Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914877119922176 |
|---|---|
| author | Fawakherji, Mulham Suriani, Vincenzo Nardi, Daniele Bloisi, Domenico Daniele |
| author_facet | Fawakherji, Mulham Suriani, Vincenzo Nardi, Daniele Bloisi, Domenico Daniele |
| contents | The use of deep learning methods for precision farming is gaining increasing interest. However, collecting training data in this application field is particularly challenging and costly due to the need of acquiring information during the different growing stages of the cultivation of interest. In this paper, we present a method for data augmentation that uses two GANs to create artificial images to augment the training data. To obtain a higher image quality, instead of re-creating the entire scene, we take original images and replace only the patches containing objects of interest with artificial ones containing new objects with different shapes and styles. In doing this, we take into account both the foreground (i.e., crop samples) and the background (i.e., the soil) of the patches. Quantitative experiments, conducted on publicly available datasets, demonstrate the effectiveness of the proposed approach. The source code and data discussed in this work are available as open source. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14119 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming Fawakherji, Mulham Suriani, Vincenzo Nardi, Daniele Bloisi, Domenico Daniele Computer Vision and Pattern Recognition Machine Learning The use of deep learning methods for precision farming is gaining increasing interest. However, collecting training data in this application field is particularly challenging and costly due to the need of acquiring information during the different growing stages of the cultivation of interest. In this paper, we present a method for data augmentation that uses two GANs to create artificial images to augment the training data. To obtain a higher image quality, instead of re-creating the entire scene, we take original images and replace only the patches containing objects of interest with artificial ones containing new objects with different shapes and styles. In doing this, we take into account both the foreground (i.e., crop samples) and the background (i.e., the soil) of the patches. Quantitative experiments, conducted on publicly available datasets, demonstrate the effectiveness of the proposed approach. The source code and data discussed in this work are available as open source. |
| title | Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.14119 |