Low-cost thermographic detection of living objects using MLP neural networks for automotive applications
DOI:
https://doi.org/10.14311/AP.2026.66.0401Keywords:
thermography, neural networks, MLP, object detection, automotive safety, AI, thermal imagingAbstract
Real-time identification of living objects is becoming an integral part of intelligent systems, particularly in the automotive sector, for security applications, and in rescue operations. This study presents an in-depth analysis of current research into the use of artificial intelligence (AI), specifically neural networks, for detecting living entities using thermal imaging cameras, with a particular emphasis on low-visibility night-time conditions.
The research focuses on the design, training, and evaluation of a multilayer perceptron (MLP) neural network. The network processes inputs, such as thermal intensity, pixel brightness, and object size, from segmented thermographic images to classify animals into five size categories and estimate their distance from the camera. The dataset was divided into training and testing sets, and the model achieved an accuracy of up to 92.4% for a five-metre range.
The article further details dataset preparation, technical parameters of thermal sensors, experimental results, and prospects for integrating AI into intelligent vehicle systems.
Downloads
References
[1] M. Islam. Autonomous systems revolution: Exploring the future of self-driving technology. Journal of Artificial Intelligence General science (JAIGS) 3(1):16–23, 2024. https://doi.org/10.60087/jaigs.v3i1.61
[2] R. Hussain, S. Zeadally. Autonomous cars: Research results, issues, and future challenges. IEEE Communications Surveys & Tutorials 21(2):1275–1313, 2019. https://doi.org/10.1109/COMST.2018.2869360
[3] SAE International. SAE levels of driving automation® refined for clarity and international audience, 2021. [2025-04-02]. https://www.sae.org/blog/sae-j3016-update
[4] U. Kiencke, L. Nielsen. Automotive control systems: For engine, driveline, and vehicle. Springer Berlin, Berlin, 2nd edn., 2005. ISBN 978-3-540-26484-2. https://doi.org/10.1007/b137654
[5] J. Liu, S. Zhang, S. Wang, D. N. Metaxas. Multispectral deep neural networks for pedestrian detection, 2016. arXiv:1611.02644. https://doi.org/10.48550/arXiv.1611.02644
[6] M. C. Budge, S. R. German. Basic radar analysis. Atech House radar series. Artech House, Boston, USA, 2015. ISBN 978-1-60807-878-3.
[7] S. M. Patole, M. Torlak, D. Wang, M. Ali. Automotive radars: A review of signal processing techniques. IEEE Signal Processing Magazine 34(2):22–35, 2017. https://doi.org/10.1109/MSP.2016.2628914
[8] T. Raj, F. H. Hashim, A. B. Huddin, et al. A survey on LiDAR scanning mechanisms. Electronics 9(5):741, 2020. https://doi.org/10.3390/electronics9050741
[9] M. Nielsen. Neural networks and deep learning, 2019. [2025-05-12]. http://neuralnetworksanddeeplearning.com
[10] A. Giusti, D. C. Cireşan, J. Masci, et al. Fast image scanning with deep max-pooling convolutional neural networks, 2013. arXiv:1302.1700. https://doi.org/10.48550/arXiv.1302.1700
[11] A. I. Alvarado-Hernandez, I. Zamudio-Ramirez, A. Y. Jaen-Cuellar, et al. Infrared thermography smart sensor for the condition monitoring of gearbox and bearings faults in induction motors. Sensors 22(16):6075, 2022. https://doi.org/10.3390/s22166075
[12] M. Bhattarai, M. Martínez-Ramón. A deep learning framework for detection of targets in thermal images to improve firefighting, 2020. arXiv:1910.03617. https://doi.org/10.48550/arXiv.1910.03617
[13] I. Bartolits. 140 éve született Christian Hülsmeyer, a radar elődjének a feltalálója [In Hungarian; Christian Hülsmeyer, inventor of the predecessor of radar, was born 140 years ago]. [2025-05-18]. https://www.hte.hu/technikatortenetievfordulok/-/hir/140-eve-szuletett-christianhulsmeyer-a-radar-elodjenek-a-feltalaloja
[14] T. Dutta, R. Bagi, H. P. Gupta. Deep learning models and their architectures for computer vision applications: A review. In A. Makkar, N. Kumar (eds.), Deep Learning for Security and Privacy Preservation in IoT, Signals and Communication Technology, pp. 31–48. Springer Singapore, Singapore, 2021. https://doi.org/10.1007/978-981-16-6186-0_2
[15] J. Kocić, N. Jovičić, V. Drndarević. An end-to-end deep neural network for autonomous driving designed for embedded automotive platforms. Sensors 19(9):2064, 2019. https://doi.org/10.3390/s19092064
[16] O. H. Boucif, A. M. Lahouaou, D. E. Boubiche, H. Toral-Cruz. Artificial intelligence of things for solar energy monitoring and control. Applied Sciences 15(11):6019, 2025. https://doi.org/10.3390/app15116019
[17] CVEDIA. Thermal animal detector. [2025-03-22]. https://www.cvedia.com/ai-models/thermalanimal-detector/
