http://www02.smt.ufrj.br/~fusion/

http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm

http://www.fullvision.ru/monitoring/description_eng.php

https://www.researchgate.net/post/Does_anybody_know_an_internet_database_for_medical_thermal_images

Hi

Please check the following link. I believe it will help you.

https://www.flir.com/oem/adas/adas-dataset-form/

Regards

Md Sazal Miah thank you

Here is the thermal face dataset

https://lcas.lincoln.ac.uk/wp/research/data-sets-software/lcas-thermal-physiological-monitoring-dataset/

Bach Huynh thank you for much

Ayşen Özün Türkçetin Did you find another dataset? I also need thermal face dataset. If you have, please share. Thanks

Just found another one on Kaggle

https://www.kaggle.com/kpvisionlab/tufts-face-database-thermal-cropped?

Dear Ayşen Özün Türkçetin,

You can find in couple of university where they use for their research lab. Examples are, University of Notre Dame (UND)-USA, The Lavel University, KAIST (Korea advance institute of Science and Technology) and other good world institutes. Important dataset are given below.

Existing databases such as

(a) OTCBVS Benchmark Database

(b) KAIST Multispectral Pedestrian Dataset

(c) CASIA Night Gait Dataset ; and

(d) CASIA Infrared Night Gait Dataset ,

References:

[1] T. Bourlai, N. Kalka, B. Čukić, et al., "Ascertaining human identity in night environments", Book Chapter, Distributed Video Sensor Networks, London, England, Springer, pp. 451-467, 2011.

[2] D. Tan, et al., "Efficient Night Gait Recognition Based on Template Matching", in Pattern Recognition, ICPR 2006, 1.

Human Dataset-

The dataset may contain thermal images of humans captured in various scenarios while walking, running, or sneaking. The recordings used to be captured in the LWIR segment of the electromagnetic (EM) in various weather condition- clear, fog and rain at different distances from the camera, different body positions (upright, hunched) and movement speeds (regular walking, running). A data set can be created by using and combining images from existing data sets, capturing new images according to the defined scenarios that best fit the needs and research goals, and combining images from existing data sets and own recordings. Motion can be captured by a telephoto lens provides enough details to be used for recognizing individual activities (running, walking, hunched walking, hunched running, etc.) and for the gait recognition and identifying people by way of walking.

Animal Dataset-

The suitability of thermal imaging in combination with digital image processing to automatically detect a chicken (Gallus domesticus) and a rabbit (Oryctolagus cuniculus) in a grassland habitat. Throughout the different test scenarios, our study animals were detected with a high precision, although the most dense grass cover reduced the detection rate. We conclude that thermal imaging and digital imaging processing may be an important tool for the improvement of wildlife-friendly farming practices in the future. This dataset is useful for finding the nests of ground nesting bird species like grey partridge (Perdix perdix) or pheasant (Phasianus colchicus) are vulnerable to farming operations in their breeding habitat, whereas in mammals, the natural instinct of e.g., leverets of brown hare (Lepus europaeus) and fawns of roe deer (Capreolus capreolus) to lay low and still in the vegetation to avoid predators increase their risk of being killed or injured in farming operations.

References:

Kim Arild Steen 1, Andrés Villa-Henriksen, Ole Roland Therkildsen, Ole Green, Automatic Detection of Animals in Mowing Operations Using Thermal Cameras, DOI: 10.3390/s120607587

Face thermal Mask

Face recognition systems operating in the visible domain have reached a significant level of maturity which enables their wide commercial use. The main and most known databases which contain face images in the infrared spectrum are following:

a) Equinox -320×240-pixel images of 90 subjects;

b) SCFace -130 subjects and the total of 4160 images;

c) Carl Database– 160×120-pixel images of 41 persons;

d) Iris thermal/visible face database– 4228 pairs of 320×240-pixel images;

(e) University of Notre Dame (UND)– 320×240-pixel images of 241 subjects;

f) The Laval University thermal IR face motion database– 640 × 512-pixel images of 200 subjects.

g) Natural Visible and Infrared Facial Expression database (USTC-NVIE) – around 100 subjects with images of 320×240-pixel resolution

References

[1] Equinox Corp. Equinox Human Identification at a Distance Database. http://www.equinoxsensors. com/products/HID.html. (Accessed Mar. 31, 2017).

[2] Grgic, M., Delac, K., Grgic, S. (2011). SCface – surveillance cameras face database. Multimed. Tools Appl., 51, 863–879.

[3] Espinosa-Duró, V., Faundez-Zanuy, M., Mekyska, J., Carl Database. Signal Processing Laboratory. http://splab.cz/en/download/databaze/carl-database (2017). (Mar. 31, 2017)

Ashish

Dear Ayşen Özün Türkçetin,

You can find in couple of university where they use for their research lab. Examples are, University of Notre Dame (UND)-USA, The Lavel University, KAIST (Korea advance institute of Science and Technology) and other good world institutes. Important dataset are given below.

