Global registration and moving objects detection in noisy airborne image sequences

Abstract

This paper presents a method for registration of noisy airborne images for the purpose of the detection of moving objects. A new iterative algorithm is developed and presented for the correction of geometrical distortion caused by global motion in a scene. A binary hypotheses test is subsequently established using a likelihood ratio test (LRT) to classify the pixels in the corrected image as either locally moving (object motion) or not moving (stationary). The paper also incorporates the use of the Expectation-Maximization method for estimation of statistical image features needed by the LRT. We use and present experiments with real image sequences to validate the analytical developments. C 2010 Society of Photo-Optical Instrumentation Engineers.