3 November 2015 Detecting small, low-contrast moving targets in infrared video produced by inconsistent sensor with bad pixels
Author Affiliations +
This paper addresses the problem of finding small and low-contrast moving targets in infrared (IR) video sequences produced by sensors with inconsistent parameters, such as intensity offset and gain as well as bad pixels. This sensor variability makes it difficult to apply methods based on frame registration using simple pixel differences. Our proposed algorithm uses regression to normalize the variations of intensity offset and gain between compared registered frames. A statistical criterion is used to calculate the threshold for the difference between normalized intensities of two frames. The algorithm for finding the differences between frames is also used to create a bad pixel mask either on- or offline. This mask is essential for the reduction of false detection rates. Our experiments show that this approach produces good results and can be used for detection of small, low-contrast targets in high dynamic range IR data. The proposed algorithm also produces good results for detecting moving targets in cases when objects are occluded by sparse vegetation.
© 2015 Society of Photo-Optical Instrumentation Engineers (SPIE)
Dmitriy Korchev, Dmitriy Korchev, Hyukseong Kwon, Hyukseong Kwon, Yuri Owechko, Yuri Owechko, } "Detecting small, low-contrast moving targets in infrared video produced by inconsistent sensor with bad pixels," Optical Engineering 54(11), 113102 (3 November 2015). https://doi.org/10.1117/1.OE.54.11.113102 . Submission:


Evaluation of tracking in video sequences
Proceedings of SPIE (February 20 2001)
Automatic target detection in cluttered IR images
Proceedings of SPIE (July 06 1998)
Analysis of a proposed infrared sensor focal plane
Proceedings of SPIE (September 15 1992)
Real-time acquisition of small target features in IR image
Proceedings of SPIE (October 21 1993)

Back to Top