Robust automatic target tracking based on a Bayesian ego-motion compensation framework for airborne FLIR imagery

Automatic target tracking in airborne FLIR imagery is currently a challenge due to the camera ego-motion. This phenomenon distorts the spatio-temporal correlation of the video sequence, which dramatically reduces the tracking performance. Several works address this problem using ego-motion compensation strategies. They use a deterministic approach to compensate the camera motion assuming a specific model of geometric transformation. However, in real sequences a specific geometric transformation can not accurately describe the camera ego-motion for the whole sequence, and as consequence of this, the performance of the tracking stage can significantly decrease, even completely fail. The optimum transformation for each pair of consecutive frames depends on the relative depth of the elements that compose the scene, and their degree of texturization. In this work, a novel Particle Filter framework is proposed to efficiently manage several hypothesis of geometric transformations: Euclidean, affine, and projective. Each type of transformation is used to compute candidate locations of the object in the current frame. Then, each candidate is evaluated by the measurement model of the Particle Filter using the appearance information. This approach is able to adapt to different camera ego-motion conditions, and thus to satisfactorily perform the tracking. The proposed strategy has been tested on the AMCOM FLIR dataset, showing a high efficiency in the tracking of different types of targets in real working conditions.

[1]  J. Aggarwal,et al.  Detecting moving objects in airborne forward looking infra-red sequences , 1999, Proceedings IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications (CVBVS'99).

[2]  Luis Salgado,et al.  Target Detection Through Robust Motion Segmentation and Tracking Restrictions in Aerial Flir Images , 2007, 2007 IEEE International Conference on Image Processing.

[3]  Abdullah Bal,et al.  Automatic target tracking in FLIR image sequences using intensity variation function and template modeling , 2005, IEEE Transactions on Instrumentation and Measurement.

[4]  Junshan Li,et al.  Mean Shift Based Target Tracking in FLIR Imagery via Adaptive Prediction of Initial Searching Points , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[5]  Abdullah Bal,et al.  Improved Multiple Target Tracking via Global Motion Compensation and Optoelectronic Correlation , 2007, IEEE Transactions on Industrial Electronics.

[6]  J.P. Havlicek,et al.  Infrared Target Tracking with AM-FM Consistency Checks , 2008, 2008 IEEE Southwest Symposium on Image Analysis and Interpretation.

[7]  Luis Salgado,et al.  Automatic aerial target detection and tracking system in airborne FLIR images based on efficient target trajectory filtering , 2007, SPIE Defense + Commercial Sensing.

[8]  Yiannis Aloimonos,et al.  A Probabilistic Notion of Correspondence and the Epipolar Constraint , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[9]  Michal Irani,et al.  Video indexing based on mosaic representations , 1998, Proc. IEEE.

[10]  Stan Birchfield,et al.  Spatial Histograms for Region‐Based Tracking , 2007 .

[11]  A. Yilmaz,et al.  TARGET-TRACKING IN FLIR IMAGERY USING MEAN-SHIFT AND GLOBAL MOTION COMPENSATION , 2001 .

[12]  Mubarak Shah,et al.  Target tracking in airborne forward looking infrared imagery , 2003, Image Vis. Comput..

[13]  Jake K. Aggarwal,et al.  MODEEP: a motion-based object detection and pose estimation method for airborne FLIR sequences , 2000, Machine Vision and Applications.

[14]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[15]  Mansoor Shafi,et al.  Quick Simulation: A Review of Importance Sampling Techniques in Communications Systems , 1997, IEEE J. Sel. Areas Commun..

[16]  Luis Salgado,et al.  Aerial Moving Target Detection Based on Motion Vector Field Analysis , 2007, ACIVS.

[17]  Guoliang Fan,et al.  Target Tracking with Online Feature Selection in FLIR Imagery , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[19]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[20]  Joni-Kristian Kämäräinen,et al.  Invariance properties of Gabor filter-based features-overview and applications , 2006, IEEE Transactions on Image Processing.

[21]  Tang Shuo,et al.  Target Detection and Tracking in Forward-looking Infrared Image Sequences Using Multiscale Morphological Filters , 2007, 2007 5th International Symposium on Image and Signal Processing and Analysis.

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

[23]  Rama Chellappa,et al.  A multi-fractal formalism for stabilization, object detection and tracking in FLIR sequences , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).