The TRICLOBS Dynamic Multiband Image Dataset

posted on 08.10.2016 by Alexander Toet, Maarten A. Hogervorst, Alan R. Pinkus

The TRICLOBS dynamic multiband image dataset contains registered visual (400-700 nm) , near-infrared (NIR, 700-1000 nm) and longwave infrared (LWIR, 8-14 µm) motion sequences. This dataset is primarily intended for the development and evaluation of image fusion and color mapping algorithms for (military and civilian)  surveillance applications. The imagery was collected during several field trials with the TRICLOBS (TRI-band Color Low-light OBServation) all-day all-weather surveillance system.  The TRICLOBS system registers a scene in the Visual, NIR and LWIR part of the electromagnetic spectrum using three optically aligned sensors (two digital image intensifiers and an uncooled longwave infrared microbolometer).  The three sensor signals are mapped to the three individual RGB color channels, digitized and stored as uncompressed RGB (false) color frames. The TRICLOBS image dataset contains 16 motion sequences representing different military and civilian surveillance scenarios and registered at three different locations.  It is expected that the dataset will be useful for the development and evaluation of (both static and dynamic) image fusion and color mapping algorithms. To enable the development or realistic color remapping procedures, the dataset also contains color photographs of each of the three scenes. The color statistics derived from these photographs may be used to define color mappings that give the multiband imagery a realistic color appearance. Some color remapped examples are provides as MP4 movies.


Effort sponsored by the Air Force Office of Scientific Research, Air Force Material Command, USAF, under grant numbers FA8655-06-1-3017, FA8655-09-1-3095, FA8655-11-1-3015, FA9550-14-1-0069, and FA9550-15-1-0433. DISTRIBUTION STATEMENT A. Approved for pu