Sobriety Testing Based on Thermal Infrared Images Using Convolutional Neural Networks

AbstractConvolutional neural networks were used for multiclass segmentation in thermal infrared face analysis. The principle is based on existing image-to-image translation approaches, where each pixel in an image is assigned to a class label. We show that established networks architectures can be trained for the task of multiclass face analysis in thermal infrared. Created class annotations consisted of pixel-accurate locations of different face classes. Subsequently, the trained network can segment an acquired unknown infrared face image into the defined classes. Furthermore, face classification in live image acquisition is shown, in order to be able to display the relative temperature in real-time from the learned areas. This allows a pixel-accurate temperature face analysis e.g. for infection detection like Covid-19. At the same time our approach offers the advantage of concentrating on the relevant areas of the face. Areas of the face irrelevant for the relative temperature calculation or accessories such as glasses, masks and jewelry are not considered. A custom database was created to train the network. The results were quantitatively evaluated with the intersection over union (IoU) metric. The methodology shown can be transferred to similar problems for more quantitative thermography tasks like in materials characterization or quality control in production.

Download Full-text

Automatic target recognition fuzzy system for thermal infrared images

[Proceedings 1993] Second IEEE International Conference on Fuzzy Systems ◽

10.1109/fuzzy.1993.327531 ◽

2002 ◽

Cited By ~ 4

Author(s):

C. Perneel ◽

M. de Mathelin ◽

M. Acheroy

Keyword(s):

Fuzzy System ◽

Target Recognition ◽

Thermal Infrared ◽

Automatic Target Recognition ◽

Infrared Images ◽

Thermal Infrared Images

Download Full-text

Transformations in the Photogrammetric Co-Processing of Thermal Infrared Images and RGB Images

Sensors ◽

10.3390/s21155061 ◽

2021 ◽

Vol 21 (15) ◽

pp. 5061

Author(s):

Adam Dlesk ◽

Karel Vach ◽

Karel Pavelka

Keyword(s):

Structure From Motion ◽

Thermal Infrared ◽

Processing Method ◽

Spatial Transformation ◽

Infrared Images ◽

Low Resolution ◽

Thermal Infrared Images ◽

Rgb Images ◽

Motion Method

The photogrammetric processing of thermal infrared (TIR) images deals with several difficulties. TIR images ordinarily have low-resolution and the contrast of the images is very low. These factors strongly complicate the photogrammetric processing, especially when a modern structure from motion method is used. These factors can be avoided by a certain co-processing method of TIR and RGB images. Two of the solutions of co-processing were suggested by the authors and are presented in this article. Each solution requires a different type of transformation–plane transformation and spatial transformation. Both types of transformations are discussed in this paper. On the experiments that were performed, there are presented requirements, advantages, disadvantages, and results of the transformations. Both methods are evaluated mainly in terms of accuracy. The transformations are presented on suggested methods, but they can be easily applied to different kinds of methods of co-processing of TIR and RGB images.

Download Full-text

Applications of Satellite Thermal Infrared Images for Monitoring North Water during the Periods of Polar Darkness

Journal of Glaciology ◽

10.3189/s0022143000015276 ◽

1980 ◽

Vol 25 (93) ◽

pp. 425-438

Author(s):

B. Dey

Keyword(s):

Satellite Images ◽

Open Water ◽

Thermal Infrared ◽

Water Area ◽

Infrared Images ◽

Baffin Bay ◽

The North ◽

Thermal Infrared Images ◽

North Water

AbstractThe study reported here illustrates the unique value of NOAA thermal infrared (TIR) images for monitoring the North Water area in Smith Sound and northern Baffin Bay during the periods of polar darkness. Wintertime satellite images reveal that, during the months of December through February, open water and thin ice occur in a few leads and polynyas. However, in March, the areas of open water and thin ice decrease to a minimum with a consequent higher concentration of ice. Two ice dams, in northern Kennedy Channel and in northern Smith Sound, regulate the flow of ice into northern Baffin Bay and also determine the areal variations of open water and thin ice in Smith Sound.

Download Full-text