Object Tracking Using High Resolution Satellite Imagery

High resolution multispectral satellite images with multi-angular look capability have tremendous potential applications. We present an object tracking algorithm that includes moving object estimation, target modeling, and target matching three-step processing. Potentially moving objects are first identified on the time-series images. The target is then modeled by extracting both spectral and spatial features. In the target matching procedure, the Bhattacharyya distance, histogram intersection, and pixel count similarity are combined in a novel regional operator design. Our algorithm has been tested using a set of multi-angular sequence images acquired by the WorldView-2 satellite. The tracking performance is analyzed by the calculation of recall, precision, and F1 score of the test. In this study, we have demonstrated the capability of object tracking in a complex environment with the help of high resolution multispectral satellite imagery.

[1]  John Kerekes,et al.  Vehicle tracking with multi-temporal hyperspectral imagery , 2006, SPIE Defense + Commercial Sensing.

[2]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  G. Seetharaman,et al.  Wide-Area Persistent Airborne Video: Architecture and Challenges , 2011 .

[4]  Alexander Dekhtyar,et al.  Information Retrieval , 2018, Lecture Notes in Computer Science.

[5]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[6]  Alan D. Raisanen,et al.  Dynamic scene generation, multimodal sensor design, and target tracking demonstration for hyperspectral/polarimetric performance-driven sensing , 2010, Defense + Commercial Sensing.

[7]  Guna Seetharaman,et al.  Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video , 2010, 2010 13th International Conference on Information Fusion.

[8]  J. Leitloff,et al.  Automatic traffic monitoring based on aerial image sequences , 2008, Pattern Recognition and Image Analysis.

[9]  Richard Bamler,et al.  Detection and velocity estimation of moving vehicles in high-resolution spaceborne synthetic aperture radar data , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Harpreet S. Sawhney,et al.  Vehicle detection and tracking in wide field-of-view aerial video , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .

[12]  Fabio Pacifici,et al.  On the relative predictive value of the new spectral bands in the WorldWiew-2 sensor , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[13]  Antony K. Liu,et al.  Wavelet analysis of satellite images for coastal watch , 1997 .

[14]  William J. Emery,et al.  Spatial classification of WorldView-2 multi-angle sequence , 2011, 2011 Joint Urban Remote Sensing Event.

[15]  Uwe Stilla,et al.  Theme issue: “Airborne and spaceborne traffic monitoring” , 2006 .

[16]  Carmen J. Carrano.  Ultra-scale vehicle tracking in low spatial resolution and low frame-rate overhead video , 2009, Optical Engineering + Applications.

[17]  Isabella Szottka,et al.  Tracking multiple vehicles in airborne image sequences of complex urban environments , 2011, 2011 Joint Urban Remote Sensing Event.

[18]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[19]  Kil Woo Chung,et al.  Concurrent use of satellite imaging and passive acoustics for maritime domain awareness , 2010, 2010 International WaterSide Security Conference.

[20]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.