Detection and Target Tracking In FLIR Imagery

Targets in closing FLIR imagery generally appear as bright “hot-spots” having high contrast than their neighboring regions. We first perform region-based segmentation to detect targets where regions corresponds to possible the targets. Target candidates are then determined by considering: brightness, gradient information on the boundary of the region and the contrast with the neighboring regions. Among the detected candidates, the false positives are extracted by utilizing the texture information of the candidate and its neighboring regions. We experimented the following texture measures: GLCM, Law’s Texture Energy, Measures, Wavelets and Steerable Pyramids

Our experiments demonstrated that by using Steerable Pyramids as texture measures along with the Energy as the feature vector and the Median as the distance measure we were able to eliminate the most (94%) of the false positives among the detected target candidates.

 

Presentation

For PowerPoint presentation click here.

Result Videos

Sequence 1
Sequence 2
Sequence 3
Sequence 4
Sequence 5
Sequence 6
Sequence 7
Sequence 8
Sequence 9
Sequence 10

Related Publications

Alper Yilimaz, Khurram Shafique, Niels Lobo, Xin Li, Teresa Olson, Mubarak Shah, Target-Tracking in FLIR Imagery Using Mean-Shift and Global Motion Compensation, Workshop on Computer Vision Beyond the Visible Spectrum, with CVPR 2001, Kauai, Hawaii, Dec 14, 2001.

Alper Yilmaz, Khurram Shafique, Mubarak Shah, Target-Tracking in Airborne Forward Looking Infrared Imagery, Image and Vision Computing Journal, in press, 2003.