Abstract
Weed detection is a challenging case within object detection as the weed targets do not generally strike out from the background in terms of color. This paper investigates how the density of structural features can be used to assist the training process of a Deep-Learning-based object detector. SIFT keypoint density is used to create overlay masks to augment images, emphasizing low-density areas—typically corresponding to weed plants. Our method is shown to improve detection \(mAP_{.5:.05:.95}\) on the YOLOR-CSP detector by up to 0.0215.
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
Ahmed, F., Kabir, M.H., Bhuyan, S., Bari, H., Hossain, E.: Automated weed classification with local pattern-based texture descriptors. Int. Arab J. Inf. Technol. 11, 87–94 (2014)
Anken, T., Šeatović, D., Holpp, M., Venn, W., Kutterer, H.: Automatic detection of broad-leaved dock in grassland (2010)
Binch, A., Cooke, N., Fox, C.W.: Rumex and Urtica detection in grassland by UAV. In: 14th International Conference on Precision Agriculture (2018)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934 [cs, eess] (2020)
Choi, J., Lee, C., Lee, D., Jung, H.: SalfMix: a novel single image-based data augmentation technique using a saliency map. Sensors 21(24), 8444 (2021). https://doi.org/10.3390/s21248444, https://www.mdpi.com/1424-8220/21/24/8444
Dürr, L., Anken, T., Bollhalder, H., Sauter, J., Burri, K.G., Kuhn, D.: Machine vision detection and microwave-based elimination of Rumex obtusifolius L. on grassland (2008)
Šeatović, D., Winterthur, Z., Switzerland: 3D-object recognition, localization and treatment of Rumex obtusifolius in its natural environment. In: International Conference on Precision Agriculture (2008)
van Evert, F.K., Polder, G., van der Heijden, G.W.A.M., Kempenaar, C., Lotz, L.A.P.: Real-time vision-based detection of Rumex obtusifolius in grassland. Weed Res. 49(2), 164–174 (2009)
FAO: fAO. FAOSTAT Statistical Database. License: CC BY-NC-SA 3.0 IGO (2021). https://www.fao.org/faostat/en/. Accessed 04 July 2022
Güldenring, R., Boukas, E., Ravn, O., Nalpantidis, L.: Few-leaf learning: weed segmentation in grasslands. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2021)
Güldenring, R., van Evert, F.K., Nalpantidis, L.: RumexWeeds: a grassland dataset for agricultural robotics. J. Field Robot. (2023). https://doi.org/10.1002/rob.22196, https://onlinelibrary.wiley.com/doi/abs/10.1002/rob.22196
Güldenring, R., Nalpantidis, L.: Self-supervised contrastive learning on agricultural images. Comput. Electron. Agric. 191, 106510 (2021)
Johnson, Q., VanGessel, M., Taylor, R.W.: Pasture and hay weed management guide delaware 2015. Technical report, University of Delaware (2015). https://s3.amazonaws.com/udextension/ag/files/2015/01/PHWeedguide.pdf
Kounalakis, T., Triantafyllidis, G.A., Nalpantidis, L.: Weed recognition framework for robotic precision farming. In: 2016 IEEE International Conference on Imaging Systems and Techniques (IST), pp. 466–471 (2016). https://doi.org/10.1109/IST.2016.7738271
Kounalakis, T., Triantafyllidis, G.A., Nalpantidis, L.: Image-based recognition framework for robotic weed control systems. Multimed. Tools Appl. 77(8), 9567–9594 (2018)
Kounalakis, T., Triantafyllidis, G.A., Nalpantidis, L.: Deep learning-based visual recognition of Rumex for robotic precision farming. Comput. Electron. Agric. 165, 104973 (2019)
Lam, O.H.Y., et al.: An open source workflow for weed mapping in native grassland using unmanned aerial vehicle: using Rumex obtusifolius as a case study. Eur. J. Remote Sens. 54(sup1), 71–88 (2021)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157. IEEE (1999)
Polder, G., et al.: Weed detection using textural image analysis. in: EFITA/ WCCA Conference (2007)
Schori, D., Anken, T., Šeatović, D.: Using fully convolutional networks for Rumex obtusifolius segmentation, a preliminary report. In: 2019 International Symposium ELMAR, pp. 119–122 (2019)
Uddin, A.F.M.S., Monira, M.S., Shin, W., Chung, T., Bae, S.H.: SaliencyMix: a saliency guided data augmentation strategy for better regularization (2021). arXiv:2006.01791 [cs, stat]
Valente, J., Doldersum, M., Roers, C., Kooistra, L.: Detecting Rumex obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. ISPRS Ann. Photogram. Remote Sens. Spat. Inf. Sci. IV-2/W5, 179–185 (2019)
Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: You only learn one representation: unified network for multiple tasks. arXiv preprint arXiv:2105.04206 (2021)
Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: You only learn one representation: unified network for multiple tasks. arXiv:2105.04206 [cs] (2021)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features (2019)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization (2018)
Zhang, W., et al.: Broad-leaf weed detection in pasture. In: 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), pp. 101–105 (2018)
Acknowledgements
This work has been supported by the European Commission and European GNSS Agency through the project “Galileo-assisted robot to tackle the weed Rumex obtusifolius and increase the profitability and sustainability of dairy farming (GALIRUMI)”, H2020-SPACE-EGNSS-2019-870258.
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
Schmidt, P., Güldenring, R., Nalpantidis, L. (2023). SIFT-Guided Saliency-Based Augmentation for Weed Detection in Grassland Images: Fusing Classic Computer Vision with Deep Learning. In: Christensen, H.I., Corke, P., Detry, R., Weibel, JB., Vincze, M. (eds) Computer Vision Systems. ICVS 2023. Lecture Notes in Computer Science, vol 14253. Springer, Cham. https://doi.org/10.1007/978-3-031-44137-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-44137-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44136-3
Online ISBN: 978-3-031-44137-0
eBook Packages: Computer ScienceComputer Science (R0)