Visual attention based target detection and tracking for UAVs

With the increasing demand for the small unmanned aerial vehicles (UAVs), researches for target detection and tracking on a small UAV platform are of important significance. In this paper, a detection method based on the bionic visual attention is proposed. In this method, the bottom-up algorithm and up-bottom algorithm are combined. Intensity and color are the two main features to get the saliency map (SM). Regions of interest are obtained by adaptive threshold segmentation and the SM processing. The histogram of oriented gradients is used to derive a descriptor for a bounding box for each target. The support vector machine is used to obtain the classifier for exacting the targets by learning and training the descriptors. The target location is acquired via vision-based measurement. This method can effectively reduce the influence of illumination, motion blur, similar-color objects and complex background, and is successfully applied on a small UAV platform for tracking the ground targets.

[1]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  C. McCollough.  Color Adaptation of Edge-Detectors in the Human Visual System , 1965, Science.

[3]  Felipe Martins,et al.  A vision-based line following strategy for an autonomous UAV , 2015, 2015 12th International Conference on Informatics in Control, Automation and Robotics (ICINCO).

[4]  He Jian.  Wiener Filtering Image Restoration Technology Research and Improvement , 2012 .

[5]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[6]  Jay Pratt,et al.  Visual attention to features by associative learning , 2014, Cognition.

[7]  Tor Arne Johansen,et al.  Automatic detection, classification and tracking of objects in the ocean surface from UAVs using a thermal camera , 2015, 2015 IEEE Aerospace Conference.

[8]  Tamir Libel,et al.  Unmanned Aerial Vehicles in the Israel Defense Forces , 2015 .

[9]  Alex Smola,et al.  Kernel methods in machine learning , 2007, math/0701907.

[10]  George J. Vachtsevanos,et al.  UAV Applications: Introduction , 2015 .

[11]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[12]  Li Wan.  A Survey of Visual Attention Based Methods for Object Tracking , 2014 .

[13]  Geoff J. M. Parker,et al.  Characterizing function–structure relationships in the human visual system with functional MRI and diffusion tensor imaging , 2004, NeuroImage.

[14]  Nuno Vasconcelos,et al.  Decision-Theoretic Saliency: Computational Principles, Biological Plausibility, and Implications for Neurophysiology and Psychophysics , 2009, Neural Computation.

[15]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..