipe or a chimney, investigating the emission region at the segment level increases detection accuracy. In this study, we used an iterative spectral feature based pixel clustering algorithm followed by spatial segmentation.
Conference Presentation
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Didem Özısık Baskurt, Yusuf Gür, Fatih Ömrüuzun, and Yasemin Yardımcı Çetin "Gas detection by using transmittance estimation and segmentation approaches", Proc. SPIE 10008, Remote Sensing Technologies and Applications in Urban Environments, 1000807 (26 October 2016);

Back to Top