CoChat
Sign Up
Cited by 17

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

A Lightweight Network Based on YOLOv8 for Improving Detection Performance and the Speed of Thermal Image Processing

Dinh, Huyen Trang, Kim, Eung-Tae·2025·Electronics
DOI 10.3390/electronics14040783
Open this paper in CoChat — free account

Abstract

Deep learning and image processing technology continue to evolve, with YOLO models widely used for real-time object recognition. These YOLO models offer both blazing fast processing and high precision, making them super popular in fields like self-driving cars, security cameras, and medical support. Most YOLO models are optimized for RGB images, which creates some limitations. While RGB images are super sensitive to lighting conditions, infrared (IR) images using thermal data can detect objects consistently, even in low-light settings. However, infrared images present unique challenges like low resolution, tiny object sizes, and high amounts of noise, which makes direct application tricky in regard to the current YOLO models available. This situation requires the development of object detection models designed specifically for thermal images, especially for real-time recognition. Given the GPU and memory constraints in edge device environments, designing a lightweight model that maintains a high speed is crucial. Our research focused on training a YOLOv8 model using infrared image data to recognize humans. We proposed a YOLOv8s model that had unnecessary layers removed, which was better suited to infrared images and significantly reduced the weight of the model. We also integrated an improved Global Attention Mechanism (GAM) module to boost IR image precision and applied depth-wise convolution filtering to maintain the processing speed. The proposed model achieved a 2% precision improvement, 75% parameter reduction, and 12.8% processing speed increase, compared to the original YOLOv8s model. This method can be effectively used in thermal imaging applications like night surveillance cameras, cameras used in bad weather, and smart ventilation systems, particularly in environments requiring real-time processing with limited computational resources.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/electronics14040783

