Small Target Detection From Image Sequences Using Improved Recursive Max-Mean Filter

摘要

This paper deals with the problem of detection of low-observable small-targets from sequence of infrared images against structural background and non-stationary clutter. Detection of low-observable small-targets from a sequence of infrared images is an important research area for image processing applications, but the difficulties in detecting small -targets arise from the fact that they are not easily discernable from the background noise. In this paper, we present a improved Recursive Max-Mean filter(RMMF) in preserving the edge information and suppressing the isolated points which helps in detecting small moving targets from noises image sequence. Since all the procedures contained in this method can be implemented by fully parallel algorithm, real-time processing is possible for image sequences at high frame rates. The detection algorithm has been tested on a number of real-world image sequences and results obtained are satisfactory.