Pakistan Journal of Agricultural Sciences
Agriculture plays a significant role in overall GDP of any country. So, there are several efforts those are being made to develop and increase the crop yield. In any of crop, weed i.e. (unwanted crops) is the major concern that may leads to poor production of crop. Therefore, an automatic crop monitoring system is required to monitor the weed. This system will help the farmers to monitor the crops, in gradual fashion, once it has been cultivated. Then specific Vegetation Index (VI) would be applied to locate all green portions in the image that would be part of early wheat crop or weed patches. We used Object Based Image Analysis (OBIA) algorithm to detect the weed patches in RGB and Multispectral imagery captured by UAV at 30-60 m altitude is used to acquire the images of wheat fields. Once the weed patches successfully identified from between the crop rows and within the crop rows then connected component-based classification technique is used that successfully classify the detected object either the object is related to weed patches or actual crop. The core objective of this work is to lessen the human involvement and to introduce the latest techniques and computation technology, peculiarly to identify the weed patches within the crop rows as well as between the crop rows in wheat field. Moreover, exploitation of UAV technology is also the core objective that will significantly provide the site specifically herbicides spraying.
[学术文献] Multi-objective path planner for an agricultural mobile robot in a virtual greenhouse environment 进入全文
Computers and Electronics in Agriculture
Robotics in agriculture has experienced enormous development in the past decade. In order to accomplish numerous agricultural tasks, the order in which the crop is covered is particularly important in order to minimise travelling cost and to preserve soil conditions. However, it is difficult to determine an optimised sequential path for the robot which minimizes navigation costs, while ensuring a fully completed agricultural operation. This paper presents the implementation of a multi-objective algorithm to solve the path planning problem for pesticide spraying operation inside a greenhouse. Pesticide spraying problems found in greenhouses have been adapted from the vehicle routing problem found in operations research, where the infected plants represent the customers and the mobile robot represents the vehicles. Routes between the plants are generated using a Probabilistic Roadmap path planner based on the designed virtual environment. The virtual environment is designed based on the real greenhouse environment to visualise the agricultural operation inside the greenhouse. To determine the best routes for the mobile robot, the Non-dominated Sorting Genetic Algorithm using Reference Point Based (NSGA-III) is tested and applied to the system. The solution quality has been compared with the Non-dominated Sorting Genetic Algorithm (NSGA-II) using the C-metric indicator. Comparisons with NSGA-II using the C-metric indicator verify that NSGA-III offers a superior performance with a good quality result.
[学术文献] Field-Based Scoring of Soybean Iron Deficiency Chlorosis Using RGB Imaging and Statistical Learning 进入全文
Iron deficiency chlorosis (IDC) is an abiotic stress in soybean that can cause significant biomass and yield reduction. IDC is characterized by stunted growth and yellowing and interveinal chlorosis of early trifoliate leaves. Scoring IDC severity in the field is conventionally done by visual assessment. The goal of this study was to investigate the usefulness of Red Green Blue (RGB) images of soybean plots captured under the field condition for IDC scoring. A total of 64 soybean lines with four replicates were planted in 6 fields over 2 years. Visual scoring (referred to as Field Score, or FS) was conducted at V3–V4 growth stage; and concurrently RGB images of the field plots were recorded with a high-throughput field phenotyping platform. A second set of IDC scores was done on the plot images (displayed on a computer screen) consistently by one person in the office (referred to as Office Score, or OS). Plot images were then processed to remove weeds and extract six color features, which were used to train computer-based IDC scoring models (referred to as Computer Score, or CS) using linear discriminant analysis (LDA) and support vector machine (SVM). The results showed that, in the fields where severe IDC symptoms were present, FS and OS were strongly positively correlated with each other, and both of them were strongly negatively correlated with yield. CS could satisfactorily predict IDC scores when evaluated using FS and OS as the reference (overall classification accuracy > 81%). SVM models appeared to outperform LDA models; and the SVM model trained to predict IDC OS gave the highest prediction accuracy. It was anticipated that coupling RGB imaging from the high-throughput field phenotyping platform with real-time image processing and IDC CS models would lead to a more rapid, cost-effective, and objective scoring pipeline for soybean IDC field screening and breeding.
International Center for Tropical Agriculture (CIAT)
Farmers in Colombia's maize-growing region of Córdoba had seen it all: too much rain one year, a searing drought the next. Yields were down and their livelihoods hung in the balance. To better deal with climate stress, farmers in Colombia's maize-growing region of Córdoba needed information services that would help them decide what varieties to plant, when they should sow and how they should manage their crops. They needed information services that would help them decide what varieties to plant, when they should sow and how they should manage their crops. A consortium formed with the government, Colombia's National Cereals and Legumes Federation (FENALCE), and big-data scientists at the International Center for Tropical Agriculture (CIAT). The researchers used big-data tools, based on the data farmers helped collect, and yields increased substantially. The study, published in September in Global Food Security, shows how machine learning of data from multiple sources can help make farming more efficient and productive even as the climate changes.