Visual tracker fusion and outlier detection on thermal image sequences

2018 ◽  
Author(s):  
Sebastian Thome ◽  
Norbert Scherer-Negenborn ◽  
Michael Arens
Keyword(s):  
Outlier Detection ◽  
Thermal Image ◽  
Image Sequences ◽  
Tracker Fusion

Robustified smoothing for enhancement of thermal image sequences affected by clouds

2015 ◽  
Author(s):  
Paolo Addesso ◽  
Maurizio Longo ◽  
Antonino Maltese ◽  
Rita Montone ◽  
Rocco Restaino ◽  
...  
Keyword(s):  
Thermal Image ◽  
Image Sequences

Thermal image sequences for natural background modeling

1993 ◽  
Author(s):  
Jan S. de Vries ◽  
Henk A. Lensen ◽  
Abraham J. Maas
Keyword(s):  
Background Modeling ◽  
Thermal Image ◽  
Image Sequences ◽  
Natural Background

Multi-tracker fusion via adaptive outlier detection

2018 ◽  
Vol 78 (2) ◽  
pp. 2227-2250 ◽  
Author(s):  
Chao Xie ◽  
Ning Wang ◽  
Wengang Zhou ◽  
Weiping Li ◽  
Houqiang Li
Keyword(s):  
Outlier Detection ◽  
Tracker Fusion

scholarly journals Detection of lies by facial thermal imagery analysis

2017 ◽  
Vol 26 (44) ◽  
pp. 45
Author(s):  
Sebastián Bedoya-Echeverry ◽  
Hernán Belalcázar-Ramírez ◽  
Humberto Loaiza-Correa ◽  
Sandra Esperanza Nope-Rodríguez ◽  
Carlos Rafael Pinedo-Jaramillo ◽  
...  
Keyword(s):  
Blood Flow ◽  
Vision System ◽  
Lie Detection ◽  
Thermal Image ◽  
Image Sequences ◽  
Physical Contact ◽  
Artificial Vision ◽  
Physiological Changes ◽  
Alternative Technique ◽  
Flow Through

An artificial vision system is presented for lie detection by analyzing face thermal image sequences. This system represents an alternative technique to the polygraph. Some of its features are: 1) it has no physical contact with the examinee, 2) it is non-intrusive, 3) it has a potential for private use, and 4) it can simultaneously analyze several persons. The proposed system is based on the detection of physiological changes in temperature in the lacrimal puncta area caused by the subtle increase in blood flow through the nearby vascular network. These changes take place when anxiety appears as a consequence of deception. Thus, the system segments the periorbital area, and tracks consecutive frames using the Kanade-Lucas-Tomasi algorithm. The results show a success rate of 79.2 % in detecting lies using a simple classification based on the comparison between the estimated temperatures in control questions, and the rest of the interrogation procedure. The performance of this system is comparable with previous works, where cameras with better specifications were used.

Sign in / Sign up

Export Citation Format

Share Document