ThermalTrack: Efficient Thermal Face Detection with Haar Cascades and Tracking for Search and Rescue
Abstract
Disasters pose immense challenges to search and rescue (SAR) operations, where rapid and accurate survivor detection is critical for mission success. This paper presents ThermalTrack, a computationally efficient real-time face detection system specifically designed for thermal imaging in SAR operations usingUAV-mounted FLIR Lepton 3.5 cameras (160×120 pixel resolution). Our system integrates Histogrambased Adaptive Dynamic Range (HADR) preprocessing with dual detection pathways: Haar Cascade classifiers and Dlib’s HOG-based frontal face detector, enhanced by Kalman filtering for robust multi-frametracking. We systematically optimized detection parameters including scale factors (1.1-1.5) and minimumneighbor values (3-7) to achieve optimal accuracy-speed tradeoffs. Experimental validation across twodistance scenarios shows detection accuracy of 85-92% with processing times of 30-50ms per frame. At50-meter range (aerial operations), the system achieves 92% precision, 84% recall, and 88% F1-score. At10-meter range (ground operations), performance reaches 85% precision, 78% recall, and 81% F1-score.HADR preprocessing improves detection rates by 13 percentage points (from 76% to 89%), while Kalmanfiltering provides stable tracking during brief occlusions and reduces detection jitter. The system demonstrates real-time capability suitable for resource-constrained UAV platforms, processing at 20-33 framesper second while maintaining competitive accuracy compared to computationally intensive CNN-based approaches.References
R. R. Fletcher et al., ”The Use of Mobile Thermal Imaging and Deep Learning for Prediction of
Surgical Site Infection,” in Proc. 43rd Annual International Conference of the IEEE Engineering
in Medicine & Biology Society (EMBC), 2021, pp.
-2580.
A. N. Wilson, K. A. Gupta, B. H. Koduru, A.
Kumar, A. Jha, and L. R. Cenkeramaddi, ”Recent Advances in Thermal Imaging and Its Applications Using Machine Learning: A Review,”
IEEE Sensors Journal, vol. 23, no. 4, pp. 3853-
, Feb. 2023.
A. Jonkus, P. Tumas, and A. Serackis, ”Thermal
imaging applications in human detection: A review,” Biomedical Signal Processing and Control,
vol. 78, p. 104089, 2022.
N. U. Huda, R. Gade, and T. B. Moeslund,
”Effects of Pre-processing on the Performance
of Transfer Learning Based Person Detection in
Thermal Images,” in Proc. IEEE 2nd International Conference on Pattern Recognition and
Machine Learning, 2021, pp. 1-6.
. . . Informatica 47 (2023) 41–52 15
I. Ullah et al., ”Predictive Maintenance of Power
Substation Equipment by Infrared Thermography
Using a Machine-Learning Approach,” Energies,
vol. 10, no. 12, p. 1987, 2017.
J. R. Ragaza and R. R. Sama, ”Critical factors affecting search and rescue operations: A perspective of disaster management authorities,” International Journal of Disaster Risk Reduction, vol.
, p. 102118, 2021.
C. Herrmann, M. Ruf, and J. Beyerer, ”CNNbased thermal infrared person detection by domain adaptation,” in Autonomous Systems: Sensors, Vehicles, Security, and the Internet of Everything, vol. 10643, International Society for Optics
and Photonics, 2018, p. 1064308.
C. Herrmann, T. M¨uller, D. Willersinn, and
J. Beyerer, ”Real-time person detection in lowresolution thermal infrared imagery with MSER
and CNNs,” in Proc. SPIE 9987, Electro-Optical
and Infrared Systems: Technology and Applications XIII, 2016, p. 99870I.
L. Zhang, A. Gonzalez-Garcia, J. van de Weijer, M. Danelljan, and F. S. Khan, ”Synthetic
data generation for end-to-end thermal infrared
tracking,” IEEE Transactions on Image Processing, vol. 28, no. 4, pp. 1837-1850, 2018.
