Chen Xiangwei

Bio: Chen Xiangwei is an academic researcher from Northwest A&F University. The author has contributed to research in topics: Correlation coefficient & RGB color model. The author has an hindex of 2, co-authored 2 publications receiving 26 citations.

Detecting maize leaf water status by using digital RGB images

Abstract: To explore the correlation between crop leaf digital RGB (Red, Green and Blue) image features and the corresponding moisture content of the leaf, a Canon digital camera was used to collect image information from detached leaves of heading-stage maize. A drying method was adopted to measure the moisture content of the leaf samples, and image processing technologies, including gray level co-occurrence matrices and grayscale histograms, was used to extract the maize leaf texture feature parameters and color feature parameters. The correlations of these feature parameters with moisture content were analyzed. It is found that the texture parameters of maize leaf RGB images, including contrast, correlation, entropy and energy, were not significantly correlated with moisture content. Thus, it was difficult to use these features to predict moisture content. Of the six groups of eigenvalues for the leaf color feature parameters, including mean, variance, energy, entropy, kurtosis and skewness, mean and kurtosis were found to be correlated with moisture content. Thus, these features could be used to predict the leaf moisture content. The correlation coefficient (R2) of the mean-moisture content relationship model was 0.7017, and the error of the moisture content prediction was within

Real-time remote monitoring system for crop water requirement information.

Abstract: Rapidly acquiring and real-time transmitting crop water requirement information constitute the basis for achieving intelligent diagnosis and precision irrigation. In order to collect and transmit crop water requirement information at real time, a new microcontroller-based real-time remote monitoring system was designed, including system hardware design, software and anti-jamming design. The system achieved the functions including clock reading, information configuration, LCD display, keyboard control, data sending and receiving, multi-channel information acquisition, conversion and storage. Laboratory and field tests showed that the system can achieve data acquisition and real-time display of the crop water requirement information. Unlike the current weather station, the system collects crop water information, meteorological factors and soil parameters at the same time. It has a high level of stability and acquisition accuracy, and can meet the requirements for real-time remote monitoring of the crop water requirement information for irrigation decision-making. Keywords: crop water requirement, information collection, microcontroller, real time monitoring, irrigation decision making DOI: 10.3965/j.ijabe.20140706.006 Citation: Han W T, Xu Z Q, Zhang Y, Cao P, Chen X W, Ooi S K. Real-time remote monitoring system for crop water requirement information. Int J Agric & Biol Eng, 2014; 7(6): 37－46.

Design and implementation of a cloud-based IoT scheme for precision agriculture

Abstract: The Internet of Things (IoT) technology is currently shaping different aspects of human life. Precision agriculture is one of the paradigms which can use the IoT advantages to optimize the production efficiency and uniformity across the agriculture fields, optimize the quality of the crops, and minimize the negative environmental impact. In this paper, we present an IoT architecture customized for precision agriculture applications. The proposed three-layer architecture collects the needed data and relays it to a cloud-based back-end where it is processed and analyzed. Feedback actions based on the analyzed data can be sent back to the front-end nodes. We built a prototype of the proposed architecture to demonstrate its performance advantages.

Advances in Structured Light Sensors Applications in Precision Agriculture and Livestock Farming

Abstract: The sustained growth of the world's population in the coming years will require an even greater role for agriculture to meet the food needs of humankind. To improve the productivity and competitiveness of the agricultural industry, it is necessary to develop new and affordable sensing technologies for agricultural operations. This kind of innovations should be implemented in a framework considering the farm, the crops, and their surroundings, with the aim of providing the farmer with information to take better decisions to enhance the production. This is the case of precision agriculture and precision livestock farming. This chapter reviews and discusses the use of structured light sensors in the characterization and phenotyping of crops in orchards and groves, weeds, and animals. As a result of a collaboration between researchers from Spain and Chile, opportunities for this type of sensors have been identified in these countries as examples of South American and European agriculture. In this context, several empirical case studies are presented regarding the use of structured light sensors for flower, fruit, branch, and trunk characterization considering depth and RGB (red-green-blue colors) information in avocados, lemons, apple, and pear orchards. Applications to weed detection and classification as well as to livestock phenotyping are also illustrated. Regarding the presented case studies, experimental and statistical results are provided showing the pros and cons of structured light sensors applied to agricultural environments. Additionally, several considerations are included for the use of this type of sensors to improve the agricultural process.

Identification and Classification of Maize Drought Stress Using Deep Convolutional Neural Network

Abstract: Drought stress seriously affects crop growth, development, and grain production. Existing machine learning methods have achieved great progress in drought stress detection and diagnosis. However, such methods are based on a hand-crafted feature extraction process, and the accuracy has much room to improve. In this paper, we propose the use of a deep convolutional neural network (DCNN) to identify and classify maize drought stress. Field drought stress experiments were conducted in 2014. The experiment was divided into three treatments: optimum moisture, light drought, and moderate drought stress. Maize images were obtained every two hours throughout the whole day by digital cameras. In order to compare the accuracy of DCNN, a comparative experiment was conducted using traditional machine learning on the same dataset. The experimental results demonstrated an impressive performance of the proposed method. For the total dataset, the accuracy of the identification and classification of drought stress was 98.14% and 95.95%, respectively. High accuracy was also achieved on the sub-datasets of the seedling and jointing stages. The identification and classification accuracy levels of the color images were higher than those of the gray images. Furthermore, the comparison experiments on the same dataset demonstrated that DCNN achieved a better performance than the traditional machine learning method (Gradient Boosting Decision Tree GBDT). Overall, our proposed deep learning-based approach is a very promising method for field maize drought identification and classification based on digital images.

An Automated Irrigation System for Smart Agriculture Using the Internet of Things

Abstract: Water is a vital and scarce resource in agriculture and its optimal management is emerging as a key challenge. This paper presents an automated irrigation system to reduce water utilization in agriculture by combining the Internet of Things (IoT), cloud computing and optimization tools. The automated irrigation system deploys low cost sensors to sense variables of interest such as soil moisture, pH, soil type, and weather conditions. The data is stored in Thingspeak cloud service for monitoring and data-storage. The field data is transmitted to the cloud using Wi-Fi modem and using GSM cellular networks. Then an optimization model is used to compute the optimal irrigation rate which are automated using a solenoid valve controlled using an ARM controller (WEMOS D1). The variables of interest are stored in the cloud and offered as a service to the farmers. The proposed approach is demonstrated on a pilot scale agricultural facility and our results demonstrate the reduction in water utilization, increase in data-availability, and visualization.