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 34

  1. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. · DOI · Paper page
  2. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23). R-CNN (Region-based Convolutional Neural Networks) Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA. · DOI · Paper page
  3. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–13). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.
  4. Yoon, 2024, YOLOv5-based Lightweight Methodology for Real-time Thermal Image Object Detection for Edge Devices, J. Broadcast Eng., 29, 703, 10.5909/JBE.2024.29.5.703 · DOI
  5. Chen, 2021, Infrared image denoising based on the variance-stabilizing transform and the dual-domain filter, Digit. Signal Process., 113, 103012, 10.1016/j.dsp.2021.103012 · DOI
  6. Yang, H., Tong, Y., Cao, Z., and Chen, Z. (2023, January 13–15). Infrared image enhancement algorithm based on improved wavelet threshold function and weighted guided filtering. Proceedings of the 2nd International Conference on Electronic Information and Communication Engineering (EICE 2023), Guangzhou, China.
  7. Zou, 2021, Super-resolution reconstruction of infrared images based on a convolutional neural network with skip connections, Opt. Lasers Eng., 146, 106717, 10.1016/j.optlaseng.2021.106717 · DOI
  8. Brehar, R., Vancea, F., Marita, T., Vancea, C., and Nedevschi, S. (2019, January 7–9). Object Detection in Infrared Images with Different Spectra. Proceedings of the IEEE 15th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, Romania.
  9. Aboalia, H., Hussein, S., and Mahmoud, A. (2024, January 21–23). Infrared Multi-Object Detection Using Deep Learning. Proceedings of the 2024 14th International Conference on Electrical Engineering (ICEENG), Cairo, Egypt. · DOI
  10. Tsai, P.-F., Liao, C.-H., and Yuan, S.-M. (2022). Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios. Sensors, 22. · DOI
  11. Park, J., Chen, J., Cho, Y.K., Kang, D.Y., and Son, B.J. (2020). CNN-Based Person Detection Using Infrared Images for Night-Time Intrusion Warning Systems. Sensors, 20. · DOI
  12. Banuls, A., Mandow, A., Vazquez-Martın, R., Morales, J., and Garcıa-Cerezo, A. (2020, January 4–6). Object Detection from Thermal Infrared and Visible Light Cameras in Search and Rescue Scenes. Proceedings of the 2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Abu Dhabi, United Arab Emirates. · DOI
  13. Agrawal, K., and Subramanian, A. (2019). Enhancing Object Detection in Adverse Conditions using Thermal Imaging. arXiv.
  14. Li, 2021, YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection, IEEE Access, 9, 141861, 10.1109/ACCESS.2021.3120870 · DOI
  15. Brehar, R., Vancea, F., Marita, T., Vancea, C., and Nedevschi, S. (2019, January 5–7). Object Detection in Monocular Infrared Images Using Classification. Proceedings of the 2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania. · DOI
  16. Chen, Z., Geng, A., Jiang, J., Lu, J., and Wu, D. (2024). Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection. arXiv.
  17. Yoon, H.S., and Kim, E.T. (2023, January 6–8). Lightweight YOLOv5-based Attention Model for Real-Time Thermal Image Object Detection. Proceedings of the Korea Institute of Communications and Information Sciences (KICS) Conference, Seoul, Republic of Korea.
  18. Shapiro, V.A., Veleva, P.K., and Sgurev, V.S. (September, January 30). An adaptive method for image thresholding. Proceedings of the 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis, Hague, The Netherlands.
  19. Jing, 2022, Recent advances on image edge detection: A comprehensive review, Neurocomputing, 503, 259, 10.1016/j.neucom.2022.06.083 · DOI
  20. Kutuk, Z., and Algan, G. (2022, January 18–24). Semantic Segmentation for Thermal Images: A Comparative Survey. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. · DOI
  21. Girshick, R. (2015). Microsoft Research. Fast R-CNN. arXiv. · DOI · Paper page
  22. He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2018). Mask R-CNN. arXiv. · DOI · Paper page
  23. Li, Y., and Ren, F. (2019). Light-Weight RetinaNet for Object Detection. arXiv. · DOI
  24. Liao, 2024, Aircraft Skin Damage Visual Testing System Using Lightweight Devices with YOLO: An Automated Real-Time Material Evaluation System, AI, 5, 1793, 10.3390/ai5040089 · DOI
  25. Huang, G., Liu, Z., and van der Maaten, L. (2018). Densely Connected Convolutional Networks. arXiv. · DOI · Paper page
  26. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. arXiv.
  27. Datta, S.K., Shaikh, M.A., Srihari, S.N., and Gao, M. (2021). Soft-Attention Improves Skin Cancer Classification Performance. arXiv. · DOI
  28. Malinowski, M., Doersch, C., Santoro, A., and Battaglia, P. (2018). Learning Visual Question Answering by Bootstrapping Hard Attention. arXiv. · DOI
  29. Datta, S.K., Shaikh, M.A., Hu, S.N.S.J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2018, January 18–23). Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
  30. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. · DOI · Paper page
  31. Liu, Y., Shao, Z., and Hoffmann, N. (2021). Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions. arXiv.
  32. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2017). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. arXiv. · DOI · Paper page
  33. Wang, C., Chen, Y., Wu, Z., Liu, B., Tian, H., Jiang, D., and Sun, X. (2025). Line-YOLO: An Efficient Detection Algorithm for Power Line Angle. Sensors, 25. · DOI
  34. Zhang, N., Tan, J., Yan, K., and Feng, S. (2025). Lightweight UAV Landing Model Based on Visual Positioning. Sensors, 25. · DOI

Metadata

Authors
Dinh, H. T., & Kim, E.-T.
Venue
Electronics
Publisher
MDPI AG
Published
2025-02-17
Volume
14
Issue
4
Pages
783
ISSN
2079-9292
DOI
10.3390/electronics14040783
Cited by
17
References
4
Language
en
Licence
creativecommons.org/licenses/by/4.0/ (vor)
Funders
Ministry of SMEs and Startups (S3312736)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review