Abstract
Soybean and cotton are major drivers of many countries' agricultural sectors, offering substantial economic returns but also facing persistent challenges from volunteer plants and weeds that hamper sustainable management. Effectively controlling volunteer plants and weeds demands advanced recognition strategies that can identify these amidst complex crop canopies. While deep learning methods have demonstrated promising results for leaf-level detection and segmentation, existing datasets often fail to capture the complexity of real-world agricultural fields. To address this, we collected 640 high-resolution images from a commercial farm spanning multiple growth stages, weed pressures, and lighting variations. Each image is annotated at the leaf-instance level, with 7,221 soybean and 5,190 cotton leaves labeled via bounding boxes and segmentation masks, capturing overlapping foliage, small leaf size, and morphological similarities. We validate this dataset using YOLO11, demonstrating state-of-the-art performance in accurately identifying and segmenting overlapping foliage. Our publicly available dataset supports advanced applications such as selective herbicide spraying and pest monitoring and can foster more robust, data-driven strategies for soybean-cotton management.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 4
Claim · model-written summary
The dataset comprises 640 high-resolution field images of soybean and cotton from a commercial farm.
- Taxon
- Soybean and cotton
Gossypium hirsutum
Glycine maxe0 - Outcome
- high-resolution imagese2
- Value
- 640e2
- Setting
- commercial farme2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Soybean and cotton are major drivers of many countries' agricultural sectors”
e2“we collected 640 high-resolution images from a commercial farm spanning multiple growth stages, weed pressures, and lighting variations”
Claim · model-written summary
The dataset contains 7,221 annotated soybean leaves.
- Taxon
- soybeanGlycine maxe1
- Outcome
- leaves labeled via bounding boxes and segmentation maskse1
- Value
- 7,221e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“with 7,221 soybean and 5,190 cotton leaves labeled via bounding boxes and segmentation masks”
Claim · model-written summary
The dataset contains 5,190 annotated cotton leaves.
- Taxon
- cottonGossypium hirsutume1
- Outcome
- leaves labeled via bounding boxes and segmentation maskse1
- Value
- 5,190e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“with 7,221 soybean and 5,190 cotton leaves labeled via bounding boxes and segmentation masks”
Claim · model-written summary
YOLO11 trained on the dataset shows state-of-the-art performance in identifying and segmenting overlapping soybean and cotton foliage.
- Taxon
- Soybean and cottonGossypium hirsutumGlycine maxe0
- Outcome
- identifying and segmenting overlapping foliagee3
- Comparator
- state-of-the-arte3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Soybean and cotton are major drivers of many countries' agricultural sectors”
e3“We validate this dataset using YOLO11, demonstrating state-of-the-art performance in accurately identifying and segmenting overlapping foliage”