Zhongqiang Liu

Mobile smart device-based vegetable disease and insect pest recognition method

Computer vision and image processing technology have been rapidly developed and widely applied in many fields. There are many potential applications in modern agriculture. In this paper, a novel vegetable disease and insect pest recognition method is proposed based on the current computer vision and image processing methods. To investigate the vegetable disease and insect pest state, it is convenient to use images captured using smart phones for judgment. To implement this application, the disease area and the insect number on the leaves should be detected and figured out. So a new extraction and classification algorithm is firstly introduced to recognize leaves from images. Then a region-labeling algorithm is applied to calculate the insect number and disease areas in the segmented images. To deal with the areas of adhesion, a mathematical morphology algorithm is used for separating the objects. The proposed method is implemented on mobile smart devices and tested with field experiments. The experimental...

A crop trait information acquisition system with multitag-based identification technologies for breeding precision management

A acquisition system is developed with multitag-based identification technologies.The system provides four kinds of data acquisition modes for different requirements.Images and data are related, and image information is automatically generated.Field maps are created after planting directly via reading the RFID/NFC tags. This paper aims to establish a crop trait information acquisition system by combining barcode and radio frequency-based electronic identification (RFID) and near-field communication (NFC) technology applications. The system was devised to ensure (a) correct identification of each crop material and plot, (b) quick query and positioning for information collection, (c) correct combination of crop phenotypic data and images, and (d) reliable recording of periodic crop trait data with dependable transmission to the main server. This system, with multitag-based identification technology, was developed on an Android platform using the Java language. A type of RFID/NFC tag with a high-frequency chip was applied in the core, and a quick response (QR) code was used on the surface for material identification. A smartphone with NFC function can be used as an RFID reader, and its built-in camera can be used to decode QR codes. The system was used in some seed industries commercial breeding and in national crop variety regional trial, with its functions including reading/writing of RFID/NFC tags, decoding QR codes, acquiring crop trait information, creating field maps, and uploading data. This system provided a low-cost and highly efficient solution for crop trait information collection.

Research and Application of Data Security for Mobile Devices

Mobile devices have been increasingly become important tools for the information system application in agriculture, but the safe problem that follow also results in risks of economy lose. Considering above problems and combining the application of an agriculture chain logistics management system, a series of jobs have been done. This paper presents a data security solution which encrypts the configuration files to protect sensitive information and uses SSL protocol to protect the network transmission security. At present, this solution has been modular integrated with the agriculture chain logistics management system. This paper also provides reference for data security problems of other mobile devices.

Golden seed breeding cloud platform for the management of crop breeding material and genealogical tracking

Abstract Effectively identifying and analyzing materials are key procedures for breeding novel crop varieties because of the large quantities of materials and their combinations. This paper presents an approach for crop breeding material management, improvement of crop breeding efficiency, and genealogical tracking through the golden seed breeding cloud platform (GSBCP). The system was developed with Java on an Eclipse integrated development environment. To support a large number of users, security, credibility, and expandability, we selected a cloud-based architecture for the system, in which material attribute, pedigree, and trait information were customized by a template. An intelligent retrieval function was provided for the rapid search of breeding materials, and material trait information, historical data, genealogical information, trial data analysis results and material images can be retrieved in the system. For the analysis of the materials’ genealogy, the rules of genealogy were regulated. The genealogy of the breeding materials was automatically generated on the basis of these rules, which support many breeding methods, such as selfing, hybridization, double cross, three-way cross, and backcross. The developed system has been successfully applied in many Chinese breeding enterprises and scientific research institutions. The system provided a low-cost and highly efficient solution for crop material information management and genealogical tracking.

Research on the Application Integration Model for the Agricultural Enterprise of Integrative Production and Marketing

To integrate application systems under heterogeneous environments has gradually become a pressing demand for most agricultural enterprise. The vast diversity of implementation technologies increases the complexity of applications integration. With the aim of facilitating the development of integration solutions, we propose the specification of application integration. To achieve this, we analyzed the current situation of information, the environment of application systems, and the specific requirements of integration. We also studied the integration technologies. And then the ESB-SOA model for the agricultural enterprise of integrative production and marketing was proposed on the basis of a number of advanced technologies, such as ESB, SOA, EAI and Web Service. Based on ESB and SOA technologies, the model is able to utilize and integrate effectively various service resources on the geographically distributed computing environments. And through intelligent agent technologies, it supports cooperation and coordination mechanisms for the service activities. To exemplify and validate the profile, a case study is presented in which the proposed profile is used.

A SaaS-Based Logistics Informatization Model for Specialized Farmers Cooperatives in China

The logistics informatization of Specialized Farmers Cooperatives (SFC) plays an important role in the development of agriculture, and Software-as-a-Service (SaaS) is the development trend of information technology (IT). Firstly, the state-of-the-art of IT on SFC and the enlightenment SaaS to the IT application in logistic are introduced. Then, analyzing of the characteristics of logistics management system for SFC based on SaaS, we explore a SaaS-based logistics informatization model for SFC in China, and some key technologies to model application are also discussed, such as software architecture, system security and data modeling. Finally, some suggestions are put forward for a large-scale promotion of the model.

A Localization Algorithm for Sparse-Anchored WSN in Agriculture

The location information is very crucial for the sensing data in modern agriculture. However, positioning errors and sparse anchors are two key problems that should first be solved for the localization of the sensor nodes. We proposed a novel algorithm to tackle with these challenges. When the system of adjacent anchor distance equations is ill, a minimized-stress search algorithm (MSS) can decrease positioning error greatly. A collaborative sparse-anchored scheme (CSA) has an excellent positioning effect on low density of anchor, specifically on marginal sensor nodes. Our experimental result verified validity and accuracy of the algorithm. It improved feasibility and cost of WSN positioning technique, significantly.