Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions
This paper presents a rule-based methodology for dynamic viewpoint selection for maturity classification of red and yellow sweet peppers. The method makes an online decision to capture an additional next-best viewpoint based on an economic analysis that considers potential misclassification and robo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/9/4414 |
_version_ | 1797505705184329728 |
---|---|
author | Rick van Essen Ben Harel Gert Kootstra Yael Edan |
author_facet | Rick van Essen Ben Harel Gert Kootstra Yael Edan |
author_sort | Rick van Essen |
collection | DOAJ |
description | This paper presents a rule-based methodology for dynamic viewpoint selection for maturity classification of red and yellow sweet peppers. The method makes an online decision to capture an additional next-best viewpoint based on an economic analysis that considers potential misclassification and robot operational costs. The next-best viewpoint is selected based on color variations on the pepper. Peppers were classified into mature and immature using a random forest classifier based on principle components of various color features derived from an RGB-D camera. The method first attempts to classify maturity based on a single viewpoint. An additional viewpoint is acquired and added to the point cloud only when it is deemed profitable. The methodology was evaluated using leave-one-out cross-validation on datasets of 69 red and 70 yellow sweet peppers from three different maturity stages. Classification accuracy was increased by 6% and 5% using dynamic viewpoint selection along with 52% and 12% decrease in economic costs for red and yellow peppers, respectively, compared to using a single viewpoint. Sensitivity analyses were performed for misclassification and robot operational costs. |
first_indexed | 2024-03-10T04:22:11Z |
format | Article |
id | doaj.art-b055e234969f4d1bb69e57d3ae25bea8 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T04:22:11Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-b055e234969f4d1bb69e57d3ae25bea82023-11-23T07:48:49ZengMDPI AGApplied Sciences2076-34172022-04-01129441410.3390/app12094414Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic DecisionsRick van Essen0Ben Harel1Gert Kootstra2Yael Edan3Farm Technology Group, Wageningen University and Research, 6700 AA Wageningen, The NetherlandsDepartment of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva 8410501, IsraelFarm Technology Group, Wageningen University and Research, 6700 AA Wageningen, The NetherlandsDepartment of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva 8410501, IsraelThis paper presents a rule-based methodology for dynamic viewpoint selection for maturity classification of red and yellow sweet peppers. The method makes an online decision to capture an additional next-best viewpoint based on an economic analysis that considers potential misclassification and robot operational costs. The next-best viewpoint is selected based on color variations on the pepper. Peppers were classified into mature and immature using a random forest classifier based on principle components of various color features derived from an RGB-D camera. The method first attempts to classify maturity based on a single viewpoint. An additional viewpoint is acquired and added to the point cloud only when it is deemed profitable. The methodology was evaluated using leave-one-out cross-validation on datasets of 69 red and 70 yellow sweet peppers from three different maturity stages. Classification accuracy was increased by 6% and 5% using dynamic viewpoint selection along with 52% and 12% decrease in economic costs for red and yellow peppers, respectively, compared to using a single viewpoint. Sensitivity analyses were performed for misclassification and robot operational costs.https://www.mdpi.com/2076-3417/12/9/4414dynamic viewpoint selectionnext-best-view planningeconomic analysissweet peppersmaturity classificationmachine vision |
spellingShingle | Rick van Essen Ben Harel Gert Kootstra Yael Edan Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions Applied Sciences dynamic viewpoint selection next-best-view planning economic analysis sweet peppers maturity classification machine vision |
title | Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions |
title_full | Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions |
title_fullStr | Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions |
title_full_unstemmed | Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions |
title_short | Dynamic Viewpoint Selection for Sweet Pepper Maturity Classification Using Online Economic Decisions |
title_sort | dynamic viewpoint selection for sweet pepper maturity classification using online economic decisions |
topic | dynamic viewpoint selection next-best-view planning economic analysis sweet peppers maturity classification machine vision |
url | https://www.mdpi.com/2076-3417/12/9/4414 |
work_keys_str_mv | AT rickvanessen dynamicviewpointselectionforsweetpeppermaturityclassificationusingonlineeconomicdecisions AT benharel dynamicviewpointselectionforsweetpeppermaturityclassificationusingonlineeconomicdecisions AT gertkootstra dynamicviewpointselectionforsweetpeppermaturityclassificationusingonlineeconomicdecisions AT yaeledan dynamicviewpointselectionforsweetpeppermaturityclassificationusingonlineeconomicdecisions |