Search

• We proposed the conception of horticultural phenomics. • High-throughput aerospace-sky-ground phenotypic facilities in horticultural phenomics have also had the embryonic form and have been introduced, analyzed, distinguish systematically in this paper. • Horticultural phenomics towards multiscale, multidimension, multiperiod at present and is shown in this paper. • Application of plant phenomics in horticulture research have been summarized, such as omics research and horticultural breeding. With the development of advanced sensors, artificial intelligence, and computer vision, horticultural phenomics has made great progress in recent years. However, there is a lack of systematic reviews to discuss the horticultural phenomics and its applications at present. In this paper, we aim to fill this gap by providing a comprehensive review of the past developments, recent advances and existing challenges. Furthermore, we propose conception and give our prospects of high-throughput horticultural phenomics. We envision that horticultural phenomics will evolve towards multiscale, multidimension, multiperiod approach in the near future. This transformation will enable researchers to better realize the physiological processes, understand the genetic composition and develop new cultivars of horticultural plants that are better adapted to specific environments. Consequently, it will greatly promote the omics research in horticultural plants. In addition to advancing scientific research, high-throughput horticultural phenomics can also assist growers in efficient crop management, leading to improved yield and quality of horticultural products. However, it is important to acknowledge the challenges that need to be overcome. Once these challenges are addressed, high-throughput horticultural phenomics will become increasingly important in the fight against climate changes and maximizing profits. [ABSTRACT FROM AUTHOR]

[Display omitted] • We developed AICropCAM, an edge-computing enabled camera system for crop monitoring. • It integrated Raspberry Pi and Arduino for image processing and LoRa communication. • It ran a stack of four deep neural networks to characterize multiple plant/canopy parameters. • We quantified the power consumption and speed of the system for edge image-processing. • AICropCAM is a next-generation enabling technology for real-time, low-latency Ag applications. Precision Agriculture (PA) promises to meet the future demands for food, feed, fiber, and fuel while keeping their production sustainable and environmentally friendly. PA relies heavily on sensing technologies to inform site-specific decision supports for planting, irrigation, fertilization, spraying, and harvesting. Traditional point-based sensors enjoy small data sizes but are limited in their capacity to measure plant and canopy parameters. On the other hand, imaging sensors can be powerful in measuring a wide range of these parameters, especially when coupled with Artificial Intelligence. The challenge, however, is the lack of computing, electric power, and connectivity infrastructure in agricultural fields, preventing the full utilization of imaging sensors. This paper reported AICropCAM, a field-deployable imaging framework that integrated edge image processing, Internet of Things (IoT), and LoRaWAN for low-power, long-range communication. The core component of AICropCAM is a stack of four Deep Convolutional Neural Networks (DCNN) models running sequentially: CropClassiNet for crop type classification, CanopySegNet for canopy cover quantification, PlantCountNet for plant and weed counting, and InsectNet for insect identification. These DCNN models were trained and tested with >43,000 field crop images collected offline. AICropCAM was embodied on a distributed wireless sensor network with its sensor node consisting of an RGB camera for image acquisition, a Raspberry Pi 4B single-board computer for edge image processing, and an Arduino MKR1310 for LoRa communication and power management. Our testing showed that the time to run the DCNN models ranged from 0.20 s for InsectNet to 20.20 s for CanopySegNet, and power consumption ranged from 3.68 W for InsectNet to 5.83 W for CanopySegNet. The classification model CropClassiNet reported 94.5 % accuracy, and the segmentation model CanopySegNet reported 92.83 % accuracy. The two object detection models PlantCountNet and InsectNet reported mean average precision of 0.69 and 0.02 for the test images. Predictions from the DCNN models were transmitted to the ThingSpeak IoT platform for visualization and analytics. We concluded that AICropCAM successfully implemented image processing on the edge, drastically reduced the amount of data being transmitted, and could satisfy the real-time need for decision-making in PA. AICropCAM can be deployed on moving platforms such as center pivots or drones to increase its spatial coverage and resolution to support crop monitoring and field operations. [ABSTRACT FROM AUTHOR]

