Background modeling and target segmentation via modified Kalman filtering

In target detection and tracking applications with imagery data taken from a moving camera platform, it is necessary to segment potential targets in each image frame. This is typically done by preprocessing individual images to exploit some known attribute about the data. Often these methods make many false detections, particularly in the presence of additive noise, and the results thus require significant post-processing. A means of estimating the background in the imagery sequence under the formalism of the Kalman filter is suggested. This background estimate is then used to recast the segmentation problem as one of outlier detection, and the result of segmentation is used to modify the filter update. Ways of making the technique computationally benign are discussed. The technique is used to analyse a simulated image sequence, and the performance is compared to that of a single-frame background-estimation technique. The feasibility of target segmentation via background tracking is thus demonstrated.

[1]  John K. Goutsias,et al.  Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators , 2004, J. Electronic Imaging.

[2]  J. J. Gerbrands,et al.  A fast Kalman filter for images degraded by both blur and noise , 1983 .

[3]  Marc Acheroy,et al.  Long-range automatic detection of small targets in sequences of noisy thermal infrared images , 1994, Defense, Security, and Sensing.

[4]  Derek R. Magee,et al.  Tracking multiple vehicles using foreground, background and motion models , 2004, Image Vis. Comput..

[5]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[6]  Songde Ma,et al.  A Novel Probability Model for Background Maintenance and Subtraction , 2002 .

[7]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[8]  Isaac Cohen,et al.  Detection and Tracking of Objects in Airborne Video Imagery , 2003 .

[9]  David B. Reiss Spatial signal processing for infrared detection , 1994, Defense, Security, and Sensing.

[10]  Daniel P. Huttenlocher,et al.  Scene modeling for wide area surveillance and image synthesis , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Olaf Munkelt,et al.  Adaptive Background Estimation and Foreground Detection using Kalman-Filtering , 1995 .

[12]  J. Mooney,et al.  Point target detection in consecutive frame staring infrared imagery with evolving cloud clutter , 1995 .

[13]  Tracie C. Moore,et al.  Performance of various background estimation and object detection algorithms on real flight test interceptor seeker data , 1999, Optics & Photonics.

[14]  Michael Elad,et al.  Super-Resolution Reconstruction of Image Sequences , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Mark J. T. Smith,et al.  Sequential digital filters for fast detection of targets in FLIR image data , 1997, Defense, Security, and Sensing.

[16]  P. Anandan,et al.  Efficient representations of video sequences and their applications , 1996, Signal Process. Image Commun..

[17]  Michael Elad,et al.  Superresolution restoration of an image sequence: adaptive filtering approach , 1999, IEEE Trans. Image Process..