Machine vision for camera-based horticulture crop growth monitoring

McCarthy, Alison and Hedley, Carolyn and El-Naggar, Ahmed (2017) Machine vision for camera-based horticulture crop growth monitoring. In: International Tri-Conference for Precision Agriculture in 2017 (PA17)/7th Asian-Australasian Conference on Precision Agriculture, 16-18 Oct 2017, Hamilton, New Zealand.

[img]
Preview
Text (Published Version)
7ACPA17_Alison_McCarthy_etal_final.pdf
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
[img]
Preview
Text (Slide Show)
2A4-7ACPA_AlisonMcCarthy.pdf
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
[img]
Preview
Text (Programme - proof of presentation)
PA17_ProgrammeOnly_links_16Nov.pdf

Download (889kB) | Preview
[img]
Preview
Text (Published Proceedings - proof of conference)
ACPA Abstracts 20171010.pdf
Available under License Creative Commons Attribution 4.0.

Download (2MB) | Preview

Abstract

Plant growth and fruiting development monitoring is required for horticulture crop and irrigation management. However, this monitoring is typically manual, labour-intensive and conducted in a limited number of locations in the field which may not represent the whole field. Rapid crop assessment throughout the season can be achieved using machine vision analysis of images captured with cameras. High spatial resolution plant growth and fruiting information can be used for yield estimation and to manage site-specific irrigation and fertiliser application.

Camera-based plant sensing systems have been developed for high spatial resolution data collection from top views of crops. The sensing systems have been installed on overhead irrigation machines. The cameras on the irrigation machine were smartphones with an App installed to capture and upload images and GPS location at a time interval. These cameras automatically captured and uploaded images during irrigation events as the machine traversed the field. Image analysis algorithms have been developed to estimate canopy cover for peas and carrots, and flower counts for peas.

These cameras have been evaluated at sites in Kalbar in South East Queensland, Australia, and Palmerston North, North Island, New Zealand. This paper compares the image analysis results with ground truthing measurements that were collected at approximately weekly intervals at the sites, and electrical conductivity, reflectance, yield and soil type maps.


Statistics for USQ ePrint 33306
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Historic - Institute for Agriculture and the Environment
Faculty/School / Institute/Centre: Historic - Institute for Agriculture and the Environment
Date Deposited: 03 Sep 2019 06:02
Last Modified: 05 Aug 2020 04:16
Uncontrolled Keywords: fruiting monitoring; machine vision; plant sensing systems
Fields of Research (2008): 07 Agricultural and Veterinary Sciences > 0701 Agriculture, Land and Farm Management > 070104 Agricultural Spatial Analysis and Modelling
09 Engineering > 0906 Electrical and Electronic Engineering > 090602 Control Systems, Robotics and Automation
07 Agricultural and Veterinary Sciences > 0703 Crop and Pasture Production > 070302 Agronomy
Fields of Research (2020): 30 AGRICULTURAL, VETERINARY AND FOOD SCIENCES > 3002 Agriculture, land and farm management > 300206 Agricultural spatial analysis and modelling
40 ENGINEERING > 4007 Control engineering, mechatronics and robotics > 400799 Control engineering, mechatronics and robotics not elsewhere classified
30 AGRICULTURAL, VETERINARY AND FOOD SCIENCES > 3004 Crop and pasture production > 300403 Agronomy
Socio-Economic Objectives (2008): D Environment > 96 Environment > 9609 Land and Water Management > 960905 Farmland, Arable Cropland and Permanent Cropland Water Management
Identification Number or DOI: https://doi.org/10.5281/zenodo.893702
URI: http://eprints.usq.edu.au/id/eprint/33306

Actions (login required)

View Item Archive Repository Staff Only