Y. Lozanov and S. Tzvetkova, ”A methodology for processing of thermographic images for
diagnostics of electrical equipment,” in Proc.
th Electrical Engineering Faculty Conference
(BulEF), 2019, pp. 1-4.
Z. Jia, Z. Liu, C. Vong, and M. Pecht, ”A Rotating Machinery Fault Diagnosis Method Based
on Feature Learning of Thermal Images,” IEEE
Access, vol. 7, pp. 12348-12359, 2019.
F. J. Martinez-Murcia, J. M. G´orriz, J. Ram´ırez,
and A. Ortiz, ”Convolutional neural networks for
neuroimaging in Parkinson’s disease: is preprocessing needed?,” International Journal of Neural
Systems, vol. 28, no. 10, p. 1850035, 2018.
D. A. Pitaloka, A. Wulandari, T. Basaruddin, and
D. Y. Liliana, ”Enhancing CNN with preprocessing stage in automatic emotion recognition,” Procedia Computer Science, vol. 116, pp. 523-529,
A. S. N. Huda and S. Taib, ”Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography,”
Infrared Physics & Technology, vol. 61, pp. 184-
, 2013.
Y. Olivatti, C. Penteado, B. P. T. Aquino Jr,
and R. Maia, ”Analysis of artificial intelligence
techniques applied to thermographic inspection
for automatic detection of electrical problems,”
in Proc. IEEE International Smart Cities Conference (ISC2), 2018, pp. 1-6.
Y. Socarras, S. Ramos, D. V´azquez, A. L´opez,
and T. Gevers, ”Adapting pedestrian detection
from synthetic to far infrared images,” in Proc.
International Conference on Computer Vision
(ICCV) Workshop, 2013, pp. 705-710.
K. K. Pal and K. Sudeep, ”Preprocessing for
image classification by convolutional neural networks,” in Proc. IEEE International Conference
on Recent Trends in Electronics, Information &
Communication Technology (RTEICT), 2016, pp.
-1781.
J. Yim and K.-A. Sohn, ”Enhancing the performance of convolutional neural networks on quality
degraded datasets,” in Proc. International Conference on Digital Image Computing: Techniques
and Applications (DICTA), 2017, pp. 1-8.
L. F. Rodrigues, M. C. Naldi, and J. F. Mari,
”Comparing convolutional neural networks and
preprocessing techniques for HEP-2 cell classification in immunofluorescence images,” Computers in Biology and Medicine, vol. 116, p. 103542,
R. Fu et al., ”Enhanced intelligent identification of concrete cracks using multi-layered image preprocessing-aided convolutional neural networks,” Sensors, vol. 20, no. 7, p. 2021, 2020.
R. Miezianko and D. Pokrajac, ”People detection in low resolution infrared videos,” in Proc.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2008, pp.
-6.
J. W. Davis and M. A. Keck, ”A two-stage template approach to person detection in thermal imagery,” in Proc. IEEE Workshops on Applications
of Computer Vision, vol. 1, 2005, pp. 364-369.
R. Gade and T. B. Moeslund, ”Constrained multitarget tracking for team sports activities,” IPSJ
Transactions on Computer Vision and Applications, vol. 10, no. 1, pp. 1-11, 2018.
G. B. Huang, M. Ramesh, T. Berg, and E.
Learned-Miller, ”Labeled Faces in the Wild: A
Database for Studying Face Recognition in Unconstrained Environments,” University of Massachusetts, Amherst, Technical Report 07-49, October 2007.
Informatica 47 (2023) 41–52
Purdue University, ”Thermal imaging
and computational intelligence for disaster response,” Engineering Research,
ECE, Computational Intelligence and Signal Processing, 2022. [Online]. Available:
https://engineering.purdue.edu/ECE/Research/Areas/CNSIP
DOI:
https://doi.org/10.31449/inf.v50i7.9833Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
