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.
In this study, a supportive method for afforestation planning process of partially forested areas using hyperspectral remote sensing imagery has been proposed. The algorithm has been tested on a scene covering METU campus area that is acquired by high resolution hyperspectral push-broom sensor operating in visible and NIR range of the electromagnetic spectrum. The main contribution of this study to the literature is segmentation of partially forested regions with a semi-supervised classification of specific tree species based on chlorophyll content quantified in hyperspectral scenes. In addition, the proposed method makes use of various hyperspectral image processing algorithms to improve identification accuracy of image regions to be planted.
This study aims to develop an effective regional shadow removal algorithm using rich spectral information existing in hyperspectral imagery. The proposed method benefits from spectral similarity of shadow and neighboring nonshadow pixels regardless of the intensity values. Although the shadow area has lower reflectance values due to inadequacy of incident light, it is expected that this area contains similar spectral characteristics with nonshadow area. Using this assumption, the endmembers in both shadowed and nonshadow area are extracted by Vertex Component Analysis (VCA). On the other hand, HySime algorithm overcomes estimating number of endmembers, which is one of the challenging parts in hyperspectral unmixing. Therefore, two sets of endmembers are extracted independently for both shadowed and nonshadow area. The proposed study aims at revealing the relation between these two endmember sets by comparing their pairwise similarities. Finally, reflectance values of shadowed pixels are re-calculated separately for each spectral band of hyperspectral image using this information.
Segmentation and identification of compounds or materials existing in a scene is a crucial process. Hyperspectral sensors operating in different regions of the electromagnetic spectrum are able to quantify spectral characteristics of materials in different states. Due to the fact that some chemical compounds in gas state have insignificant light reflectance characteristics in visible region of the spectrum, imaging sensors operating in infrared regions are needed to sense energy absorbency characteristics of these compositions. The present study proposes a novel method for detection of flammable gases in long-wave infrared hyperspectral images. Proposed method begins with Black-Body radiation curve compensation. Since a priori information regarding the compounds in the scene is not always available, endmember spectral signatures are extracted with VCA hyperspectral unmixing algorithm. Afterwards, endmember signatures are matched with infrared energy absorbance signature of the target gas obtained from NIST (National Institute of Standards and Technology) Material Measurement Laboratory. Finally, concentration of target signature at each image pixel is detected by means of endmember abundance maps. The performance of the approach is compared with that of similarity measure based gas detection methods. It is observed that the proposed technique removes the need for an external threshold setting while providing better resolvability of the gasses.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.