TY - GEN
T1 - Robust illumination-invariant tracking algorithm based on HOGs
AU - Miramontes-Jaramillo, Daniel
AU - Kober, Vitaly
AU - Díaz-Ramírez, Víctor H.
N1 - Publisher Copyright:
© 2015 SPIE.
PY - 2015
Y1 - 2015
N2 - Common tracking systems are usually affected by environmental and technical interferences such as non-uniform illumination, sensors' noise, geometrical scene distortion, etc. Among these issues, the former is particularly interesting because it destroys important spatial characteristics of objects in observed scenes. We propose a two-step tracking algorithm: first, preprocessing locally normalizes the illumination difference between the target object and observed frames; second, the normalized object is tracked by means of a designed template structure based on histograms of oriented gradients and kinematic prediction model. The algorithm performance is tested in terms of recognition and localization errors in real scenarios. In order to achieve high rate of the processing, we use GPU parallel processing technologies. Finally, our algorithm is compared with other state-of-the-art trackers.
AB - Common tracking systems are usually affected by environmental and technical interferences such as non-uniform illumination, sensors' noise, geometrical scene distortion, etc. Among these issues, the former is particularly interesting because it destroys important spatial characteristics of objects in observed scenes. We propose a two-step tracking algorithm: first, preprocessing locally normalizes the illumination difference between the target object and observed frames; second, the normalized object is tracked by means of a designed template structure based on histograms of oriented gradients and kinematic prediction model. The algorithm performance is tested in terms of recognition and localization errors in real scenarios. In order to achieve high rate of the processing, we use GPU parallel processing technologies. Finally, our algorithm is compared with other state-of-the-art trackers.
KW - GPU implementation
KW - Tracking
KW - non-uniform illumination
KW - oriented gradient histograms
UR - http://www.scopus.com/inward/record.url?scp=84951299317&partnerID=8YFLogxK
U2 - 10.1117/12.2186424
DO - 10.1117/12.2186424
M3 - Contribución a la conferencia
AN - SCOPUS:84951299317
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Applications of Digital Image Processing XXXVIII
A2 - Tescher, Andrew G.
A2 - Tescher, Andrew G.
PB - SPIE
T2 - Applications of Digital Image Processing XXXVIII
Y2 - 10 August 2015 through 13 August 2015
ER -