Recent studies indicate that food demand will increase by 35–56% over the period 2010–2050 due to population increase, economic development, and urbanization. Greenhouse systems allow for the sustainable intensification of food production with demonstrated high crop production per cultivation area. Breakthroughs in resource-efficient fresh food production merging horticultural and AI expertise take place with the international competition “Autonomous Greenhouse Challenge”. This paper describes and analyzes the results of the third edition of this competition. The competition’s goal is the realization of the highest net profit in fully autonomous lettuce production. Two cultivation cycles were conducted in six high-tech greenhouse compartments with operational greenhouse decision-making realized at a distance and individually by algorithms of international participating teams. Algorithms were developed based on time series sensor data of the greenhouse climate and crop images. High crop yield and quality, short growing cycles, and low use of resources such as energy for heating, electricity for artificial light, and CO2 were decisive in realizing the competition’s goal. The results highlight the importance of plant spacing and the moment of harvest decisions in promoting high crop growth rates while optimizing greenhouse occupation and resource use. In this paper, images taken with depth cameras (RealSense) for each greenhouse were used by computer vision algorithms (Deepabv3+ implemented in detectron2 v0.6) in deciding optimum plant spacing and the moment of harvest. The resulting plant height and coverage could be accurately estimated with an R2 of 0.976, and a mIoU of 98.2, respectively. These two traits were used to develop a light loss and harvest indicator to support remote decision-making. The light loss indicator could be used as a decision tool for timely spacing. Several traits were combined for the harvest indicator, ultimately resulting in a fresh weight estimation with a mean absolute error of 22 g. The proposed non-invasively estimated indicators presented in this article are promising traits to be used towards full autonomation of a dynamic commercial lettuce growing environment. Computer vision algorithms act as a catalyst in remote and non-invasive sensing of crop parameters, decisive for automated, objective, standardized, and data-driven decision making. However, spectral indexes describing lettuces growth and larger datasets than the currently accessible are crucial to address existing shortcomings between academic and industrial production systems that have been encountered in this work.
Greenhouse horticulture plays an important role globally by producing nutritious fruits and vegetables with high resource use efficiency. Modern greenhouses are large-scale high-tech production factories that are increasingly data-driven, and where climate and irrigation control are gradually becoming more autonomous. This is enabled by technological developments and driven by shortages in skilled labor and the demand for improved resource use efficiency. In the Autonomous Greenhouse Challenge, it has been shown that controlling greenhouse cultivation can be done efficiently with intelligent algorithms. For an optimal strategy, however, it is essential that control algorithms properly account for crop responses, which requires appropriate sensors, reliable data, and accurate models. This paper presents the results of the 4th Autonomous Greenhouse Challenge, in which international teams developed six intelligent algorithms that fully controlled a dwarf tomato cultivation, a crop that is well-suited for robotic harvesting, but for which little prior cultivation data exists. Nevertheless, the analysis of the experiment showed that all teams managed to obtain a profitable strategy, and the best algorithm resulted a production equivalent to 45 kg/m2/year, higher than in the commercial practice of high-wire cherry tomato growing. The predominant factor was found to be the much higher plant density that can be achieved in the applied growing system. More difficult challenges were found to be related to measuring crop status to determine the harvest moment. Finally, this experiment shows the potential for novel greenhouse cultivation systems that are inherently well-suited for autonomous control, and results in a unique and rich dataset to support future research.
Background: A well-known method for evaluating plant resistance to insects is by measuring insect reproduction or oviposition. Whiteflies are vectors of economically important viral diseases and are, therefore, widely studied. In a common experiment, whiteflies are placed on plants using clip-on-cages, where they can lay hundreds of eggs on susceptible plants in a few days. When quantifying whitefly eggs, most researchers perform manual eye measurements using a stereomicroscope. Compared to other insect eggs, whitefly eggs are many and very tiny, usually 0.2 mm in length and 0.08 mm in width; therefore, this process takes a lot of time and effort with and without prior expert knowledge. Plant insect resistance experiments require multiple replicates from different plant accessions; therefore, an automated and rapid method for quantifying insect eggs can save time and human resources. Results: In this work, a novel automated tool for fast quantification of whitefly eggs is presented to accelerate the determination of plant insect resistance and susceptibility. Leaf images with whitefly eggs were collected from a commercial microscope and a custom-built imaging system. A deep learning-based object detection model was trained using the collected images. The model was incorporated into an automated whitefly egg quantification algorithm, deployed in a web-based application called Eggsplorer. Upon evaluation on a testing dataset, the algorithm was able to achieve a counting accuracy as high as 0.94, r2 of 0.99, and a counting error of ± 3 eggs relative to the actual number of eggs counted by eye. The automatically collected counting results were used to determine the resistance and susceptibility of several plant accessions and were found to yield significantly comparable results as when using the manually collected counts for analysis. Conclusion: This is the first work that presents a comprehensive step-by-step method for fast determination of plant insect resistance and susceptibility with the assistance of an automated quantification tool.
Plant phenotyping involves the measurements of plant traits to gain more insight into the interaction between the genotype (G), environment (E) and crop management strategies (M). To improve plant phenotyping, accurate measurements are crucial. Manual measurements are biased, time-intensive, and therefore limited to only a few plants. Especially measurements of 3D phenotypic traits, such as plant architecture, internode length, and leaf area are difficult to extract manually. To enhance the speed and accuracy of phenotyping, there is a need for automatic digital plant phenotyping solutions. The presented dataset contains 3D point clouds of tomato plants, which will enable researchers to develop novel methods to extract 3D phenotypic traits. Converting 3D point clouds to plant traits is also known as 3D plant phenotyping. This process can be subdivided into three steps: point cloud segmentation, skeletonisation to extract plant architecture, and plant-traits extraction. Those three steps need to be analysed properly to indicate bottlenecks and improve 3D phenotyping algorithms. Currently, the development of 3D phenotyping algorithms is inhibited by the availability of comprehensive datasets and algorithms to analyse all steps. To our best knowledge only five annotated datasets exist for testing and validating 3D phenotyping algorithms. However, these datasets mainly focus on the segmentation step. Skeletonisation and manual measured plant traits are frequently not included. To improve 3D plant phenotyping, a novel dataset, TomatoWUR, is presented. This comprehensive dataset consists of 44 point clouds of single tomato plants imaged by fifteen cameras to create a point cloud using the shape-from-silhouette methodology. The dataset includes annotated point clouds, skeletons, and manual reference measurements. In addition, the dataset includes software for comprehensive evaluation and comparison of phenotyping methods, which is expected to benefit the development of 3D phenotyping algorithms. The related software can be found our GIT: https://github.com/WUR-ABE/TomatoWUR.