Abstract
The plant community composition is an essential indicator of environmental changes and is, for this reason, usually analyzed in ecological field studies in terms of the so-called plant cover. The manual acquisition of this kind of data is time-consuming, laborious, and prone to human error. Automated camera systems can collect high-resolution images of the surveyed vegetation plots at a high frequency. In combination with subsequent algorithmic analysis, it is possible to objectively extract information on plant community composition quickly and with little human effort. An automated camera system can easily collect the large amounts of image data necessary to train a Deep Learning system for automatic analysis. However, due to the amount of work required to annotate vegetation images with plant cover data, only few labeled samples are available. As automated camera systems can collect many pictures without labels, we introduce an approach to interpolate the sparse labels in the collected vegetation plot time series down to the intermediate dense and unlabeled images to artificially increase our training dataset to seven times its original size. Moreover, we introduce a new method we call Monte-Carlo Cropping. This approach trains on a collection of cropped parts of the training images to deal with high-resolution images efficiently, implicitly augment the training images, and speed up training. We evaluate both approaches on a plant cover dataset containing images of herbaceous plant communities and find that our methods lead to improvements in the species, community, and segmentation metrics investigated.
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
Notes
References
Andrzejak, M., Korell, L., Auge, H., Knight, T.M.: Effects of climate change and pollen supplementation on the reproductive success of two grassland plant species. Ecol. Evol. 12(1), e8501 (2022)
Bolzano, B.: Beyträge zu einer begründeteren Darstellung der Mathematik, vol. 1. Im Verlage bey Caspar Widtmann (1810)
Bruelheide, H., et al.: Global trait-environment relationships of plant communities. Nat. Ecol. Evol. 2(12), 1906–1917 (2018)
Cheng, B., et al.: Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12475–12485 (2020)
Cui, Y., Song, Y., Sun, C., Howard, A., Belongie, S.: Large scale fine-grained categorization and domain-specific transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4109–4118 (2018)
Evans, M.J., Rosenthal, J.S.: Probability and Statistics: The Science of Uncertainty. Macmillan, New York (2004)
Gerstner, K., Dormann, C.F., Stein, A., Manceur, A.M., Seppelt, R.: Editor’s choice: review: effects of land use on plant diversity-a global meta-analysis. J. Appl. Ecol. 51(6), 1690–1700 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Helm, J., Dutoit, T., Saatkamp, A., Bucher, S.F., Leiterer, M., Römermann, C.: Recovery of mediterranean steppe vegetation after cultivation: legacy effects on plant composition, soil properties and functional traits. Appl. Veg. Sci. 22(1), 71–84 (2019)
Hill, M.O., Gauch, H.G.: Detrended correspondence analysis: an improved ordination technique. In: van der Maarel, E. (ed.) Classification and ordination. AIVS, vol. 2, pp. 47–58. Springer, Dordrecht (1980). https://doi.org/10.1007/978-94-009-9197-2_7
Kahn, J., Lee, A., Hannun, A.: Self-training for end-to-end speech recognition. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7084–7088. IEEE (2020)
Körschens, M., Bodesheim, P., Denzler, J.: Beyond global average pooling: alternative feature aggregations for weakly supervised localization. In: VISIGRAPP (2022)
Körschens, M.: Weakly supervised segmentation pretraining for plant cover prediction. In: Bauckhage, C., Gall, J., Schwing, A. (eds.) DAGM GCPR 2021. LNCS, vol. 13024, pp. 589–603. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-92659-5_38
Körschens, M., Bodesheim, P., Römermann, C., Bucher, S.F., Ulrich, J., Denzler, J.: Towards confirmable automated plant cover determination. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12540, pp. 312–329. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65414-6_22
Li, C., et al.: Yolov6 v3. 0: a full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)
Li, S., et al.: Efficient multi-order gated aggregation network. arXiv preprint arXiv:2211.03295 (2022)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117–2125 (2017)
Liu, H., et al.: Shifting plant species composition in response to climate change stabilizes grassland primary production. Proc. Natl. Acad. Sci. 115(16), 4051–4056 (2018)
Lloret, F., Peñuelas, J., Prieto, P., Llorens, L., Estiarte, M.: Plant community changes induced by experimental climate change: seedling and adult species composition. Perspect. Plant Ecol. Evol. Syst. 11(1), 53–63 (2009)
Rosenzweig, C., Casassa, G., Karoly, D.J., et al.: Assessment of observed changes and responses in natural and managed systems. Climate Change 2007: Impacts, Adaptation and Vulnerability. Contribution of Working Group II to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change, pp. 79–131 (2007)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Scudder, H.: Probability of error of some adaptive pattern-recognition machines. IEEE Trans. Inf. Theory 11(3), 363–371 (1965)
Souza, L., Zelikova, T.J., Sanders, N.J.: Bottom-up and top-down effects on plant communities: nutrients limit productivity, but insects determine diversity and composition. Oikos 125(4), 566–575 (2016)
Ulrich, J., et al.: Invertebrate decline leads to shifts in plant species abundance and phenology. Front. Plant Sci. 11, 1410 (2020)
Wang, W., et al.: Internimage: exploring large-scale vision foundation models with deformable convolutions. arXiv preprint arXiv:2211.05778 (2022)
Yuan, Y., Chen, X., Chen, X., Wang, J.: Segmentation transformer: object-contextual representations for semantic segmentation. arXiv preprint arXiv:1909.11065 (2019)
Zhang, H., Cissé, M., Dauphin, Y., Lopez-Paz, D.: mixup: beyond empirical risk minimization. ArXiv abs/1710.09412 (2017)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929 (2016)
Acknowledgements
Matthias Körschens thanks the Carl Zeiss Foundation for the financial support. We thank Alban Gebler for enabling the image collection process in the iDiv EcoTron and Josephine Ulrich for the data collection. We acknowledge funding from the German Research Foundation (DFG) via the German Centre for Integrative Biodiversity research (iDiv) Halle-Jena-Leipzig (FZT 118) for the support of the FlexPool project PhenEye (09159751).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Körschens, M., Bucher, S.F., Römermann, C., Denzler, J. (2024). Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping. In: Köthe, U., Rother, C. (eds) Pattern Recognition. DAGM GCPR 2023. Lecture Notes in Computer Science, vol 14264. Springer, Cham. https://doi.org/10.1007/978-3-031-54605-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-54605-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54604-4
Online ISBN: 978-3-031-54605-1
eBook Packages: Computer ScienceComputer Science (R0)