ACIVS 2007: Advanced Concepts for Intelligent Vision Systems pp 990-1001 | Cite as
Aerial Moving Target Detection Based on Motion Vector Field Analysis
Abstract
An efficient automatic detection strategy for aerial moving targets in airborne forward-looking infrared (FLIR) imagery is presented in this paper. Airborne cameras induce a global motion over all objects in the image, that invalidates motion-based segmentation techniques for static cameras. To overcome this drawback, previous works compensate the camera ego-motion. However, this approach is too much dependent on the quality of the ego-motion compensation, tending towards an over-detection. In this work, the proposed strategy estimates a robust motion vector field, free of erroneous vectors. Motion vectors are classified into different independent moving objects, corresponding to background objects and aerial targets. The aerial targets are directly segmented using their associated motion vectors. This detection strategy has a low computational cost, since no compensation process or motion-based technique needs to be applied. Excellent results have been obtained over real FLIR sequences.
Keywords
Motion Vector Target Detection Global Motion Laplacian Distribution Background ObjectPreview
Unable to display preview. Download preview PDF.
References
- 1.Strehl, A., Aggarwal, J.K.: Detecting moving objects in airborne forward looking infra-red sequences. In: Proc. IEEE Workshop on Computer Vision Beyond Visible Spectrum, pp. 3–12. IEEE Computer Society Press, Los Alamitos (1999)CrossRefGoogle Scholar
- 2.Strehl, A., Aggarwal, J.K.: MODEEP: a Motion-Based Object Detection and Pose Estimation Method for Airborne FLIR Sequences. Machine Vision and Applications 11(6), 267–276 (2000)CrossRefGoogle Scholar
- 3.Estalayo, E., Salgado, L., Jaureguizar, F., García, N.: Efficient image stabilization and automatic target detection in aerial FLIR sequences. Automatic Target Recognition XVI. In: Proc. of the SPIE, vol. 6234 (2006)Google Scholar
- 4.Seok, H.D., Lyou, J.: Digital Image Stabilization using Simple Estimation of the Rotational and Translational Motion. Acquisition, Tracking and Pointing XIX. Proc. of SPIE 5810, 170–181 (2005)CrossRefGoogle Scholar
- 5.Yilmaz, A., Shafique, K., Lobo, N., Li, X., Olson, T., Shah, M.A.: Target-tracking in FLIR imagery using mean-shift and global motion compensation. In: Proc. IEEE Workshop Computer Vision Beyond Visible Spectrum, IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
- 6.Yilmaz, A., Shafique, K., Shah, M.: Target Tracking in Airborne Forward Looking Infrared Imagery. Image and Vision Computing Journal 21(7), 623–635 (2000)CrossRefGoogle Scholar
- 7.Meier, W., Stein, H.: Estimation of object and sensor motion in infrared image sequences. In: Proc. IEEE. Int. Conf. on Image Processing, vol. 1, pp. 568–572. IEEE, Los Alamitos (1994)CrossRefGoogle Scholar
- 8.Wechsler, H., Duric, Z., Fayin, L., Cherkassky, V.: Motion estimation using statistical learning theory. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(4), 466–478 (2004)CrossRefGoogle Scholar
- 9.Stewart, C.V.: Robust parameter estimation in computer vision. SIAM Reviews 41(3), 513–537 (1999)MATHCrossRefGoogle Scholar
- 10.Meer, P., Stewart, C.V., Tyler, D.: Robust computer vision: an interdisciplinary challenge. Computer Vision and Image Understanding 78(1), 1–7 (2000)CrossRefGoogle Scholar
- 11.Rosin, P.: Edges: Saliency measures and automatic thresholding. Machine Vision and Applications 9(4), 139–159 (1999)CrossRefGoogle Scholar
- 12.Srivastava, A., Lee, A.B., Simoncelli, E.P., Zhu, S.C.: On Advances in Statistical Modeling of Natural Images. Journal of Mathematical Imaging and Vision 18, 17–33 (2003)MATHCrossRefGoogle Scholar