Short temporal change detection in complex urban area

Thermal hyperspectral imaging (THI) extends the activities of automatic spectral based target detection to the thermal infrared spectral range. This imaging technique which allows the detection of targets regardless of illumination, unfortunately, frequently suffers from high false alarm rates due to the high noise contained in the image. This study develops a new Normalised Difference Thermal Index NDTI_MM which allows the physics -based segmentation of Man-Made objects in the scene. This index produces quick and efficient separation of man-made objects containing silicate minerals from other natural and man-made materials. The change detectors are spatially adapted to segments which present different NDTI_MM ratios. As a result, the scene is enhanced and the performances of change detection methods which are based on NDTI_MM segments distance are significantly improved.