This paper deals with point target detection in infrared images of the sky for which there are local variations of the gray level mean value. We show that considering a simple image model with the gray level mean value varying as a linear or a quadratic function of the pixel coordinates can improve mixed segmentation–detection performance in comparison to homogeneous model-based approaches.
© 2010 Optical Society of America
Original Manuscript: November 11, 2009
Manuscript Accepted: January 3, 2010
Published: March 10, 2010
Emilie Vasquez, Frédéric Galland, Guillaume Delyon, and Philippe Réfrégier, "Mixed segmentation-detection-based technique for point target detection in nonhomogeneous sky," Appl. Opt. 49, 1518-1527 (2010)