[Deep Thermal Imaging]

　 　

Information

This README.md is modified on 6th June 2019.
Author: Youngjun Cho

• UCL Computer Science
• Email: [email protected]
  

Original page: https://github.com/deepneuroscience/DeepThermalImaging

　 　

Requirement

Matlab (version>2012)

MatConvNet (https://github.com/vlfeat/matconvnet): Deep CNN Framework for Matlab users.
 

　 　

Quick Instruction to install MatConvNet

git clone https://github.com/vlfeat/matconvnet.git
　 　
(On the command window of MATLAB)
close all
clc
mex -setup C
mex -setup C++　 　
(Detailed instruction is available at http://www.vlfeat.org/matconvnet/)
　 　

　 　

Quick Instruction to use the Deep Thermal Imaging API

The first thing you need to do is to put the Deep Thermal Imaging API codes in the 'examples' directory.
(e.g., c:\your_directory\matconvnet\examples\DeepThermalImagingAPI*")

You can easily get example command lines by typing the below on the Matlab command window:

help deep_thermal_imaging_training_and_testing
help deep_thermal_imaging_utils/buildconfusionmatrix
help deep_thermal_imaging_utils/testingasample
help deep_thermal_imaging_utils/growingdataset
help deep_thermal_imaging_utils/simpleDRQ
(Detailed instruction is available at http://youngjuncho.com/2018/deepthermalimagingapi/)

　 　

Data sets: http://youngjuncho.com/datasets/

　 　

Citation:

　 　 Youngjun Cho, Nadia Bianchi-Berthouze, Nicolai Marquardt, and Simon J. Julier. "Deep Thermal Imaging: Proximate Material Type Recognition in the Wild through Deep Learning of Spatial Surface Temperature Patterns." In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. ACM, 2018.

@inproceedings{youngjunDeepBreath,  
  title={Deep Thermal Imaging: Proximate Material Type Recognition in the Wild through Deep Learning of Spatial Surface Temperature Patterns.},  
  author={Youngjun Cho, Nadia Bianchi-Berthouze, Nicolai Marquardt, Simon J. Julier},  
  proceedingtitle={In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. ACM},  
  year={2018}  
}  

　 　

Q&A

If you have any questions, feel free to contact us / http://youngjuncho.com .