Object tracking based on the somatosensory system

In this paper, a new way for a robust object tracking which based on somatosensory system tracking process is presented. When an object moves on the skin, it stimulates sensory receptors. Then, human can define object location at any time as well as its path. This perception is made by stimulation of the mechanoceptors. In this proposed approach, initially selected points named motionreceptors are fixed on the scene. Firstly, the tracker detects moving objects and represents them as points. Secondly, the tracker finds an association between objects and new detected zones. This association is done by calculating the degree of similarity between stimulated motionreceptors by new zones and objects. Then, it attributes new zones detected in motion to objects. Stimulated motionreceptors are points of the scene that are linked by a segment with points of objects or zones in the Delaunay triangulation. Finally, it updates objects position each time. Our approach was applied to some videos.

[1]  Tatjana Seizova-Cajic,et al.  Somatosensory Space Abridged: Rapid Change in Tactile Localization Using a Motion Stimulus , 2014, PloS one.

[2]  Anurag Singh,et al.  Object Tracking Using Frame Differencing and Template Matching , 2012 .

[3]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[4]  Eric Debreuve,et al.  Méthode de suivi d`objets basée sur des trajectoires temporelles de points d`intérêt , 2007 .

[5]  T. Remi,et al.  Probabilistic Matching Algorithm for Keypoint Based Object Tracking Using a Delaunay Triangulation , 2007, Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '07).

[6]  Emilio Maggio,et al.  Video Tracking - Theory and Practice , 2011 .

[7]  Alper Yilmaz,et al.  Kernel-based object tracking using asymmetric kernels with adaptive scale and orientation selection , 2011, Machine Vision and Applications.

[8]  János Pach.  New Trends in Discrete and Computational Geometry , 2013 .

[9]  H. Nicolas,et al.  Video Surveillance Traffic Analysis Using Scene Geometry , 2010, 2010 Fourth Pacific-Rim Symposium on Image and Video Technology.

[10]  Toby Howard,et al.  Real-time markerless human body tracking using colored voxels and 3D blobs , 2004, Third IEEE and ACM International Symposium on Mixed and Augmented Reality.

[11]  Mark de Berg,et al.  Computational geometry: algorithms and applications , 1997 .

[12]  Lixin Fan,et al.  A feature-based object tracking approach for realtime image processing on mobile devices , 2010, 2010 IEEE International Conference on Image Processing.

[13]  Karan Gupta,et al.  Implementation of an Automated Single Camera Object Tracking System Using Frame Differencing and Dynamic Template Matching , 2007, SCSS.

[14]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[15]  Mahdi Koohi,et al.  An algorithm for object tracking based on adaptive triangle shape mesh estimation method , 2011, 2011 24th Canadian Conference on Electrical and Computer Engineering(CCECE).

[16]  Jinwei Jiang,et al.  Persistent tracking of static scene features using geometry , 2014, Comput. Vis. Image Underst..

[17]  C. Spence,et al.  Skin and Touch , 2014 .

[18]  Sayoko Ogura,et al.  β2-Adrenergic Receptor-Dependent Attenuation of Hypoxic Pulmonary Vasoconstriction Prevents Progression of Pulmonary Arterial Hypertension in Intermittent Hypoxic Rats , 2014, PloS one.

[19]  Zu Kim,et al.  Realtime Obstacle Detection and Tracking Based on Constrained Delaunay Triangulation , 2006, 2006 IEEE Intelligent Transportation Systems Conference.