<title>Optical flow techniques for moving target detection</title>

Abstract

We present an evaluation of several pixel level optical flow techniques, for flow computation accuracy. Flow accuracy is characterized with respect to spatio-temporal image characteristics relevant to moving target detection. Results of flow computation and target detection are presented for infrared (8 -12 jtm) imagery.

Motion estimation for moving target detection

“…The motion estimates have to be further processed to produce the final output of moving target detection: a target list containing centroid and bounding box information of detected targets. For stationary sensors (including sensors with drift), optical flow discontinuity detection and histogram segmentation approaches have been used by Russo, et al [10] to demonstrate the feasibility of performing moving target detection. These techniques provide only a visual output, and not an explicit target list.…”

Detection of small moving targets in staring images sequence with complex background and low contrast

“…3-D Matched Filtering 4,5 , Sequential Hypothesis Testing 6 and Neural Networks 7 are also detecting algorithms based on images sequence, and their computer simulating results are smart, however these algorithms also have a large calculating quantity and their detecting performance is easy influenced by noise. Optical Flow techniques [8][9][10][11][12][13][14][15] based on either gradient constancy or brightness constancy constraints have been used for more effective exploitation of the motion discriminant of targets.…”