Dataset Ninja LogoDataset Ninja:

Dataset of Annotated Food Crops and Weed Images Dataset

117621
Tagagriculture
Taskobject detection
Release YearMade in 2021
LicenseCC BY 4.0
Download367 MB

Introduction #

Released 2021-04-26 ·Kaspars Sudars, Janis Jasko, Ivars Namatevset al.

The Dataset of Annotated Food Crops and Weed Images offers a comprehensive look at food crops and weeds in their early seedling stages. With 1,118 images and 7,853 manual annotations, it neatly classifies them into two primary categories: weed and crop. The dataset was collected in several locations in Latvia and describes eight weed and six food species.

The species of the food crops were chosen based on their popularity among consumers in Latvia and the necessity to implement intensive weed management solutions. Two types of images are included in data set: images of food crops and weeds that have been cultivated in vegetation pots in controlled greenhouse conditions; images of food crops and weeds from open field conditions. Images of plants from greenhouse were taken at the Scientific Institute for Plant Protection Research “Agrihorts”, University of Life Sciences and Technologies of Latvia, Jelgava, Latvia. Images from field conditions are from three locations in Latvia: Kekava, Rujiena, and Krimulda. The digital images were captured with perspective projection over plants.

To build the dataset, common weed species found in vegetable fields were selected, 8 weeds: goosefoot (Chenopodium album), catchweed (Galium aparine), field pennycress (Thlaspi arvense), shepherd’s purse (Capsella bursa-pastoris), field chamomile (Matricaria perforata), wild buckwheat (Polygonum convolvulus), field pansy (Viola arvensis), quickweed (Galinsoga parviflora). There were 6 food crops selected: beetroot (Beta vulgaris), carrot (Daucus carota var. sativus), zucchini (Cucurbita pepo subsp. pepo), pumpkin (Cucurbita pepo), radish (Raphanus sativus var. sativus), black radish (Raphanus sativus var. niger).

Abbreviation Taxonomic classification Family Common name Class
CA Chenopodium album L. Amaranthaceae Goosefoot Weed Weed
GA Galium aparine Rubiaceae Catchweed Weed Weed
TA Thlaspi arvense Brassicaceae Field pennycress Weed
CB Capsella bursa-pastoris Brassicaceae Shepherd’s purse Weed
MI Matricaria perforata Asteraceae Field chamomile Weed
PC Polygonum convolvulus Polygonaceae Wild buckwheat Weed
VA Viola arvensis Violaceae Field pansy Weed
GP Galinsoga parviflora Asteraceae Quickweed Weed
BV Beta vulgaris Amaranthaceae Common beet Crop
DC Daucus carota var. sativus Apiaceae Carrot Crop
CPS Cucurbita pepo subsp. pepo Cucurbitaceae Zucchini Crop
CP Cucurbita pepo Cucurbitaceae Pumpkin Crop
RSS Raphanus sativus var. sativus Brassicaceae Radish Crop
RSN Raphanus sativus var. niger Brassicaceae Black radish Crop

List of food crops and weed species available in the dataset.

In a greenhouse, plants were grown in vegetation pots under natural and artificial light. The peat substrate was used for soil preparation with such characteristics: pH 6.0, moisture content <65%, peat fraction <20.0 mm, N 12.0%, P₂O₅ 14.0%, K₂O 24.0%, Te 1.0 kg m³. In each vegetation pot, the seeds of the plants were sown in one to two rows at a distance between them of 2.0 – 5.0 cm. The seedling boxes were watered once to twice per week. Temperature was set to +20.0 °C daytime (8:00 a.m. – 8:00 p.m.), and +15.0 °C during the night (8:00 p.m. – 8:00 a.m.), humidity <50%. Additional to natural light, LED lamps (Philips Lightning IBRS, 180W) were used for plant cultivation with illumination period from 6:00 a.m. – 8:00 p.m. Photos of vegetation boxes were taken with additional light and a three-point supporting photostat. A distance of 30 cm was set from the lens of the camera to the surface of the vegetation box. Once a day, images of plants were taken starting from the first stage of the plant development.

Canon EOS 800D and Sony W800 digital cameras and Intel RealSense D435 cameras were used to take photos. An Intel RealSense D435 camera and Sony W800 digital camera were used to acquire images in field conditions, but Canon EOS 800D digital camera was used in a controlled environment.

Images of plants in field conditions were taken in the organic vegetable farms in three locations specified above before weeding activities carried out by farmers. To capture images a platform mounted on four wheels was constructed. A digital camera was attached in the middle of the platform with the lens directed downwards. The platform was moved across the field in different directions to take photos of the plants. Afterwards, weeds and crops at early growth stages were manually marked in the pictures with ground truth bounding boxes. All raw images were annotated by human experts.

