UAV Infrared Image Human and Vehicle Object Detection Based on YOLOv5

Leihao Zhao

doi:10.62051/ijcsit.v3n2.03

Authors

Leihao Zhao

DOI:

https://doi.org/10.62051/ijcsit.v3n2.03

Keywords:

YOLOv5, Object Detection, Infrared Images, Human Object Recognition, Vehicle Object Recognition

Abstract

Currently, the primary methods for searching for missing persons and vehicles in the wilderness involve extensive manpower for ground-based grid searches. Occasionally, a limited number of helicopters are deployed to assist in the search and rescue operations, and in some cases, UAVs equipped with visible light imaging cameras are used for manual image recognition. However, these search methods are inefficient and require significant human and material resources. To address these issues, this paper proposes a search and rescue method that combines multi-rotor UAVs with image target recognition technology. The YOLOv5-based object detection method is employed to identify humans and vehicles in UAV infrared images, achieving a mean Average Precision (mAPs) of 99%, with a mAP of 98.5% for human recognition and 99.5% for vehicle recognition. This object recognition algorithm model has profound implications for the automation of multi-rotor UAV wilderness search and rescue operations.

Downloads

Download data is not yet available.

References

Fan, Bangkui, et al. "Review on the technological development and application of UAV systems." Chinese Journal of Electronics 29.2 (2020): 199-207.

Portmann, Jan, et al. "People detection and tracking from aerial thermal views." 2014 IEEE international conference on robotics and automation (ICRA). IEEE, 2014.

Jia, Xinyu, et al. "LLVIP: A visible-infrared paired dataset for low-light vision." Proceedings of the IEEE/CVF international conference on computer vision. 2021.

Gündoğan, Meryem Mine, et al. "IR Reasoner: Real-time Infrared Object Detection by Visual Reasoning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.

Bravo, Raissa Zurli Bittencourt, Adriana Leiras, and Fernando Luiz Cyrino Oliveira. "The use of UAVs in humanitarian relief: An application of POMDP‐based methodology for finding victims." Production and Operations Management 28.2 (2019): 421-440.

Zou, Zhengxia, et al. "Object detection in 20 years: A survey." Proceedings of the IEEE 111.3 (2023): 257-276.

Maes, W., A. Huete, and K. Steppe. "Optimizing the processing of UAV-based thermal imagery, Remote Sens., 9, 476." (2017).

Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

Lin, Tsung-Yi, et al. "Focal loss for dense object detection." Proceedings of the IEEE international conference on computer vision. 2017.

Tian, Zhi, et al. "FCOS: A simple and strong anchor-free object detector." IEEE Transactions on Pattern Analysis and Machine Intelligence 44.4 (2020): 1922-1933.

Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.

Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." IEEE transactions on pattern analysis and machine intelligence 39.6 (2016): 1137-1149.

Dai, Jifeng, et al. "R-fcn: Object detection via region-based fully convolutional networks." Advances in neural information processing systems 29 (2016).

He, Kaiming, et al. "Mask r-cnn." Proceedings of the IEEE international conference on computer vision. 2017.

Li, Minglei, et al. "ComNet: Combinational neural network for object detection in UAV-borne thermal images." IEEE Transactions on Geoscience and Remote Sensing 59.8 (2020): 6662-6673.