In plant phenotyping, there is a demand for high-throughput, non-destructive systems that can accurately analyse various plant traits by measuring features such as plant volume, leaf area, and stem length. Existing vision-based systems either focus on speed using 2D imaging, which is consequently inaccurate, or on accuracy using time-consuming 3D methods. In this paper, we present a computer-vision system for seedling phenotyping that combines best of both approaches by utilizing a fast three-dimensional (3D) reconstruction method. We developed image processing methods for the identification and segmentation of plant organs (stem and leaf) from the 3D plant model. Various measurements of plant features such as plant volume, leaf area, and stem length are estimated based on these plant segments. We evaluate the accuracy of our system by comparing the measurements of our methods with ground truth measurements obtained destructively by hand. The results indicate that the proposed system is very promising.
The reduction of labour cost is the major motivation to develop a system for robot harvesting of roses in greenhouses that at least can compete with manual harvesting.Due to overlapping leaves, one of the most complicated tasks in robotic rose cutting is to locate the stem and trace the stem down to locate the cutting position. Computer vision techniques like stereo imaging, laser triangulation, röntgen imaging and a new technique, called reverse volumetric intersection, are evaluated in this paper to determine which technique is most feasible for the task. Experiments with the techniques applied on different rose plant indicate that reverse volumetric intersection shows that this technique is most promising to locate the stem down to the cutting position in terms of robustness and costs. INTRODUCTIONHigh labour costs and poor utilisation of product space are two of the areas where cost quickly add up for cut rose growers growing in traditional gutters. Also the poor availability of low cost untrained personnel for the task of rose cutting, the need of walking in and out long pathways and the tedious handwork is becoming a threat for future rose growing in the Netherlands. This has been recognised by several cut rose growers, system developers and research institutes several years ago and a task force was initialised to develop a mobile rose transportation system that bring the roses to the labourer instead of the other way around. At this time several mobile rose transportation systems are commercially available, varying from moving gutters with plants to individual plants in a single pot. Although a 30-40% reduction in labour cost is feasible with the mobilisation of the roses, reduction of manual labour will be a final factor of cost reduction (Wijchman, 2004). Also, with the mobilisation of the roses, the use of a robotic harvester instead of a human one is the next logical step in the automation process. Therefore, several research groups, institutes and commercial companies in the Netherlands have initiated the development of a robotic harvester for cut roses.Unlike previous developed robotic harvesters (van Henten et al., 2002; van Henten et al., 2003), the robot harvester for cut roses will be located on a fixed position in the greenhouse and the rose plants are transported to the robot harvester by means of a mobile transportation system. The major parts of the robot harvester consists of robots for the cutting and handling of ripe roses and a comprehensive vision system for the visual guidance of the robots. The complicated task of rose cutting can be subdivided in a number of subsequent operations. The first step is pre-selection where a vision system detects the presence of potential ripe roses. When a potential ripe rose is detected, the next step is the determination of the ripeness stage of the rose candidate. If the rose is ready to harvest the vision system of the robot harvester must determine its corresponding stem, trace the stem to the connection with the rose plant, cut the stem at...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.