RECORD
Crop identification using deep learning on LUCAS crop cover photos
Computer Vision and Pattern Recognition · Submitted 8 May 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The proposed methodology shows the possibility for using minimal auxiliary data, outside the images themselves, in order to achieve a M-F1 of 0.817 for labelling between 12 major European crops.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Crop classification via deep learning on ground imagery can deliver timely and accurate crop-specific information to various stakeholders. Dedicated ground-based image acquisition exercises can help to collect data in data scarce regions, improve control on timing of collection, or when study areas are to small to monitor via satellite. Automatic labelling is essential when collecting large volumes of data. One such data collection is the EU's Land Use Cover Area frame Survey (LUCAS), and in particular, the recently published LUCAS Cover photos database. The aim of this paper is to select and publish a subset of LUCAS Cover photos for 12 mature major crops across the EU, to deploy, benchmark, and identify the best configuration of Mobile-net for the classification task, to showcase the possibility of using entropy-based metrics for post-processing of results, and finally to show the applications and limitations of the model in a practical and policy relevant context. In particular, the usefulness of automatically identifying crops on geo-tagged photos is illustrated in the context of the EU's Common Agricultural Policy. The work has produced a dataset of 169,460 images of mature crops for the 12 classes, out of which 15,876 were manually selected as representing a clean sample without any foreign objects or unfavorable conditions. The best performing model achieved a Macro F1 (M-F1) of 0.75 on an imbalanced test dataset of 8,642 photos. Using metrics from information theory, namely - the Equivalence Reference Probability, resulted in achieving an increase of 6%. The most unfavorable conditions for taking such images, across all crop classes, were found to be too early or late in the season. The proposed methodology shows the possibility for using minimal auxiliary data, outside the images themselves, in order to achieve a M-F1 of 0.817 for labelling between 12 major European crops.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Crop classification via deep learning on ground imagery can deliver timely and accurate crop-specific information to various stakeholders. | background 1.00 | 0.07 | 0.06 | hedged possibility 0.88 |
| s1 | Dedicated ground-based image acquisition exercises can help to collect data in data scarce regions, improve control on timing of collection, or when study areas are to small to monitor via satellite. | background 0.98 | 0.08 | 0.02 | hedged possibility 0.84 |
| s2 | Automatic labelling is essential when collecting large volumes of data. | background 0.98 | 0.05 | 0.02 | asserted 1.00 |
| s3 | One such data collection is the EU's Land Use Cover Area frame Survey (LUCAS), and in particular, the recently published LUCAS Cover photos database. | background 0.90 | 0.07 | 0.02 | asserted 0.98 |
| s4 | The aim of this paper is to select and publish a subset of LUCAS Cover photos for 12 mature major crops across the EU, to deploy, benchmark, and identify the best configuration of Mobile-net for the classification task, to showcase the possibility of using entropy-based metrics for post-processing of results, and finally to show the applications and limitations of the model in a practical and policy relevant context. | contribution 1.00 | 0.57 | 0.07 | asserted 0.89 |
| s5 | In particular, the usefulness of automatically identifying crops on geo-tagged photos is illustrated in the context of the EU's Common Agricultural Policy. | interpretation 0.50 | 0.60 | 0.09 | asserted 0.95 |
| s6 | The work has produced a dataset of 169,460 images of mature crops for the 12 classes, out of which 15,876 were manually selected as representing a clean sample without any foreign objects or unfavorable conditions. | contribution 0.57 | 0.96 | 0.06 | asserted 1.00 |
| s7 | The best performing model achieved a Macro F1 (M-F1) of 0.75 on an imbalanced test dataset of 8,642 photos. | result 1.00 | 0.95 | 0.15 | asserted 1.00 |
| s8 | Using metrics from information theory, namely - the Equivalence Reference Probability, resulted in achieving an increase of 6%. | result 0.99 | 0.90 | 0.08 | asserted 1.00 |
| s9 | The most unfavorable conditions for taking such images, across all crop classes, were found to be too early or late in the season. | result 0.99 | 0.93 | 0.04 | asserted 1.00 |
| s10 | The proposed methodology shows the possibility for using minimal auxiliary data, outside the images themselves, in order to achieve a M-F1 of 0.817 for labelling between 12 major European crops. | result 0.88 | 0.90 | 0.46 | hedged possibility 0.62 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Crop classification via deep learning on ground imagery can deliver timely and accurate crop-specific information to various stakeholders. Dedicated ground-based image acquisition exercises can help to collect data in data scarce regions, improve control on timing of collection, or when study areas are to small to monitor via satellite. Automatic labelling is essential when collecting large volumes of data. One such data collection is the EU's Land Use Cover Area frame Survey (LUCAS), and in particular, the recently published LUCAS Cover photos database. The aim of this paper is to select and publish a subset of LUCAS Cover photos for 12 mature major crops across the EU, to deploy, benchmark, and identify the best configuration of Mobile-net for the classification task, to showcase the possibility of using entropy-based metrics for post-processing of results, and finally to show the applications and limitations of the model in a practical and policy relevant context. In particular, the usefulness of automatically identifying crops on geo-tagged photos is illustrated in the context of the EU's Common Agricultural Policy. The work has produced a dataset of 169,460 images of mature crops for the 12 classes, out of which 15,876 were manually selected as representing a clean sample without any foreign objects or unfavorable conditions. The best performing model achieved a Macro F1 (M-F1) of 0.75 on an imbalanced test dataset of 8,642 photos. Using metrics from information theory, namely - the Equivalence Reference Probability, resulted in achieving an increase of 6%. The most unfavorable conditions for taking such images, across all crop classes, were found to be too early or late in the season. The proposed methodology shows the possibility for using minimal auxiliary data, outside the images themselves, in order to achieve a M-F1 of 0.817 for labelling between 12 major European crops.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 2 sentences without a confident label
Cites as background 1 paper
-
A leading architecture in this regard is MobileNet ( [ref] ), of which there are third generation flavours ( [ref] ), which in turn are both significantly smaller than and equal in performance to the previous ones ( [ref] ).
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications · Introduction · 0.81
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.