The rate of change of top projected leaf area (TPLA) of lettuce (Lactuca sativa L.) seedlings was determined with machine vision technology. Differences of TPLA between control and treatment plants were detectable with this technique within 48 hours from the onset of an imposed nutrient stress. The nutrient stress treatments were 0%, 50%, 150% of the control (100%). There were no differences for the 50% and 150% treatments compared to the control plants, even after a 6-day observation period. However, the 0% treatment caused different TPLA expansion within 48 hours and required a recovery period of 3 or 4 days after being returned to normal EC levels before again attaining prestressed growth rates.
G.A. Giacomelli, P.P. Ling, and Jaco Kole
M. A. L. Smith, J. Reid, A. Hansen, Z. Li, and D. L. Madhavi
Industrial-scale cultivation of plant cells for valuable product recovery (e.g. natural pigments, pharmaceutical compounds) can only be considered commercially-feasible when a fully-automated, predictable bioprocess is achieved. Automation of cell selection, quantification, and sorting procedures, and pinpointing of optimal microenvironmental regimes can be approached via machine vision. Macroscopic staging of Ajuga reptans callus masses (ranging between 2-6 g FW) permitted simultaneous rapid capture of top and side views. Area data used in a linear regression model yielded a reliable, non-destructive estimate of fresh mass. Suspension culture images from the same cell line were microscopically imaged at 4x (with an inverted microscope). Using color machine vision, the HSI (hue-saturation-intensity) coordinates were used to successfully separate pigmented cells and aggregates from non-pigmented cells, aggregates, and background debris. Time-course sampling of a routine suspension culture consistently allowed pigmented cells to be detected, and intensity could be correlated with the degree of pigmentation as verified using spectrophotometer analysis of parallel samples.
Z. Mganilwa, M. Nagata, H. Wang, and Q. Cao
Based on seedling properties and stage of growth for cucurbitaceous and solanaceous vegetables, separate robots are being marketed for each. Full automatic grafting robots are used for solanaceous vegetables like tomato and egg-plant employing ordinary splice method by making a diagonal cut through the hypocotyl of both the scion and the rootstock. However, cutting one piece of cotyledon diagonally from the rootstock does grafting of cucurbitaceous vegetables like cucumber, melon, and pumpkin. This method had the advantage of easy recovery and high survival rate of seedlings. Only semi-automatic robots are marketed for this kind of plants because a fixed cotyledon orientation is required for grafting operation. Both the scion and the rootstock are loaded manually to their corresponding feeding devices. To replace the manual loading operation, this study proposed a neural network based automatic seedling loading system. The system automatically estimates the quality and determines the cotyledon orientation of seedling for guiding the loading device of the grafting robot. As a first step toward solution, we report the development of a model for seedling quality estimation and orientation detection using image processing and neural network techniques. The model has a learning ability and can judge seedlings according to the training patterns. A seedling leaves feature extraction model of 10 characteristics was proposed and a three-layer neural network was constructed. The experimental results indicate that the seedling leaves orientation was accurately detected with an average error of 3 degrees within 360 degrees of freedom and the machine vision system could properly classify seedlings into three classes (A-good, B-fair, and C-bad) according to the training pattern.
T. Burks, F. Villegas, M. Hannan, S. Flood, B. Sivaraman, V. Subramanian, and J. Sikes
Automated solutions for fresh market fruit and vegetable harvesting have been studied by numerous researchers around the world during the past several decades. However, very few developments have been adopted and put into practice. The reasons for this lack of success are due to technical, economic, horticultural, and producer acceptance issues. The solutions to agricultural robotic mechanization problems are multidisciplinary in nature. Although there have been significant technology advances during the past decade, many scientific challenges remain. Viable solutions will require engineers and horticultural scientists who understand crop-specific biological systems and production practices, as well as the machinery, robotics, and controls issues associated with the automated production systems. Focused multidisciplinary teams are needed to address the full range of commodity-specific technical issues involved. Although there will be common technology components, such as machine vision, robotic manipula-tion, vehicle guidance, and so on, each application will be specialized, due to the unique nature of the biological system. Collaboration and technology sharing between commodity groups offers the benefit of leveraged research and development dollars and reduced overall development time for multiple commodities. This paper presents an overview of the major horticultural and engineering aspects of robotic mechanization for horticultural crop harvesting systems.
The commercial greenhouse operation, with a controlled and structured environment and a large number of highly repetitive tasks, offers many advantages for automation relative to other segments of agriculture. Benefits and incentives to automate are significant and include improving the safety of the work force and the environment, along with ensuring sufficient productivity to compete in today's global market. The use of equipment and computers to assist production also may be particularly important in areas where labor costs and/or availability are a concern. However, automation for greenhouse systems faces very significant challenges in overcoming nonuniformity, cultural practice, and economic problems. As a case study, a robotic workcell for processing geranium cuttings for propagation has been developed. The robot grasps randomly positioned cuttings from a conveyor, performs leaf removal, trims the stems, and inserts the cuttings into plug trays. While the system has been shown to process effectively many plants automatically, the robot is not equipped to handle successfully the wide variety of cuttings that a trained worker handles with aplomb. A key challenge in greenhouse automation will be to develop productive systems that can perform in a reliable and cost-effective way with highly variable biological products.
Shahrokh Khanizadeh, Clément Vigneault, and Deborah Buszard
David Obenland, Dennis Margosan, Joseph L. Smilanick, and Bruce Mackey
portion of a multispectral analysis system to identify and classify peel defects in citrus ( Blasco et al., 2007 , 2009 ); however, the work used fruit with a limited number of known peel problems using machine vision in the laboratory and was targeted
Lloyd L. Nackley, Brent Warneke, Lauren Fessler, Jay W. Pscheidt, David Lockwood, Wesley C. Wright, Xiaocun Sun, and Amy Fulcher
variable-rate technology without an improvement in spray application characteristics ( Fessler et al., 2020 ). Unlike the constant-rate spray mode, the machine-vision variable-rate sprayer mode made real-time adjustments, decreasing the application volume
M.A.L. Smith, I. Dustin, R. Leathers, and J-P. Zrÿd
Natural plant pigments (produced as secondary metabolites in cell culture) can replace controversial synthetic chemical colorants to enhance the appearance of processed foods. Intensive bioreactor-based production systems designed for betalain pigment-producing cultures of Beta vulgaris are still not economically competitive, in part due to the slow, prohibitively expensive, and incomplete conventional methods (HPLC analysis, biomass estimates, cell counts) which must be used to assess culture status. As an alternative, software was written using Semper 6 (a high level programming language for image analysis) for collection of exacting morphometric (spatial) and photometric (spectral) process information from an intense violet cell line. Uniform, crisp images of 1 ml culture samples in multiwell plates were captured macroscopically, and the pattern of pigment production was traced at 3 day intervals over the course of a 15 day growth cycle with monochromatic color filters and image grey level data. Rod-shaped cells and aggregates were automatically sorted and measured using parameters of particle size, density, and circularity. The machine vision method offers greater opportunity to fine-tune cell selection for enhanced pigment content.
Sai Xu, Huazhong Lu, Xu Wang, Christopher M. Ference, Xin Liang, and Guangjun Qiu
suitable for spot checking, and cannot meet the need for flavor detection for an entire harvest of fruit from an orchard. An intelligent method—machine vision technology ( Gongal et al., 2018 ; Naik and Patel, 2017 )—has been applied in the field of fruit