Abstract
Human detection plays an important role in surveillance by ensuring security and maintaining public order. It is still considered a complex task in the deep learning field due to the highly varying illumination conditions under which humans should be detected. This paper proposes a new approach based on the enhanced YOLOv5 to detect humans in thermal images. It consists of integrating the Convolutional Block Attention Module (CBAM) into the backbone network to enhance the model’s ability to extract features. To measure the effectiveness of our method, we evaluated its performance on two benchmark thermal image datasets: the Ohio State University thermal pedestrian dataset, and the autonomous system lab thermal infrared dataset. Both datasets represent various challenges and images are collected in different humidity and weather conditions. From the obtained results, our approach performs human detection with 96% mean average precision and 91,8% recall, outperforming state-of-the-art CNN-based techniques like YOLOv5, RCNN, and Cascade RCNN.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gade, R., Moeslund, T.B.: Thermal cameras, and applications: a survey. Mach. Vis. Appl. 25(1), 245–262 (2014)
Lang, S., Zhijie, Z., Bo, L.: Research on dense-yolov5 algorithm for infrared target detection. Optics & Optoelectronic Technol. 19(01), 69–75 (2021)
Huijun, D., Zhigang, W., Yan, W.: Two-channel saliency object recognition algorithm based on improved YOLO network. Laser & Infrared 50(11), 1370–1378 (2020)
Wang, Y., Xiuxin, C., Hejin, Y.: Multi-target recognition of substation infrared image based on improved faster RCNN. Chinese J. Sensors and Actuators 34(04), 522–530 (2021)
Li, M., Zhang, T., Cui, W.: Research of infrared small pedestrian target detection based on YOLOv3. Infrared Technol. 42(02), 176–181 (2020)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In Proceedings ofthe IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Redmon, J., Farhadi, A.: Yolov3: An Incremental Improvement (2018). arXiv preprint arXiv:1804.02767
Bochkovskiy, A., Wang, C.-Y., Liao, H.Y.M.: Yolov4: Optimal Speed and Accuracy of Object Detection (2020). arXiv preprint arXiv:2004.10934
Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., Cspnet, I.-H.Y.: A new backbone that can enhance the learning capability of CNN. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390–391 (2020)
Woo, S., Park, J., Lee, J.Y., et al.: CBAM: convolutional block attention module. Computer Vision-ECCV 2018. Lecture Notes in Computer Science, Springer, Cham, 112211, 319 (2018)
Wang, Q., et al.: A real-time individual identification method for swimming fish based on improved Yolov5. SSRN Journal (2022). https://doi.org/10.2139/ssrn.4044575
Portmann, J., Lynen, S., Chli, M., Siegwart, R.: People detection and tracking from aerial thermal views. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 1794–1800 (2014)
Davis, J.W., Keck, M.A.: A two-stage template approach to person detection in thermal imagery. In: 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION’05)-Volume 1, 1, IEEE, pp. 364–369 (2005)
“GitHub - ultralytics/yolov5: YOLOv5
in PyTorch > ONNX > CoreML > TFLite,” GitHub. https://github.com/ultralytics/yolov5. Accessed 1 Sep. 2022
in PyTorch > ONNX > CoreML > TFLite,” GitHub. Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Khalfaoui, A., Abdelmajid, B., Ilham, E.M. (2023). An Improved YOLOv5 Based on Attention Model for Infrared Human Detection. In: Masrour, T., Ramchoun, H., Hajji, T., Hosni, M. (eds) Artificial Intelligence and Industrial Applications. A2IA 2023. Lecture Notes in Networks and Systems, vol 772. Springer, Cham. https://doi.org/10.1007/978-3-031-43520-1_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-43520-1_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43519-5
Online ISBN: 978-3-031-43520-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)