Real-time head tracking by saccadic exploration and Gabor decomposition

Author(s):  
F. Smeraldi ◽  
O. Carmona ◽  
J. Bigun
Keyword(s):  
2014 ◽  
Vol 609-610 ◽  
pp. 1532-1537
Author(s):  
Yong Jun Wang ◽  
Jing Shuo Xu ◽  
Lin Li

Head tracking technique plays an important role in the modern war. Because it is directly related to target capture rate. To adapt to rapid attitude position of the helmet, a novel real-time head tracking technology based on Micro-Electro-Mechanical Systems inertial navigation system (MEMS-INS) and Charge Coupled Device (CCD) is put forward. This method not only considers the spatial limitations of the helmet, but also takes into account the complementarity between inertial method and optical method. Firstly, the fundamental principle of head attitude measurement based on MEMS-INS/CCD is introduced. The state space model of the helmet attitude measurement is then built. In the end, feasibility of this method is validated by simulation. Simulation results show that head misalignment angle error can be estimated and reaches anticipated precision2 in 10 seconds. The helmet real-time tracking can be completed.


2015 ◽  
Vol 3 ◽  
pp. 829-836 ◽  
Author(s):  
Ilja T. Feldstein ◽  
Alexander Güntner ◽  
Klaus Bengler

Author(s):  
JASON Z. ZHANG ◽  
Q. M. JONATHAN WU ◽  
WILLIAM A. GRUVER

This paper presents a method for tracking a human head based on the integration of camera saccade and chromatic shape fitting, which are implemented as functional modules in an active tracking system. Head motion is detected in the saccade module by extracting edges from two successive images. The position of the head in the current image is approximated as the centroid of the apparition formed by the moving edges of the target. A visual position cue is used to drive a pan/tilt camera to perform real-time saccade keeping the target in the foveal area in the image. The shape-fitting module is invoked to extract more information from the target. The shape of the target is modeled as an ellipse whose position, orientation and size are dynamically determined by shape fitting, and implemented with a color registration technique. In the proposed method, quasi real-time pursuit is achieved using a Pentium II computer in an uncontrolled environment with arbitrary relative motion between the target and camera.


2015 ◽  
Vol 9 (2) ◽  
pp. 141-151 ◽  
Author(s):  
Laura Montanini ◽  
Enea Cippitelli ◽  
Ennio Gambi ◽  
Susanna Spinsante

Sign in / Sign up

Export Citation Format

Share Document