Plant phenotyping is the study of complex plant traits to evaluate its status depending on the life-cycle conditions. Often, these evaluations are carried out by human operators, and the accuracy could be biased by their experience and skill, especially when dealing with huge amounts of data produced by high-throughput phenotyping (HTP) platforms. With the rapid development of key enabling technologies, HTP is only made possible by the vast amounts of data made available by computer vision systems. In this scenario, artificial intelligence algorithms play a key role in the automation, standardization, and quantitative analysis of large data. This paper focuses on detecting tomato plants phenotyping traits using single-stage detectors (either stand-alone or ensemble) based on YOLOv5, aiming to effectively identify nodes, fruit, and flowers on a challenging dataset acquired during a stress experiment conducted on multiple tomato genotypes. Results demonstrate that the models achieve relatively high scores, considering the particular challenges of the input images in terms of object size, similarity between objects, and their color. • YOLOv5-based deep learning models for tomato plant phenotyping. • Performance evaluation using stand alone detectors and ensemble strategies. • Identification of nodes, fruits and flowers on a challenging image dataset (different object size, similarity between objects and their color). [ABSTRACT FROM AUTHOR]

• An overview of generative adversarial network (GAN) architectures is presented. • The application of GANs in agriculture is reviewed. • The challenges and opportunities of GANs are discussed. In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e.g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments. Large-scale, balanced and ground-truthed image datasets are tremendously beneficial but most often difficult to obtain to fuel the development of highly performant models. As artificial intelligence through deep learning is impacting analysis and modeling of agricultural images, image augmentation plays a crucial role in boosting model performance while reducing manual efforts for image collection and labelling, by algorithmically creating and expanding datasets. Beyond traditional data augmentation techniques, generative adversarial network (GAN) invented in 2014 in the computer vision community, provides a suite of novel approaches that can learn good data representations and generate highly realistic samples. Since 2017, there has been a growth of research into GANs for image augmentation or synthesis in agriculture for improved model performance. This paper presents an overview of the evolution of GAN architectures followed by a first systematic review of various applications in agriculture and food systems (https://github.com/Derekabc/GANs-Agriculture), involving a diversity of visual recognition tasks for plant health conditions, weeds, fruits (preharvest), aquaculture, animal farming, plant phenotyping as well as postharvest detection of fruit defects. Challenges and opportunities of GANs are discussed for future research. [ABSTRACT FROM AUTHOR]

• The applications of computer vision techniques and machine learning algorithms in the mushroom industry are reviewed. • The strengths and weaknesses of various approaches proposed in current studies are analyzed. • Sizes, shapes and colors are currently used as the main parameters in the automated grading of mushrooms. • The possibilities of the application of 3D technology in the edible fungus industry are discussed. • Methods based on image and machine learning show great potential in the mushroom industry. Mushrooms are popular food items containing numerous vitamins, dietary fibers, and a large number of proteins. As a result, mushrooms can increase the body's immunity and prevent many types of cancer to keep the body healthy. For these reasons, the demand for high yields and safety in the production of high-quality mushrooms is increasing. This review highlights the application of computer vision and machine learning algorithms in the mushroom industry. Through a systematic review of papers published between 1991 and 2021, this article introduces key aspects related to mushrooms (e.g., species identification and quality classification based on artificial intelligence), and discusses the advantages and disadvantages of various approaches. Numerous artificial intelligence and machine vision technologies have been implemented in research efforts focusing on edible fungi. However, their applications are generally limited to the identification of poisonous mushrooms according to their forms, the plucking of cultivated mushrooms covered by soil, and the mechanized grading of mushrooms. Clearly, the currently available methods cannot meet the requirements of the digitization and intelligentization in the field of edible mushrooms. Considering these reasons, it is possible to develop further application opportunities, such as digital mushroom phenotype determination, and high-throughput breeding based on big data, and mechanical picking by a harvesting robot as well. Therefore, the integration of computer vision and machine learning with the development of more efficient algorithms will undoubtedly be a hotspot for future studies in the context of the mushroom industry. [ABSTRACT FROM AUTHOR]