DOI QR코드

DOI QR Code

Automatic Detection of Dead Trees Based on Lightweight YOLOv4 and UAV Imagery

  • Yuanhang Jin (State Key Laboratory of Geo-Information Engineering and School of Civil Engineering, University of Science and Technology Liaoning) ;
  • Maolin Xu (State Key Laboratory of Geo-Information Engineering and School of Civil Engineering, University of Science and Technology Liaoning) ;
  • Jiayuan Zheng (State Key Laboratory of Geo-Information Engineering and School of Civil Engineering, University of Science and Technology Liaoning)
  • Received : 2022.06.21
  • Accepted : 2022.11.28
  • Published : 2023.10.31

Abstract

Dead trees significantly impact forest production and the ecological environment and pose constraints to the sustainable development of forests. A lightweight YOLOv4 dead tree detection algorithm based on unmanned aerial vehicle images is proposed to address current limitations in dead tree detection that rely mainly on inefficient, unsafe and easy-to-miss manual inspections. An improved logarithmic transformation method was developed in data pre-processing to display tree features in the shadows. For the model structure, the original CSPDarkNet-53 backbone feature extraction network was replaced by MobileNetV3. Some of the standard convolutional blocks in the original extraction network were replaced by depthwise separable convolution blocks. The new ReLU6 activation function replaced the original LeakyReLU activation function to make the network more robust for low-precision computations. The K-means++ clustering method was also integrated to generate anchor boxes that are more suitable for the dataset. The experimental results show that the improved algorithm achieved an accuracy of 97.33%, higher than other methods. The detection speed of the proposed approach is higher than that of YOLOv4, improving the efficiency and accuracy of the detection process.

Keywords

Acknowledgement

This research was supported by the Fund project of the Provincial Education Department (No. LJKMZ20220638) and the Open Fund Project of the Marine Information Technology Innovation Center of the Ministry of Natural Resources.

References

  1. A. Kaminska, M. Lisiewicz, K. Sterenczak, B. Kraszewski, and R. Sadkowski, "Species-related single dead tree detection using multi-temporal ALS data and CIR imagery," Remote Sensing of Environment, vol. 219, pp. 31-43, 2018. https://doi.org/10.1016/j.rse.2018.10.005
  2. K. Otsu, M. Pla, A. Duane, A. Cardil, and L. Brotons, "Estimating the threshold of detection on tree crown defoliation using vegetation indices from UAS multispectral imagery," Drones, vol. 3, no. 4, article no. 80, 2019. https://doi.org/10.3390/drones3040080
  3. S. Malek, Y. Bazi, N. Alajlan, H. AlHichri, and F. Melgani, "Efficient framework for palm tree detection in UAV images," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 12, pp. 4692-4703, 2014. https://doi.org/10.1109/JSTARS.2014.2331425
  4. W. Li, H. Fu, L. Yu, and A. Cracknell, "Deep learning based oil palm tree detection and counting for highresolution remote sensing images," Remote Sensing, vol. 9, no. 1, article no. 22, 2016. https://doi.org/10.3390/rs9010022
  5. M. Culman, S. Delalieux, and K. Van Tricht, "Individual palm tree detection using deep learning on RGB imagery to support tree inventory," Remote Sensing, vol. 12, no. 21, article no. 3476, 2020. https://doi.org/10.3390/rs12213476
  6. E. Guirado, S. Tabik, D. Alcaraz-Segura, J. Cabello, and F. Herrera, "Deep-learning versus OBIA for scattered shrub detection with Google earth imagery: Ziziphus Lotus as case study," Remote Sensing, vol. 9, no. 12, article no. 1220, 2017. https://doi.org/10.3390/rs9121220
  7. H. Tao, C. Li, D. Zhao, S. Deng, H. Hu, X. Xu, and W. Jing, "Deep learning-based dead pine tree detection from unmanned aerial vehicle images," International Journal of Remote Sensing, vol. 41, no. 21, pp. 8238-8255, 2020. https://doi.org/10.1080/01431161.2020.1766145
  8. R. Yu, Y. Luo, Q. Zhou, X. Zhang, D. Wu, and L. Ren, "Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery," Forest Ecology and Management, vol. 497, article no. 119493, 2021. https://doi.org/10.1016/j.foreco.2021.119493
  9. M. H. Junos, A. S. Mohd Khairuddin, S. Thannirmalai, and M. Dahari, "Automatic detection of oil palm fruits from UAV images using an improved YOLO model," The Visual Computer, vol. 38, pp. 2341-2355, 2022. https://doi.org/10.1007/s00371-021-02116-3
  10. X. Liu, K. H. Ghazali, F. Han, and I. I. Mohamed, "Automatic detection of oil palm tree from UAV images based on the deep learning method," Applied Artificial Intelligence, vol. 35, no. 1, pp. 13-24, 2021. https://doi.org/10.1080/08839514.2020.1831226
  11. K. Yarak, A. Witayangkurn, K. Kritiyutanont, C. Arunplod, and R. Shibasaki, "Oil palm tree detection and health classification on high-resolution imagery using deep learning," Agriculture, vol. 11, no. 2, article no. 183, 2021. https://doi.org/10.3390/agriculture11020183
  12. R. Girshick, "Fast R-CNN," in Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015, pp. 1440-1448. https://doi.org/10.1109/ICCV.2015.169
  13. A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, "Albumentations: fast and flexible image augmentations," Information, vol. 11, no. 2, article no. 125, 2020. https://doi.org/10.3390/info11020125
  14. X. Wang, Z. Jia, J. Yang, and N. Kasabov, "Change detection in SAR images based on the logarithmic transformation and total variation denoising method," Remote Sensing Letters, vol. 8, no. 3, pp. 214-223, 2017. https://doi.org/10.1080/2150704X.2016.1258125
  15. M. P. Mathew and T. Y. Mahesh, "Leaf-based disease detection in bell pepper plant using YOLO v5," Signal, Image and Video Processing, vol. 16, no. 841-847, 2022. https://doi.org/10.1007/s11760-021-02024-y
  16. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The pascal visual object classes (VOC) challenge," International Journal of Computer Vision, vol. 88, pp. 303-338, 2010. https://doi.org/10.1007/s11263-009-0275-4
  17. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, "YOLOv4: optimal speed and accuracy of object detection," 2020 [Online]. Available: https://arxiv.org/abs/2004.10934.
  18. A. Howard, M. Sandler, G. Chu, L. C. Chen, B. Chen, M. Tan, et al., "Searching for MobileNetv3," in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, South Korea, 2019, pp. 1314-1324. https://doi.org/10.1109/ICCV.2019.00140
  19. 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," 2017 [Online]. Available: https://arxiv.org/abs/1704.04861.
  20. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetv2: inverted residuals and linear bottlenecks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 4510-4520. https://doi.org/10.1109/CVPR.2018.00474
  21. J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 7132-7141. https://doi.org/10.1109/CVPR.2018.00745
  22. D. Arthur and S. Vassilvitskii, "K-means++ the advantages of careful seeding," in Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, LA, 2007, pp. 1027-1035.
  23. C. Donmez, O. Villi, S. Berberoglu, and A. Cilek, "Computer vision-based citrus tree detection in a cultivated environment using UAV imagery," Computers and Electronics in Agriculture, vol. 187, article no. 106273, 2021. https://doi.org/10.1016/j.compag.2021.106273
  24. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, "SSD: single shot multibox detector," in Computer Vision-ECCV 2016. Cham, Switzerland: Springer, 2016, pp. 21-37. https://doi.org/10.1007/978-3-319-46448-0_2