ExpandExpand
Dataset LinkHomepageDataset LinkResearch Paper

Summary #

Dataset of Annotated Food Crops and Weed Images is a dataset for an object detection task. It is used in the agricultural industry.

The dataset consists of 1176 images with 7853 labeled objects belonging to 2 different classes including weed and crop.

Images in the Dataset of Annotated Food Crops and Weed Images dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are no pre-defined train/val/test splits in the dataset. The dataset was released in 2021 by the Institute of Electronics and Computer Science, Latvia and Latvia University of Life Sciences and Technologies.

Dataset Poster

Explore #

Dataset of Annotated Food Crops and Weed Images dataset has 1176 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.

OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
OpenSample annotation mask from Dataset of Annotated Food Crops and Weed ImagesSample image from Dataset of Annotated Food Crops and Weed Images
👀
Have a look at 1176 images
View images along with annotations and tags, search and filter by various parameters

Class balance #

There are 2 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.

Search
Rows 1-2 of 2
Class
Images
Objects
Count on image
average
Area on image
average
weed
rectangle
1116
7565
6.78
1.19%
crop
rectangle
60
288
4.8
3.9%

Co-occurrence matrix #

Co-occurrence matrix is an extremely valuable tool that shows you the images for every pair of classes: how many images have objects of both classes at the same time. If you click any cell, you will see those images. We added the tooltip with an explanation for every cell for your convenience, just hover the mouse over a cell to preview the description.

Images #

Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.

Object distribution #

Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.

Class sizes #

The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.

Search
Rows 1-2 of 2
Class
Object count
Avg area
Max area
Min area
Min height
Min height
Max height
Max height
Avg height
Avg height
Min width
Min width
Max width
Max width
weed
rectangle
7565
0.18%
4.79%
0%
1px
0.13%
210px
28%
35px
4.93%
2px
0.2%
240px
21.6%
crop
rectangle
288
0.81%
28.45%
0.03%
7px
1.3%
431px
57.47%
45px
8.16%
8px
1%
495px
49.5%

Spatial Heatmap #

The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.

Spatial Heatmap

Objects #

Table contains all 7853 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.

Search
Rows 1-10 of 7853
Object ID
Class
Image name
click row to open
Image size
height x width
Height
Height
Width
Width
Area
1
weed
rectangle
34241.jpg
720 x 1280
15px
2.08%
25px
1.95%
0.04%
2
weed
rectangle
34241.jpg
720 x 1280
20px
2.78%
30px
2.34%
0.07%
3
weed
rectangle
34241.jpg
720 x 1280
36px
5%
31px
2.42%
0.12%
4
weed
rectangle
34241.jpg
720 x 1280
35px
4.86%
29px
2.27%
0.11%
5
weed
rectangle
34241.jpg
720 x 1280
45px
6.25%
32px
2.5%
0.16%
6
weed
rectangle
34241.jpg
720 x 1280
41px
5.69%
66px
5.16%
0.29%
7
weed
rectangle
IMG_6043.JPG
750 x 1000
40px
5.33%
20px
2%
0.11%
8
weed
rectangle
IMG_6043.JPG
750 x 1000
24px
3.2%
25px
2.5%
0.08%
9
weed
rectangle
IMG_6043.JPG
750 x 1000
28px
3.73%
25px
2.5%
0.09%
10
weed
rectangle
IMG_6043.JPG
750 x 1000
25px
3.33%
24px
2.4%
0.08%

License #

Dataset of Annotated Food Crops and Weed Images is under CC BY 4.0 license.

Source

Citation #

If you make use of the Dataset of Annotated Food Crops and Weed Images data, please cite the following reference:

@article{SUDARS2020105833,
  title = {Dataset of annotated food crops and weed images for robotic computer vision control},
  journal = {Data in Brief},
  volume = {31},
  pages = {105833},
  year = {2020},
  issn = {2352-3409},
  doi = {https://doi.org/10.1016/j.dib.2020.105833},
  url = {https://www.sciencedirect.com/science/article/pii/S2352340920307277},
  author = {Kaspars Sudars and Janis Jasko and Ivars Namatevs and Liva Ozola and Niks Badaukis},
}

Source

If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:

@misc{ visualization-tools-for-dataset-of-annotated-food-crops-and-weed-images-dataset,
  title = { Visualization Tools for Dataset of Annotated Food Crops and Weed Images Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/dataset-of-annotated-food-crops-and-weed-images } },
  url = { https://datasetninja.com/dataset-of-annotated-food-crops-and-weed-images },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { jun },
  note = { visited on 2024-06-25 },
}

Download #

Dataset Dataset of Annotated Food Crops and Weed Images can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='Dataset of Annotated Food Crops and Weed Images', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here.

. . .

Disclaimer #

Our gal from the legal dep told us we need to post this:

Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.

You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.