Human Tracking in Thermal Imaging

Hits: 0
Research Area: Uncategorized
Status: Not started  
Members:  
 
Funded by: Fundação para a Ciência e a Tecnologia Funding: 0.00 EUR
Description:

ACKNOWLEDGEMENT:

This project module is the part of the FCT (Fundação para a Ciência e Tecnologia) financed project "BioRec - Non-Cooperative Multimodal Biometric Recognition" (PTDC/EIA/69106/2006).


INTRODUCTION:

Recent advances in digital storage and video hardware has lead to new applications like surveillance, advance driver assistance system, non-cooperative biometrics, virtual reality etc. The cheaper cost and easy availability of imaging modality has attracted researcher’s attention in motion tracking system to be applied in a number of applications.

The purpose of this project is to research the approaches for motion tracking of human beings using thermal imaging only. Emphasis is placed on using only thermal imaging using infrared cameras. Recently, there have been some attempts to include the thermal imaging in applications like face recognition and motion tracking in addition to the visible cameras. However, if only one of the modalities is used and reliable results are obtained with it, cost saving and higher processing speed would be the benefits for the system. In applications like outdoor surveillance, thermal imaging can play vital role in identifying persons and tracking each of them. This fact has primly motivated us to use only thermal imaging for motion tracking of human beings. Another advantage regarding thermal imaging lies in the fact that it cannot sense shadow or light illumination, which is normally the bottleneck in most of the motion tracking based on visible camera. Thus, making it more suitable for motion tracking in out-door environment in day time as well as night time, where shadows and variable illuminations are dominating factors making tracking more difficult.

On the contrary, clutters like cool body, variation in temperature across same subjects, blowing winds with different temperature gradients and person overlap while crossing each other, put challenges in thermal imaging and will have to be handled intelligently in order to obtain the efficient performance from motion tracking system using only single imaging modality like thermal imaging.


PUBLICATIONS:

C. N. Padole , L. A. Alexandre, ”Wigner Distribution based Motion Tracking of Human Beings using Thermal Imaging “,in IEEE CVPR 10, OTCBVS 10 workshop , July 2010, San Francisco ( USA) , [PDF Paper], [PDF Presentation] [BibTex]


DATASET:

[1] - Link for third party DATASET: http://www.cse.ohio-state.edu/otcbvs-bench/

[2] - Annotation Tools and Ground Truth Data [More Information...].

 

INTERNAL PRESENTATIONS:

To be coming soon...

 

SUMMARY:

To be coming soon...