SMALL MOVING OBJECT DETECTION FROM INFRA-RED SEQUENCES

Abstract

In military and civil applications it is of utmost importance to detect and identify targets from Infra-Red (IR) sequences. Usually the targets of interest are of small size and moving with great velocity. In addition, IR sequences are extremely noisy due to rampant system noise incurred by the sensing instrument and the environment. In this paper, we develop a method which can effectively detect and identify targets of interest from noisy IR sequences through manipulations in the temporal, spectral, and spatial domains. With this method, first a bandstop filtering in the DCT transform domain is conducted in order to remove noises, especially system ones. Next candidate target locations are declared through a spectral bandpassing for temporal pixel processes, where by taking advantage of the fact that targets of interest are fast moving the background and random noises are largely removed. The estimated targets of interest for each IR frame are further refined after a post-processing step in the spatial domain. The final targets of interest are then declared after a consistency check-up along the temporal dimension by use of an adaptive Hough transform. Experimental results based on this proposed method suggested encouraging performances.