Abstract
With unmanned aerial vehicle (UAV) becoming more accessible, remote sensing using UAVs have garnered a lot of attention. UAVs have applications in traffic management, weather monitoring, precision agriculture, orchard management, etc. Now, it is possible to detect and monitor trees from their canopy with the availability of high spatial resolution images acquired from cameras mounted on UAV. Tree canopy detection and counting has been important in orchard management, forest surveys and inventory, monitoring tree health, tree counting, and so on. Previous studies have focused on usage of deep neural networks for detecting tree canopy and in a few cases, they have delineated the tree canopy masks. However, creating training samples of masks by annotation is an extremely challenging task for two important reasons. Firstly, due to the sheer volume of data required for deep neural networks and the effort required for creating labelled masks through bounding boxes can be manifold. Secondly, resolution of the UAV images and irregular shapes of the tree canopies make it a difficult process to hand draw the masks around the canopies. In this work, a two stage semi-supervised approach for detecting the tree canopy is proposed. The first stage comprises of detecting tree canopy through bounding boxes using RetinaNet, and the second stage finds the tree canopy masks using a combination of thresholded ExGI (excess green index) values, neural networks with back propagation and SLIC (simple linear iterative clustering). The results showed a mean average precision of 90% for tree canopy detection and 65% accuracy for the tree canopy extraction.
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
Similar content being viewed by others
References
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.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems – NIPS’15, vol. 1, pp. 91–99. Cambridge, MA, USA, MIT Press (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol. 9351. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
Santos, A.A.D., et al.: Assessment of cnn-based methods for individual tree detection on images captured by rgb cameras attached to UAVs. Sensors 19(16), 3595 (2019)
Weinstein, B.G., Marconi, S., Bohlman, S., Zare, A., White, E.: Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks. Remote Sensing 11(11), 1309 (2019)
Silva, C.A., et al.: Imputation of individual longleaf pine (Pinus palustris mill.) tree attributes from field and lidar data. Can. J. Remote Sens. 42(5), 554–573 (2016)
Weinstein, B.G., Marconi, S., Bohlman, S.A., Zare, A., White, E.P.: Cross-site learning in deep learning RGB tree crown detection. EcologicalInformatics 56, 101061 (2020)
Roslan, Z., Long, Z.A., Ismail, R.: Individual tree crown detectionusing GAN and RetinaNet on tropical forest. In: 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), pp. 1–7. IEEE (2021)
Adhikari, A., Kumar, M., Agrawal, S., Raghavendra, S.: An integrated object and machine learning approach for tree canopy extraction from UAV datasets. J. Indian Soc. Remote Sens. 49(3), 471–478 (2021)
Guo, Y., et al.: Integrating spectral and textural information for monitoring the growth of pear trees using optical images from the UAV platform. Remote Sens. 13(9), 1795 (2021)
Agarwal, A., Kumar, S., Singh, D.: An adaptive techniqueto detect and remove shadow from drone data. J. Indian Soc. Remote Sens. 49(3), 491–498 (2021)
Woebbecke, D.M., Meyer, G.E., Von Bargen, K., Mortensen, D.A.: Color indices for weed identification under various soil, residue, and lighting conditions. Trans. ASAE 38(1), 259–269 (1995)
Meyer, G.E., Neto, J.C.: Verification of color vegetation indices for automated crop imaging applications. Comput. Electron. Agric. 63(2), 282–293 (2008)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S.: SLIC superpixels. Tech. Rep. 149300, EcolePolytechnique Fédéral de Lausssanne (EPFL) (2010)
Kanezaki, A.: Unsupervised image segmentation by backpropagation. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 1543–1547. IEEE (2018)
Tzutalin. Labelimg. https://github.com/tzutalin/labelImg (2015)
Dutta, A., Zisserman, A.: The via annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2276–2279 (2019)
Micheal, A.A., Vani, K., Sanjeevi, S., Lin, C.-H.: Object detection and tracking with UAV data using deep learning. J. Indian Soc. Remote Sens. 49(3), 463–469 (2020)
Acknowledgements
We are grateful to the International Institute of Information Technology Bangalore (IIITB), India for the infrastructure support. We are thankful to Infosys Foundation for the financial assistance and project grant through the Infosys Foundation Career Development Chair Professor.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, U., Dasgupta, A., Venkata Vamsi Krishna, L.S.N., Chintakunta, P.K. (2022). Towards Semi-supervised Tree Canopy Detection and Extraction from UAV Images. In: Raman, B., Murala, S., Chowdhury, A., Dhall, A., Goyal, P. (eds) Computer Vision and Image Processing. CVIP 2021. Communications in Computer and Information Science, vol 1568. Springer, Cham. https://doi.org/10.1007/978-3-031-11349-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-11349-9_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11348-2
Online ISBN: 978-3-031-11349-9
eBook Packages: Computer ScienceComputer Science (R0)