- You are here:
-
-
All publications
- A Deep Learning Supported Machine Vision Control System to Precisely Auto-position the Header of a Mechanical Wild Blueberry Harvester with Fruit Height
All publications from your selection
A Deep Learning Supported Machine Vision Control System to Precisely Auto-position the Header of a Mechanical Wild Blueberry Harvester with Fruit Height
Authors: Zeeshan Haydar,
Travis Esau,
Aitazaz Farooque,
Patrick J. Hennessy,
Qamar Zaman,
Kuljeet Grewal,
Farhat Abbas
Identifier: CSBE23135
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Lethbridge 2023
Download RAW file:
DOI:
Description: Lowbush blueberry (Vaccinium angustifolium Ait.) is a major commodity cultivated in Atlantic Canada. An operator of a wild blueberry harvester faces fatigue from manually adjusting the height of the harvester?s head to account for spatial variations in plant height, fruit zone, and field topography. For ease of operation, a deep learning-supported machine vision control system has been developed to detect the fruit height, taking into account the variability of a wild blueberry field's variability and precisely auto-adjust the header picking teeth' position rakes. The OpenCV AI Kit (OAK-D) was used with YOLOv4-Tiny deep learning model using code developed in Python to match the fruit zone to the harvester?s head position. The system accuracy was statistically evaluated with R2 (coefficient of determination) and ? (standard deviation) measured on the difference in distances between the picker teeth and average fruit heights, which were 72, 43% and 0.021, 0.023 m for the auto and manual head adjustment systems, respectively. This innovative system performed well in weed-free areas but required further work to operate in weedy sections of the fields efficiently. Benefits of using this system include automated control of the harvester?s head to match the header picking rake height to the appropriate level within the fruit zone while reducing the operator?s stress.
Keywords: Stereo vision camera, convolutional neural network, harvest efficiency, fruit picking
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2023-07-23
Technical field:
Conference name: CSBE/SCGAB 2023 Annual Conference, Lethbridge, Alberta, 23-26 July 2023.
Session name:
Other information:
Type: Poster
Format:
Publication type: Text.Abstract
Source:
Relation:
Coverage: North_America
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
DOI:
Description: Lowbush blueberry (Vaccinium angustifolium Ait.) is a major commodity cultivated in Atlantic Canada. An operator of a wild blueberry harvester faces fatigue from manually adjusting the height of the harvester?s head to account for spatial variations in plant height, fruit zone, and field topography. For ease of operation, a deep learning-supported machine vision control system has been developed to detect the fruit height, taking into account the variability of a wild blueberry field's variability and precisely auto-adjust the header picking teeth' position rakes. The OpenCV AI Kit (OAK-D) was used with YOLOv4-Tiny deep learning model using code developed in Python to match the fruit zone to the harvester?s head position. The system accuracy was statistically evaluated with R2 (coefficient of determination) and ? (standard deviation) measured on the difference in distances between the picker teeth and average fruit heights, which were 72, 43% and 0.021, 0.023 m for the auto and manual head adjustment systems, respectively. This innovative system performed well in weed-free areas but required further work to operate in weedy sections of the fields efficiently. Benefits of using this system include automated control of the harvester?s head to match the header picking rake height to the appropriate level within the fruit zone while reducing the operator?s stress.
Keywords: Stereo vision camera, convolutional neural network, harvest efficiency, fruit picking
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2023-07-23
Technical field:
Conference name: CSBE/SCGAB 2023 Annual Conference, Lethbridge, Alberta, 23-26 July 2023.
Session name:
Other information:
Type: Poster
Format:
Publication type: Text.Abstract
Source:
Relation:
Coverage: North_America
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
©
2026
CSBE-SCGAB