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.