| Title: |
Advancing precision agriculture: domain-specific augmentations and robustness testing for convolutional neural networks in precision spraying evaluation |
| Authors: |
Rogers, H; De La Iglesia, B; Zebin, T; Cielniak, G; Magri, B |
| Publisher Information: |
Springer Nature |
| Publication Year: |
2024 |
| Collection: |
Brunel University London: Brunel University Research Archive (BURA) |
| Subject Terms: |
agri-Robotics; computer vision; data augmentation; XAI |
| Description: |
Data availability: The data currently are unavailable. Reason for Unavailability: We would like to refine the dataset and then open source in future. The data were also collected on a proprietary system. ; Modern agriculture relies heavily on the precise application of chemicals such as fertilisers, herbicides, and pesticides, which directly affect both crop yield and environmental footprint. Therefore, it is crucial to assess the accuracy of precision sprayers regarding the spatial location of spray deposits. However, there is currently no fully automated evaluation method for this. In this study, we collected a novel dataset from a precision spot spraying system to enable us to classify and detect spray deposits on target weeds and non-target crops. We employed multiple deep convolutional backbones for this task; subsequently, we have proposed a robustness testing methodology for evaluation purposes. We experimented with two novel data augmentation techniques: subtraction and thresholding which enhanced the classification accuracy and robustness of the developed models. On average, across nine different tests and four distinct convolutional neural networks, subtraction improves robustness by 50.83%, and thresholding increases by 42.26% from a baseline. Additionally, we have presented the results from a novel weakly supervised object detection task using our dataset, establishing a baseline Intersection over Union score of 42.78%. Our proposed pipeline includes an explainable artificial intelligence stage and provides insights not only into the spatial location of the spray deposits but also into the specific filtering methods within that spatial location utilised for classification. ; Engineering and Physical Sciences Research Council [EP/S023917/1]. This work is also supported by Syngenta as the Industrial partner. The research presented in this paper was carried out on the High-Performance Computing Cluster supported by the Research and Specialist Computing Support service at the University of East Anglia. |
| Document Type: |
article in journal/newspaper |
| File Description: |
20211 - 20229; Print-Electronic |
| Language: |
unknown |
| Relation: |
Neural Computing and Applications; https://bura.brunel.ac.uk/handle/2438/29935 |
| DOI: |
10.1007/s00521-024-10142-0 |
| Availability: |
https://bura.brunel.ac.uk/handle/2438/29935; https://doi.org/10.1007/s00521-024-10142-0 |
| Rights: |
Attribution 4.0 International ; https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0legalcode.en |
| Accession Number: |
edsbas.D7C38C52 |
| Database: |
BASE |