Cargando…

Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting

Current harvesting robots are limited by low detection rates due to the unstructured and dynamic nature of both the objects and the environment. State-of-the-art algorithms include color- and texture-based detection, which are highly sensitive to the illumination conditions. Deep learning algorithms...

Descripción completa

Detalles Bibliográficos
Autores principales: Arad, Boaz, Kurtser, Polina, Barnea, Ehud, Harel, Ben, Edan, Yael, Ben-Shahar, Ohad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6470490/
https://www.ncbi.nlm.nih.gov/pubmed/30901837
http://dx.doi.org/10.3390/s19061390
_version_ 1783411809214005248
author Arad, Boaz
Kurtser, Polina
Barnea, Ehud
Harel, Ben
Edan, Yael
Ben-Shahar, Ohad
author_facet Arad, Boaz
Kurtser, Polina
Barnea, Ehud
Harel, Ben
Edan, Yael
Ben-Shahar, Ohad
author_sort Arad, Boaz
collection PubMed
description Current harvesting robots are limited by low detection rates due to the unstructured and dynamic nature of both the objects and the environment. State-of-the-art algorithms include color- and texture-based detection, which are highly sensitive to the illumination conditions. Deep learning algorithms promise robustness at the cost of significant computational resources and the requirement for intensive databases. In this paper we present a Flash-No-Flash (FNF) controlled illumination acquisition protocol that frees the system from most ambient illumination effects and facilitates robust target detection while using only modest computational resources and no supervised training. The approach relies on the simultaneous acquisition of two images—with/without strong artificial lighting (“Flash”/“no-Flash”). The difference between these images represents the appearance of the target scene as if only the artificial light was present, allowing a tight control over ambient light for color-based detection. A performance evaluation database was acquired in greenhouse conditions using an eye-in-hand RGB camera mounted on a robotic manipulator. The database includes 156 scenes with 468 images containing a total of 344 yellow sweet peppers. Performance of both color blob and deep-learning detection algorithms are compared on Flash-only and FNF images. The collected database is made public.
format Online
Article
Text
id pubmed-6470490
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-64704902019-04-26 Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting Arad, Boaz Kurtser, Polina Barnea, Ehud Harel, Ben Edan, Yael Ben-Shahar, Ohad Sensors (Basel) Article Current harvesting robots are limited by low detection rates due to the unstructured and dynamic nature of both the objects and the environment. State-of-the-art algorithms include color- and texture-based detection, which are highly sensitive to the illumination conditions. Deep learning algorithms promise robustness at the cost of significant computational resources and the requirement for intensive databases. In this paper we present a Flash-No-Flash (FNF) controlled illumination acquisition protocol that frees the system from most ambient illumination effects and facilitates robust target detection while using only modest computational resources and no supervised training. The approach relies on the simultaneous acquisition of two images—with/without strong artificial lighting (“Flash”/“no-Flash”). The difference between these images represents the appearance of the target scene as if only the artificial light was present, allowing a tight control over ambient light for color-based detection. A performance evaluation database was acquired in greenhouse conditions using an eye-in-hand RGB camera mounted on a robotic manipulator. The database includes 156 scenes with 468 images containing a total of 344 yellow sweet peppers. Performance of both color blob and deep-learning detection algorithms are compared on Flash-only and FNF images. The collected database is made public. MDPI 2019-03-21 /pmc/articles/PMC6470490/ /pubmed/30901837 http://dx.doi.org/10.3390/s19061390 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Arad, Boaz
Kurtser, Polina
Barnea, Ehud
Harel, Ben
Edan, Yael
Ben-Shahar, Ohad
Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title_full Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title_fullStr Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title_full_unstemmed Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title_short Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting
title_sort controlled lighting and illumination-independent target detection for real-time cost-efficient applications. the case study of sweet pepper robotic harvesting
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6470490/
https://www.ncbi.nlm.nih.gov/pubmed/30901837
http://dx.doi.org/10.3390/s19061390
work_keys_str_mv AT aradboaz controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting
AT kurtserpolina controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting
AT barneaehud controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting
AT harelben controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting
AT edanyael controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting
AT benshaharohad controlledlightingandilluminationindependenttargetdetectionforrealtimecostefficientapplicationsthecasestudyofsweetpepperroboticharvesting