TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover

Journal of Information and Optimization Sciences

(Since 1980)
Open Access ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Information and Optimization Sciences
Open Access Research Article

Detecting and classifying objects from thermal images : A technical analysis

* , ,

* Corresponding author · click or hover a name for details

pp. 683–713Vol. 47Issue 2February 2026DOI: 10.47974/JIOS-2040XML
Received:
12 Feb 2025
Published Online:
20 Jan 2026
Article type:
Research Article
Language:
EN
Article no.:
JIOS-2040
Pages:
683–713

Abstract

Object detection and classification in thermal imaging is crucial for a range that operates continuously, such as security, inspection, emergency assistance, and border tracking. When applying several state-of-the-art object detection algorithms to ground-based thermal imaging, the main obstacles include inconsistencies in target size, low-quality images, obstruction, and varying illuminating conditions. This study analyzes the ability of deep-learning algorithms to examine various objects within ground-based thermal images. The novelty of this study lies in its utilization of two network architectures, MobileNetV2 and EfficientNet-B0, which are pre-trained on ImageNet visual images. These networks are typically employed for traditional optical images, but MobileNetv2in this research, are repurposed and trained on custom datasets of thermal images that have been created using the “Seek Shot” camera. This modification aims to test their performance and suitability in analyzing thermal images, expanding their usefulness beyond their original purpose. Standard metrics such as precision, the experiment, the 5-fold cross-validation used to address the bias of the models. The results demonstrate that the MobileNetV2 model achieves the highest detection accuracy of 96.5% for car classes. The research explores alternative deep learning models Faster RCNN and RetinaNet to compare object detection accuracy in thermal datasets. The results showed that out of all the models, MobileNetv2 had the highest mean average precision (mAP) with 92.6% and EfficientNet-B0 had better accuracy than the other two state-of-the-art models, while RetinaNet had the lowest mAP score of 6.57%.

