3D modeling and reconstruction of plants and trees: A cross-cutting review across computer graphics, vision, and plant phenotyping

Three-Dimensional Modeling of Maize Canopies Based on Computational Intelligence

The 3-dimensional (3D) modeling of crop canopies is fundamental for studying functional-structural plant models. Existing studies often fail to capture the structural characteristics of crop canopies, such as organ overlapping and resource competition. To address this issue, we propose a 3D maize modeling method based on computational intelligence. An initial 3D maize canopy is created using the t-distribution method to reflect characteristics of the plant architecture. The subsequent model considers the 3D phytomers of maize as intelligent agents. The aim is to maximize the ratio of sunlit leaf area, and by iteratively modifying the azimuth angle of the 3D phytomers, a 3D maize canopy model that maximizes light resource interception can be constructed. Additionally, the method incorporates a reflective approach to optimize the canopy and utilizes a mesh deformation technique for detecting and responding to leaf collisions within the canopy. Six canopy models of 2 varieties plus 3 planting densities was constructed for validation. The average R2 of the difference in azimuth angle between adjacent leaves is 0.71, with a canopy coverage error range of 7% to 17%. Another 3D maize canopy model constructed using 12 distinct density gradients demonstrates the proportion of leaves perpendicular to the row direction increases along with the density. The proportion of these leaves steadily increased after 9 × 104 plants ha-1. This study presents a 3D modeling method for the maize canopy. It is a beneficial exploration of swarm intelligence on crops and generates a new way for exploring efficient resources utilization of crop canopies.

Soft robotics for farm to fork: applications in agriculture & farming

Agricultural tasks and environments range from harsh field conditions with semi-structured produce or animals, through to post-processing tasks in food-processing environments. From farm to fork, the development and application of soft robotics offers a plethora of potential uses. Robust yet compliant interactions between farm produce and machines will enable new capabilities and optimize existing processes. There is also an opportunity to explore how modeling tools used in soft robotics can be applied to improve our representation and understanding of the soft and compliant structures common in agriculture. In this review, we seek to highlight the potential for soft robotics technologies within the food system, and also the unique challenges that must be addressed when developing soft robotics systems for this problem domain. We conclude with an outlook on potential directions for meaningful and sustainable impact, and also how our outlook on both soft robotics and agriculture must evolve in order to achieve the required paradigm shift.

A Novel Method for Quantifying Plant Morphological Characteristics Using Normal Vectors and Local Curvature Data via 3D Modelling-A Case Study in Leaf Lettuce

Three-dimensional measurement is a high-throughput method that can record a large amount of information. Three-dimensional modelling of plants has the possibility to not only automate dimensional measurement, but to also enable visual assessment to be quantified, eliminating ambiguity in human judgment. In this study, we have developed new methods that could be used for the morphological analysis of plants from the information contained in 3D data. Specifically, we investigated characteristics that can be measured by scale (dimension) and/or visual assessment by humans. The latter is particularly novel in this paper. The characteristics that can be measured on a scale-related dimension were tested based on the bounding box, convex hull, column solid, and voxel. Furthermore, for characteristics that can be evaluated by visual assessment, we propose a new method using normal vectors and local curvature (LC) data. For these examinations, we used our highly accurate all-around 3D plant modelling system. The coefficient of determination between manual measurements and the scale-related methods were all above 0.9. Furthermore, the differences in LC calculated from the normal vector data allowed us to visualise and quantify the concavity and convexity of leaves. This technique revealed that there were differences in the time point at which leaf blistering began to develop among the varieties. The precise 3D model made it possible to perform quantitative measurements of lettuce size and morphological characteristics. In addition, the newly proposed LC-based analysis method made it possible to quantify the characteristics that rely on visual assessment. This research paper was able to demonstrate the following possibilities as outcomes: (1) the automation of conventional manual measurements, and (2) the elimination of variability caused by human subjectivity, thereby rendering evaluations by skilled experts unnecessary.

A deep learning generative model approach for image synthesis of plant leaves

Objectives

A well-known drawback to the implementation of Convolutional Neural Networks (CNNs) for image-recognition is the intensive annotation effort for large enough training dataset, that can become prohibitive in several applications. In this study we focus on applications in the agricultural domain and we implement Deep Learning (DL) techniques for the automatic generation of meaningful synthetic images of plant leaves, which can be used as a virtually unlimited dataset to train or validate specialized CNN models or other image-recognition algorithms.

Methods

Following an approach based on DL generative models, we introduce a Leaf-to-Leaf Translation (L2L) algorithm, able to produce collections of novel synthetic images in two steps: first, a residual variational autoencoder architecture is used to generate novel synthetic leaf skeletons geometry, starting from binarized skeletons obtained from real leaf images. Second, a translation via Pix2pix framework based on conditional generator adversarial networks (cGANs) reproduces the color distribution of the leaf surface, by preserving the underneath venation pattern and leaf shape.

Results

The L2L algorithm generates synthetic images of leaves with meaningful and realistic appearance, indicating that it can significantly contribute to expand a small dataset of real images. The performance was assessed qualitatively and quantitatively, by employing a DL anomaly detection strategy which quantifies the anomaly degree of synthetic leaves with respect to real samples. Finally, as an illustrative example, the proposed L2L algorithm was used for generating a set of synthetic images of healthy end diseased cucumber leaves aimed at training a CNN model for automatic detection of disease symptoms.

Conclusions

Generative DL approaches have the potential to be a new paradigm to provide low-cost meaningful synthetic samples. Our focus was to dispose of synthetic leaves images for smart agriculture applications but, more in general, they can serve for all computer-aided applications which require the representation of vegetation. The present L2L approach represents a step towards this goal, being able to generate synthetic samples with a relevant qualitative and quantitative resemblance to real leaves.

Life in 2.5D: Animal Movement in the Trees

The complex, interconnected, and non-contiguous nature of canopy environments present unique cognitive, locomotor, and sensory challenges to their animal inhabitants. Animal movement through forest canopies is constrained; unlike most aquatic or aerial habitats, the three-dimensional space of a forest canopy is not fully realized or available to the animals within it. Determining how the unique constraints of arboreal habitats shape the ecology and evolution of canopy-dwelling animals is key to fully understanding forest ecosystems. With emerging technologies, there is now the opportunity to quantify and map tree connectivity, and to embed the fine-scale horizontal and vertical position of moving animals into these networks of branching pathways. Integrating detailed multi-dimensional habitat structure and animal movement data will enable us to see the world from the perspective of an arboreal animal. This synthesis will shed light on fundamental aspects of arboreal animals’ cognition and ecology, including how they navigate landscapes of risk and reward and weigh energetic trade-offs, as well as how their environment shapes their spatial cognition and their social dynamics.