[18] J. Liu, W. YI. Power grid fault diagnosis method based on VGG network line graph semantic extraction. International Journal of Scientific Engineering and Research 10(5):16–20, 2022. https://www.ijser.in/abstract.php?paperid=SE22502172124
[19] K. He, X. Zhang, S. Ren, J. Sun. Deep residual earning for image recognition, 2015. arXiv:1512.03385. https://doi.org/10.48550/arXiv.1512.03385
[20] H. M. Ahmed, B. Abdulrazak. Monitoring indoor activity of daily living using thermal imaging: A case study. International Journal of Advanced Computer Science and Applications 12(9):2, 2021. https://doi.org/10.14569/IJACSA.2021.0120902
[21] M. Chang, T. Vuong, M. Palaparthi, et al. An empirical study of automatic wildlife detection using drone thermal imaging and object detection, 2023. arXiv:2310.11257. https://doi.org/10.48550/arXiv.2310.11257
[22] Axis Communications. Thermal cameras. [2025-03-22]. https://www.axis.com/enus/products/thermal-cameras
[23] K. Yoneda, N. Suganuma, R. Yanase, M. Aldibaja. Automated driving recognition technologies for adverse weather conditions. IATSS Research 43(4):253–262, 2019. https://doi.org/10.1016/j.iatssr.2019.11.005
[24] C. Burke, M. Rashman, S. Wich, et al. Optimising observing strategies for monitoring animals using drone-mounted thermal infrared cameras. International Journal of Remote Sensing 40(2):439–467, 2019. https://doi.org/10.1080/01431161.2018.1558372
[25] Teledyne FLIR OEM. Thermal imaging for large animal detection to help reduce wildlife vehicle collisions. [2025-03-22]. https://oem.flir.com/en-150/about/news/thermalimaging-for-large-animal-detection-to-helpreduce-wildlife-vehicle-collisions/
[26] S. Ren, K. He, R. Girshick, J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6):1137–1149, 2017. https://doi.org/10.1109/TPAMI.2016.2577031
[27] C. Cheng, Z. Shang, Z. Shen. CNN-based deep architecture for reinforced concrete delamination segmentation through thermography, 2019. arXiv:1904.05509. https://doi.org/10.48550/arXiv.1904.05509
[28] J. Zuluaga-Gomez, Z. Al Masry, K. Benaggoune, et al. A CNN-based methodology for breast cancer diagnosis using thermal images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 9(2):131–145, 2021. https://doi.org/10.1080/21681163.2020.1824685
[29] X. Wu, D. Sahoo, S. C. H. Hoi. Recent advances in deep learning for object detection, 2019. arXiv:1908.03673. https://doi.org/10.48550/arXiv.1908.03673
[30] M. Jangblad. Object detection in infrared images using deep convolutional neural network. Master’s thesis, Uppsala University, 2018. [2025-04-25]. https://www.diva-portal.org/smash/get/diva2:1228617/FULLTEXT01.pdf
[31] J. Yang, W. Wang, G. Lin, et al. Infrared thermal imaging-based crack detection using deep learning. IEEE Access 7:182060–182077, 2019. https://doi.org/10.1109/ACCESS.2019.2958264
[32] D. Mlakić, S. Nikolovski, L. Majdandžić. Deep learning method and infrared imaging as a tool for transformer faults detection. Journal of Electrical Engineering 6(2):98–106, 2018. https://doi.org/10.17265/2328-2223/2018.02.006
[33] Z. A. Jaffery, A. K. Dubey. Design of early fault detection technique for electrical assets using infrared thermograms. International Journal of Electrical Power & Energy Systems 63:753–759, 2014. https://doi.org/10.1016/j.ijepes.2014.06.049
[34] S. Parashar, A. Kumar, P. Sharma, et al. Fault prediction in electrical assets using infrared thermography. Journal of Physics: Conference Series 2570(1):012019, 2023. https://doi.org/10.1088/1742-6596/2570/1/012019
[35] A. Younis, L. Qiang, C. O. Nyatega, et al. Brain tumor analysis using deep learning and VGG-16 ensembling learning approaches. Applied Sciences 12(14):7282, 2022. https://doi.org/10.3390/app12147282
[36] M. Piekarski, J. Jaworek-Korjakowska, A. I. Wawrzyniak, M. Gorgon. Convolutional neural network architecture for beam instabilities identification in synchrotron radiation systems as an anomaly detection problem. Measurement 165:108116, 2020. https://doi.org/10.1016/j.measurement.2020.108116
[37] X. J. Dang, F. H. Wang, W. J. Ma. Fault diagnosis of power transformer by acoustic signals with deep learning. In 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), pp. 1–4. IEEE, Beijing, China, 2020. https://doi.org/10.1109/ICHVE49031.2020.9279751
[38] S. Sharma, K. Guleria. A deep learning based model for the detection of pneumonia from chest X-ray images using VGG-16 and neural networks. Procedia Computer Science 218:357–366, 2023. https://doi.org/10.1016/j.procs.2023.01.018
[39] A. S. Bhadoriya, V. Vegamoor, S. Rathinam. Vehicle detection and tracking using thermal cameras in adverse visibility conditions. Sensors 22(12):4567, 2022. https://doi.org/10.3390/s22124567
[40] E. Volná, M. Kotyrba, M. Janošek, V. Kocian. Umělá inteligence: Rozpoznávání vzorů v dynamických datech [In Czech; Artificial intelligence: Pattern recognition in dynamic data]. BEN – technická literatura, Prague, Czech Republic, 2014. ISBN 978-80-7300-497-2.