Existing databases such as

(a) OTCBVS Benchmark Database

(b) KAIST Multispectral Pedestrian Dataset

(c) CASIA Night Gait Dataset ; and

(d) CASIA Infrared Night Gait Dataset ,

References:

[1] T. Bourlai, N. Kalka, B. Čukić, et al., "Ascertaining human identity in night environments", Book Chapter, Distributed Video Sensor Networks, London, England, Springer, pp. 451-467, 2011.

[2] D. Tan, et al., "Efficient Night Gait Recognition Based on Template Matching", in Pattern Recognition, ICPR 2006, 1.

Human Dataset-

The dataset may contain thermal images of humans captured in various scenarios while walking, running, or sneaking. The recordings used to be captured in the LWIR segment of the electromagnetic (EM) in various weather condition- clear, fog and rain at different distances from the camera, different body positions (upright, hunched) and movement speeds (regular walking, running). A data set can be created by using and combining images from existing data sets, capturing new images according to the defined scenarios that best fit the needs and research goals, and combining images from existing data sets and own recordings. Motion can be captured by a telephoto lens provides enough details to be used for recognizing individual activities (running, walking, hunched walking, hunched running, etc.) and for the gait recognition and identifying people by way of walking.

Animal Dataset-

The suitability of thermal imaging in combination with digital image processing to automatically detect a chicken (Gallus domesticus) and a rabbit (Oryctolagus cuniculus) in a grassland habitat. Throughout the different test scenarios, our study animals were detected with a high precision, although the most dense grass cover reduced the detection rate. We conclude that thermal imaging and digital imaging processing may be an important tool for the improvement of wildlife-friendly farming practices in the future. This dataset is useful for finding the nests of ground nesting bird species like grey partridge (Perdix perdix) or pheasant (Phasianus colchicus) are vulnerable to farming operations in their breeding habitat, whereas in mammals, the natural instinct of e.g., leverets of brown hare (Lepus europaeus) and fawns of roe deer (Capreolus capreolus) to lay low and still in the vegetation to avoid predators increase their risk of being killed or injured in farming operations.

References:

Kim Arild Steen 1, Andrés Villa-Henriksen, Ole Roland Therkildsen, Ole Green, Automatic Detection of Animals in Mowing Operations Using Thermal Cameras, DOI: 10.3390/s120607587

Face thermal Mask

Face recognition systems operating in the visible domain have reached a significant level of maturity which enables their wide commercial use. The main and most known databases which contain face images in the infrared spectrum are following:

a) Equinox -320×240-pixel images of 90 subjects;

b) SCFace -130 subjects and the total of 4160 images;

c) Carl Database– 160×120-pixel images of 41 persons;

d) Iris thermal/visible face database– 4228 pairs of 320×240-pixel images;

(e) University of Notre Dame (UND)– 320×240-pixel images of 241 subjects;

f) The Laval University thermal IR face motion database– 640 × 512-pixel images of 200 subjects.

g) Natural Visible and Infrared Facial Expression database (USTC-NVIE) – around 100 subjects with images of 320×240-pixel resolution

References

[1] Equinox Corp. Equinox Human Identification at a Distance Database. http://www.equinoxsensors. com/products/HID.html. (Accessed Mar. 31, 2017).

[2] Grgic, M., Delac, K., Grgic, S. (2011). SCface – surveillance cameras face database. Multimed. Tools Appl., 51, 863–879.

[3] Espinosa-Duró, V., Faundez-Zanuy, M., Mekyska, J., Carl Database. Signal Processing Laboratory. http://splab.cz/en/download/databaze/carl-database (2017). (Mar. 31, 2017).

Ashish

Ashish Thakur thank you very much

Thank you Aysen.welcome.

https://blog.roboflow.com/thermal-infrared-dataset-computer-vision/

https://www.flir.com/oem/adas/adas-dataset-form/

http://www.fullvision.ru/monitoring/description_eng.php

http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm

http://www02.smt.ufrj.br/~fusion/

thank you Larbi Messaouda

Dear;

You can read it in the following link:

https://www.flir.com/oem/adas/adas-dataset-form/

Regards

Dear;

You can read it in the following link:

http://www.fullvision.ru/monitoring/description_eng.php

Regards

thanks Abdelghani Rouini

Here ( https://github.com/QiaoLiuHit/LSOTB-TIR ) is a large-scale thermal infrared dataset for object tracking.

thank you Qiao Liu

I have been searching for data sets and found some information in the link provided

https://bib.irb.hr/datoteka/1005656.Thermal_Imaging_Dataset_for_Person_Detection_final.pdf