Keywords

Deep learningThermal imagingCustom datasetMobilenet-V2EfficientNET-B0

Subject Classifications

68U1094A08

References

[1] T.Z. Xiang, G.S. Xia and L. Zhang, “Mini-unmanned aerial vehicle-based remote sensing: Techniques, applications and prospects,” IEEE Geoscience Remote Sensing, vol. 7, pp. 29–63 (2019).
[2] P. Lin, H. Yang, S. Cheng, F. Guo, L. Wang and Y. Lin, “An improved YOLOv5s method-based bruises detection on apples using cold excitation thermal images”, Postharvest Biology and Technology, vol.199, no. 112280, pp.0925-5214 (2023).
[3] C. Jiang, H. Ren, X. Ye, J. Zhu, H. Zeng, Y. Nan, M. Sun, X. Ren and H. Huo, “Object detection from UAV thermal infrared images and videos using YOLO models,” International Journal of Applied Earth Observation and Geoinformation, vol. 112, pp. 1569-8432 (2022).
[4] S. B. A. Aaditya, P. B. Karandikar, M. Jain, J. Suryawanshi, A. Bellam, D. Chavan, R. Holmukhe, P. S. Chaudhari, and A. Gandhar, “Thermal profiling of ultracapacitor modules: A layered analysis,” Journal of Information and Optimization Sciences, vol. 45, no. 2, pp 291–303 (2024).
[5] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu and A.C. Berg, “Ssd: Single shot multibox detector,” In Proceedings of the European Conference on Computer Vision, pp. 21–37 (2017). 
[6] C.Y. Fu, W. Liu, A. Ranga, A. Tyagi and A.C. Berg, “Dssd: Deconvolutional single shot detector,” arXiv:1701.06659 (2017).
[7] M. Everingham, L.V. Gool, C.K. Williams, J. Winn and A. Zisserman, “The pascal visual object classes (voc) challenge,” International Journal of Computer Mathematics, vol. 88, pp. 303–338 (2010). 
[8] T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár and C.L. Zitnick, “Microsoft coco: Common objects in context,” In Proceedings of the European Conference on Computer Vision, pp. 740–755 (2014).
[9] N.D. Nguyen, T. Do and T.D. Ngo, “An Evaluation of Deep Learning Methods for Small Object Detection’” Journal of Electrical and Computer Engineering, 3189691 (2020).  
[10] S.S. Sumit, D.R.A. Rambli and S. Mirjalili, “Vision-Based Human Detection Techniques: A Descriptive Review,” vol. 9, pp. 42724–42761 (2021).
[11] K.R. Akshatha, A.K. Karunakar, S.B. Shenoy, A.K. Pai, N.H. Nagaraj and S.S. Rohatgi, “Human Detection in Aerial Thermal Images Using Faster R-CNN and SSD Algorithms,” Electronics, vol. 11, no. 1151 (2022)
[12] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005). 
[13] P. Viola and M.J. Jones, “Robust real-time face detection,” International Journal of Computer Mathematics, vol.57, pp 137–154 (2004).
[14]  P.F. Felzenszwalb, R.B. Girshick, D. McAllester and D. Ramanan, “Object Detection with Discriminatively Trained Part-Based Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp.1627–1645 (2010).
[15] M. Teutsch, T. Mueller, M. Huber and J. Beyerer, “Low resolution person detection with a moving thermal infrared camera by hot spot classification,” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 23, pp. 209–216 (2014). 
[16] Y. Ma, X. Wu, G. Yu, Y. Xu and Y. Wang, “Pedestrian detection and tracking from low-resolution unmanned aerial vehicle thermal imagery,” Sensors, vol. 16, no. 446 (2016). 
[17] Y. Chen, W. Chen, and H. Ni, “Image segmentation in thermal images,” IEEE International Conference on Industrial Technology (ICIT), pp. 1507-1512 (2016).
[18] I. Lahouli, R. Haelterman, Z. Chtourou, G. De Cubber and R. Attia, “Pedestrian detection and tracking in thermal images from aerial MPEG videos,” In Proceedings of the 13th International Joint Conference on Computer Vision Imaging and Computer Graphics Theory and Applications, vol. 5, pp. 487–495 (2018). 
[19]  J. Li, k. Jin, D. Zhou, N. Kubota and Z. Ju, “Attention mechanism-based CNN for facial expression recognition,” Neurocomputing, vol. 411, pp.340-350 (2020).
[20] P. Poirson, P. Ammirato, C.Y. Fu, W. Liu, J. Kosecka and A.C. Berg, “Fast single shot detection and pose estimation,” Fourth International Conference on 3D Vision (3DV), pp. 676–684 (2017).
[21] M. S. Mangale and M. Khambete, “Moving Object Detection using Visible Spectrum Imaging and Thermal Imaging,” International Conference on Industrial Instrumentation and Control (ICIC), pp. 590-593 (2015).
[22] V. Ghenescu, E. Barnoviciu, S.V. Carata, and M. Ghenescu, R. Mihaescu, M. Chindea, “Object Recognition on Long Range Thermal Image Using State of the Art DNN,” pp. 1-4 (2019).
[23] A. Akula, and H.K. Sardana, “Deep CNN-based Feature Extractor for Target Recognition in Thermal Images,” TENCON 2019 IEEE Region 10 Conference (TENCON), pp. 2370-2375 (2019). 
[24] S. Qian, C. Ning, and Y. Hu, “MobileNetV3 for Image Classification. (2021),” IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), pp.490-497 (2021).
[25] S. Civilibal, K.K. Cevik, and A. Bozkurt, “A deep learning approach for automatic detection, segmentation and classification of breast lesions from thermal images,” Expert Systems with Applications, vol. 212, no.118774 (2023).
[26] M. A. Farooq, P. Corcoran, C. Rotari and W. Shariff, “Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS),” vol. 9. pp. 156465-156481 (2021).
[27] C. Jiang, H. Ren, X. Ye, J. Zhu, H. Zeng, Y. Nan, M. Sun, X. Ren and H. Huo, “Object detection from UAV thermal infrared images and videos using YOLO models,” International Journal of Applied Earth Observation and Geoinformation, vol. 112, no. 102912, pp. 1569-8432 (2022).
[28] F. Munir, S. Azam, M. Rafique, A. Sheri and M. Jeon, “Exploring thermal images for object detection in underexposure regions for autonomous driving,” Applied Soft Computing, vol. 121, no. 108793 (2022).
[29] A. Narayanan, R.D. Kumar, R. RoselinKiruba, and T.S. Sharmila, “Study and analysis of pedestrian detection in thermal images using YOLO and SVM,” In 2021 Sixth International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), pp. 431-434 (2021).
[30] D. Rahadiyan1, S. Hartati1, M. Wahyono1, and A. Nugroho, “Percentage of Phosphorus Deficiency Estimation in Chili Leaves Images,” Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 7, pp.2089-3272 (2019).
[31] R. Gupta, S. Jain, and M. Kumar, “Enhanced Thermal Object Detection and Classification with MobileNetV3: A Cutting-Edge Deep Learning Solution,” 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kamand, India, pp. 1-6 (2024).
[32] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510-4520 (2018).
[33] Q. Xiang, X. Wang, R. Li, G. Zhang, J. Lai, and Q. Hu, “Fruit image classification based on mobilenetv2 with transfer learning technique,” Proceedings of the 3rd International Conference on Computer Science and Application Engineering, pp.1-7 (2019).
[34] G. Andrew Z. Menglong, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” CoRR (2017)
[35] S. Qian, C. Ning and Y. Hu, “MobileNetV3 for Image Classification,” IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), pp. 490-497 (2021).
[36] M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. 36th Int. Conf. Machine Learning (ICML), Long Beach, CA, USA, pp. 6105–6114 (2019).
[37] A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv, pp.1704.04861 (2017).
[38] R. Gupta, S. Jain, and M. Kumar, “Role of Thermal Images in Various Applications of Computer Vision,” 2023 4th International Conference on Intelligent Engineering and Management (ICIEM), London, United Kingdom, pp. 1-6 (2023)
[39] M. Fatemeh, D. Javan, F. Farzaneh and S. Farhad, “Potential evaluation of visible-thermal UAV image fusion for individual tree detection based on convolutional neural network,” International Journal of Applied Earth Observation and Geoinformation, vol. 113, no. 103011 (2022).
[40] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 658–666 (2019).
[41] X. Yang, R. Guo and H. Li, “Comparison of multimodal RGB-thermal fusion techniques for exterior wall multi-defect detection,” Journal of Infrastructure Intelligence and Resilience. vol. 2, no. 2, pp. 2772-9915 (2023).
[42]  R. Gupta, S. Jain, and M. Kumar, “Thermal Vision for Airfield Safety: A Dynamic FOD Detection Framework,” IAENG International Journal of Computer Science, vol. 52, no. 4, pp.1178-1186 (2025).
[43] J. Yang, W. Wang, G. Lin, Q. Li and Y. Sun, “Infrared Thermal Imaging-Based Crack Detection Using Deep Learning,” IEEE Access, vol. 7, pp. 182060-182077 (2019).

Views: 262Downloads: 117Citations: 0