A Deep Learning Architecture for Batch-Mode Fully Automated Field Boundary Detection

Meyer, Lars; Lemarchand, François; Sidiropoulos, Panagiotis

doi:10.5194/isprs-archives-xliii-b3-2020-1009-2020

Cited by 10 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Field boundaries guide sampling and area estimation methods to provide statistically sound estimates of cropped area and are helpful for sub-field assessments of inputs, crop performance, and production (figure 2(c)) [12]. Some studies have used instance segmentation methods from computer vision like Mask R-CNN [13], but most recent work has used semantic segmentation methods like U-Nets followed by post-processing to isolate individual field instances [14].…”

Section: Field Boundary Delineationmentioning

confidence: 99%

Considerations for AI-EO for agriculture in Sub-Saharan Africa

Nakalembe

Kerner

2023

Environ. Res. Lett.

View full text Add to dashboard Cite

With the ever-growing urgency of food insecurity and the threat of climate change, there is increasing interest in using artificial intelligence for Earth observations (AI-EO) for agriculture, particularly in Sub-Saharan Africa (SSA). This paper provides an overview of the primary research areas within AI-EO for agriculture in SSA. %(cropland and crop type classification, field boundary delineation, yield estimation, and pest/disease monitoring). We discuss examples and limitations of current research and opportunities for future work. In addition, we identify ten key considerations for future efforts involving AI-EO for agriculture in SSA.

show abstract

Section: Field Boundary Delineationmentioning

confidence: 99%

Considerations for AI-EO for agriculture in Sub-Saharan Africa

Nakalembe

Kerner

2023

Environ. Res. Lett.

View full text Add to dashboard Cite

show abstract

“…In recent years, the improvement capability of satellite sensors (e.g., Landsat 8, Worldview-3, and PlanetScope) allowed a more precise crop inventory and at higher spatial resolutions. In Meyer et al [25], they investigated the possibility of accurately splitting large areas of land into discrete fields using high-resolution satellite images as well as deep learning algorithms. Similarly, North et al [22] developed an automated method of deriving closed polygons around fields from time-series satellite imagery.…”

Section: Related Workmentioning

confidence: 99%

Estimation of Agricultural Dykelands Cultivated in Nova Scotia Using Land Property Boundaries and Crop Inventory

Bilodeau

Esau

Farooque

et al. 2021

IJGI

View full text Add to dashboard Cite

Dykelands are agricultural ground protected from coastal inundation by dyke infra-structure and constitute some of the most agriculturally productive lands in Nova Scotia. Between 2015 and 2019, Canada’s Annual Crop Inventory was used to characterize and estimate hectares of agricultural dykelands cultivated in Nova Scotia. The number of hectares of wheat, barley, corn, forages and soybeans were compiled for each year and compared to the previous year. This was accomplished using GIS software, satellite images, and geodata from the Nova Scotia’s Land Property Database. Results revealed that from 2015 to 2019, an average of 56% of the dykelands’ total surface was dedicated to the production of field crops (wheat, barley, corn, soybeans) and forage. Results also highlighted the importance of forage production on the dykelands. Forage was the largest commodity grown, representing around 80% of the total crop land area of the agricultural dykelands. Corn and soybeans were the second and third crops of abundance, constituting 12 and 4% of the total crop land area, respectively. This study represents the first attempt to document the number of hectares of the principal crops grown on Nova Scotia’s dykelands using crop inventory and property boundaries. Given the predictions of rising sea levels and the overtopping risks that the dykelands face, this study will facilitate more suitable land-use policies by providing stakeholders with an accurate quantitative assessment of the utilization of agricultural dykelands.

show abstract

Comparison of an Optimised Multiresolution Segmentation Approach with Deep Neural Networks for Delineating Agricultural Fields from Sentinel-2 Images

Tetteh

Schwieder

Erasmi

et al. 2023

PFG

View full text Add to dashboard Cite

Effective monitoring of agricultural lands requires accurate spatial information about the locations and boundaries of agricultural fields. Through satellite imagery, such information can be mapped on a large scale at a high temporal frequency. Various methods exist in the literature for segmenting agricultural fields from satellite images. Edge-based, region-based, or hybrid segmentation methods are traditional methods that have widely been used for segmenting agricultural fields. Lately, the use of deep neural networks (DNNs) for various tasks in remote sensing has been gaining traction. Therefore, to identify the optimal method for segmenting agricultural fields from satellite images, we evaluated three state-of-the-art DNNs, namely Mask R-CNN, U-Net, and FracTAL ResUNet against the multiresolution segmentation (MRS) algorithm, which is a region-based and a more traditional segmentation method. Given that the DNNs are supervised methods, we used an optimised version of the MRS algorithm based on supervised Bayesian optimisation. Monotemporal Sentinel-2 (S2) images acquired in Lower Saxony, Germany were used in this study. Based on the agricultural parcels declared by farmers within the European Common Agricultural Policy (CAP) framework, the segmentation results of each method were evaluated using the F-score and intersection over union (IoU) metrics. The respective average F-score and IoU obtained by each method are 0.682 and 0.524 for Mask R-CNN, 0.781 and 0.646 for U-Net, 0.808 and 0.683 for FracTAL ResUNet, and 0.805 and 0.678 for the optimised MRS approach. This study shows that DNNs, particularly FracTAL ResUNet, can be effectively used for large-scale segmentation of agricultural fields from satellite images.

show abstract

A Deep Learning Architecture for Batch-Mode Fully Automated Field Boundary Detection

Cited by 10 publications

References 18 publications

Considerations for AI-EO for agriculture in Sub-Saharan Africa

Considerations for AI-EO for agriculture in Sub-Saharan Africa

Estimation of Agricultural Dykelands Cultivated in Nova Scotia Using Land Property Boundaries and Crop Inventory

Comparison of an Optimised Multiresolution Segmentation Approach with Deep Neural Networks for Delineating Agricultural Fields from Sentinel-2 Images

Contact Info

Product

Resources

About