Next Article in Journal
Design of an Embedded Multi-Camera Vision System—A Case Study in Mobile Robotics
Previous Article in Journal
Workspace Limiting Strategy for 6 DOF Force Controlled PKMs Manipulating High Inertia Objects
Previous Article in Special Issue
Automated Detection of Branch Shaking Locations for Robotic Cherry Harvesting Using Machine Vision
Article Menu
Issue 1 (March) cover image

Export Article

Open AccessArticle
Robotics 2018, 7(1), 11;

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Department of Computing Science, Umeå University, Umeå 901 87, Sweden
Author to whom correspondence should be addressed.
Received: 31 August 2017 / Revised: 22 January 2018 / Accepted: 30 January 2018 / Published: 5 February 2018
(This article belongs to the Special Issue Agriculture Robotics)
PDF [904 KB, uploaded 5 February 2018]


The presented work is part of the H2020 project SWEEPER with the overall goal to develop a sweet pepper harvesting robot for use in greenhouses. As part of the solution, visual servoing is used to direct the manipulator towards the fruit. This requires accurate and stable fruit detection based on video images. To segment an image into background and foreground, thresholding techniques are commonly used. The varying illumination conditions in the unstructured greenhouse environment often cause shadows and overexposure. Furthermore, the color of the fruits to be harvested varies over the season. All this makes it sub-optimal to use fixed pre-selected thresholds. In this paper we suggest an adaptive image-dependent thresholding method. A variant of reinforcement learning (RL) is used with a reward function that computes the similarity between the segmented image and the labeled image to give feedback for action selection. The RL-based approach requires less computational resources than exhaustive search, which is used as a benchmark, and results in higher performance compared to a Lipschitzian based optimization approach. The proposed method also requires fewer labeled images compared to other methods. Several exploration-exploitation strategies are compared, and the results indicate that the Decaying Epsilon-Greedy algorithm gives highest performance for this task. The highest performance with the Epsilon-Greedy algorithm ( ϵ = 0.7) reached 87% of the performance achieved by exhaustive search, with 50% fewer iterations than the benchmark. The performance increased to 91.5% using Decaying Epsilon-Greedy algorithm, with 73% less number of iterations than the benchmark. View Full-Text
Keywords: reinforcement learning; Q-Learning; image thresholding; ϵ-greedy strategies reinforcement learning; Q-Learning; image thresholding; ϵ-greedy strategies

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Ostovar, A.; Ringdahl, O.; Hellström, T. Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot. Robotics 2018, 7, 11.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Robotics EISSN 2218-6581 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top