[41] P. Neelima, A. Swathi, K. Sushmitha, P. Haripriya. Human activity recognition using deep learning. International Journal for Research in Applied Science and Engineering Technology 13(4):3605–3610, 2025. https://doi.org/10.22214/ijraset.2025.69027
[42] H. Zhang, L. Wang, J. Sun, et al. NAS-EOD: An end-to-end neural architecture search method for efficient object detection. In 2020 25th International Conference on Pattern Recognition (ICPR), pp. 1446–1451. IEEE, Milan, Italy, 2021. https://doi.org/10.1109/ICPR48806.2021.9413209
[43] A. Singh. Vision-RADAR fusion for robotics BEV detections: A survey, 2023. arXiv:2302.06643. https://doi.org/10.48550/ARXIV.2302.06643
[44] M. Drahanský, M. Charvát, I. Macek, J. Mohelníková. Thermal imaging detection system: A case study for indoor environments. Sensors 23(18):7822, 2023. https://doi.org/10.3390/s23187822
[45] P.-F. Tsai, C.-H. Liao, S.-M. Yuan. Using deep learning with thermal imaging for human detection in heavy smoke scenarios. Sensors 22(14):5351, 2022. https://doi.org/10.3390/s22145351
[46] R. Dedhiya, S. T. Kakileti, G. Deepu, et al. Evaluation of non-invasive thermal imaging for detection of viability of onchocerciasis worms, 2022. arXiv:2203.12620. https://doi.org/10.48550/arXiv.2203.12620
[47] Pelco. Thermal security cameras & surveillance systems. [2025-04-06]. https://www.pelco.com/cameras/thermal
[48] TOPDON Incorporated. TOPDON termokamera TC001 [In Czech; TOPDON thermal camera TC001], 2017. [2025-03-22]. https://eu.topdon.com/en-cz/products/tc001?gad_source=1&gad_campaignid=22473453029&gbraid=0AAAAApG2_mRaUOy4ZPZJHXvqlRZjNSN6-&gclid=Cj0KCQjwjJrCBhCXARIsAI5x66WL5DPsTZVbAEl1pDWdVXB74e4G4SovN2swgR4AOQCpXSV3S5tmoaAkjgEALw_wcB
[49] Timi Creation. Termovizní kamera TIMI EDU [In Czech; Thermal imaging camera TIMI EDU]. [2025-03-22]. https://shop.timic.cz/termoviznikamera-timi-edu/
[50] A. Orman, M. I. Endres. Use of thermal imaging for identification of foot lesions in dairy cattle. Acta Agriculturae Scandinavica, Section A – Animal Science 66(1):1–7, 2016. https://doi.org/10.1080/09064702.2016.1179785
[51] D. Hendrycks, K. Gimpel. A baseline for detecting misclassified and out-of-distribution examples in neural networks, 2016. arXiv:1610.02136. https://doi.org/10.48550/ARXIV.1610.02136
[52] V. Novotný. Inteligentní asistenční systémy pro osobní automobily [In Czech; Thermographic detection of living objects using neural networks]. Master’s thesis, Škoda Auto Vysoká škola, Mladá Boleslav, Czech Republic, 2024.
[53] N. Chowdhury, L. M. Mackenzie. Vehicular communications for smart cars: Protocols, applications and security concerns. CRC Press, Boca Raton, 2022. ISBN 978-0-367-45744-0.
[54] D. Möller, R. E. Haas. Guide to automotive connectivity and cybersecurity: Trends, technologies, innovations and applications. Computer communications and networks. Springer International Publishing AG, Cham, 2019. ISBN 978-3-319-73511-5.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jiří David, Vojtěch Novotný, Pavel Brom, Pavel Švec, Josef Bradáč
This work is licensed under a Creative Commons Attribution 4.0 International License.
