• Corpus ID: 236987105

Presenting an extensive lab- and field-image dataset of crops and weeds for computer vision tasks in agriculture

  title={Presenting an extensive lab- and field-image dataset of crops and weeds for computer vision tasks in agriculture},
  author={Michael A. Beck and Chen-Yi Liu and Christopher Paul Bidinosti and Christopher J. Henry and Cara M. Godee and Manisha Ajmani},
We present two large datasets of labelled plant-images that are suited towards the training of machine learning and computer vision models. The first dataset encompasses as the day of writing over 1.2 million images of indoorgrown crops and weeds common to the Canadian Prairies and many US states. The second dataset consists of over 540,000 images of plants imaged in farmland. All indoor plant images are labelled by species and we provide rich metadata on the level of individual images. This… 

Figures and Tables from this paper


Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images
This paper proposes a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images that is comparable to traditional supervised training data labeling.
Analysis of Morphology-Based Features for Classification of Crop and Weeds in Precision Agriculture
Determining the types of vegetation present in an image is a core step in many precision agriculture tasks. In this letter, we focus on pixel-based approaches for classification of crops versus
Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review
This work presents a systematic review that aims to identify the applicability of computer vision in precision agriculture for the production of the five most produced grains in the world: maize, rice, wheat, soybean, and barley.
Deep learning in agriculture: A survey
A survey of 40 research efforts that employ deep learning techniques, applied to various agricultural and food production challenges indicates that deep learning provides high accuracy, outperforming existing commonly used image processing techniques.
Controlled comparison of machine vision algorithms for Rumex and Urtica detection in grassland
  • A. Binch, C. Fox
  • Engineering, Computer Science
    Comput. Electron. Agric.
  • 2017
A definitive, large-scale independent study of all major known grassland weed removal methods evaluated on a new standardised data set under a wider range of environment conditions, finding the most accurate method to use linear binary patterns together with a support vector machine.
A Survey of Ranging and Imaging Techniques for Precision Agriculture Phenotyping
A survey of the state-of-the-art in optical visible and near-visible spectrum sensors and techniques to estimate phenotyping variables from intensity, spectral, and volumetric measurements is presented.
Digital image processing techniques for detecting, quantifying and classifying plant diseases
A survey on methods that use digital image processing techniques to detect, quantify and classify plant diseases from digital images in the visible spectrum, providing a comprehensive and accessible overview of this important field of research.
3-D Imaging Systems for Agricultural Applications—A Review
The aim of this review paper is to investigate the state-of-the-art of 3-D vision systems in agriculture, and the role and value that only3-D data can have to provide information about environmental structures based on the recent progress in optical 3- D sensors.
Citizen crowds and experts: observer variability in image-based plant phenotyping
While expertise of the observer plays a role, if sufficient statistical power is present, a collection of non-experienced users and even citizens can be included in image-based phenotyping annotation tasks as long they are suitably designed.
Image Analysis in Plant Sciences: Publish Then Perish.
  • G. Lobet
  • Biology, Medicine
    Trends in plant science
  • 2017
The current state of the field is presented, based on data from the plant-image-analysis.org database, and the challenges faced by its community are identified and workable ways of improvement are proposed.