Key Laboratory of Agricultural Information Acquisition Technology

Beijing, China

Key Laboratory of Agricultural Information Acquisition Technology

Beijing, China

Time filter

Source Type

Deng C.,China Agricultural University | Deng C.,China Tobacco Guangxi Industrial Co. | Song J.,Chinese Academy of Sciences | Sun R.,China Agricultural University | And 7 more authors.
Tobacco Science and Technology | Year: 2016

As a solution to the massive marketing data and unsatisfactory analysis efficiency, a visual analysis system of marketing data (VASMD) for cigarette enterprises was developed based on thermodynamic diagram. VASMD adopted a triple-layer distributed data processing architecture, including data collecting layer, data preprocessing layer, and visual analysis layer. Data analysis models were built by using k-means and DBSCAN data mining algorithms, an interactive visual analysis diagram and several auxiliary analysis tools were developed based on Baidu map. In the case studies, two marketing data sets of cigarette brand"Zhenlong" produced by China Tobacco Guangxi Industrial Limited Corporation were used for screening, preprocessing and visual analysis. The results showed that: 1) The development of sale hot spots in main cities had strong guiding effects on the hot spot formation of their neighboring counties, towns and villages. 2) The hot spots distributed and spread mostly along the major and trunk traffic networks. 3) There existed mutual traction effects between those regions with frequent economic contacts and similar language and culture in the formation and spreading of hot spots. In conclusion, a VASMD in the form of thermodynamic diagram can figuratively demonstrate the geographic distribution and structure of cigarette consumer groups, reveal the market development patterns and rules implied by the data, and promote the level of precise marketing of enterprises effectively. © 2016, Editorial Office of Tobacco Science and Technology. All right reserved.


Huang J.,China Agricultural University | Huang J.,Key Laboratory of Agricultural Information Acquisition Technology | Sedano F.,University of Maryland University College | Huang Y.,U.S. Department of Agriculture | And 8 more authors.
Agricultural and Forest Meteorology | Year: 2016

The scale mismatch between remote sensing observations and state variables simulated by crop growth models decreases the reliability of crop yield estimates. To overcome this problem, we implemented a two-step data-assimilation approach: first, we generated a time series of 30-m-resolution leaf area index (LAI) by combining Moderate Resolution Imaging Spectroradiometer (MODIS) data and three Landsat TM images with a Kalman filter algorithm (the synthetic KF LAI series); second, the time series were assimilated into the WOFOST crop growth model to generate an ensemble Kalman filter LAI time series (the EnKF-assimilated LAI series). The synthetic EnKF LAI series then drove the WOFOST model to simulate winter wheat yields at 1-km resolution for pixels with wheat fractions of at least 50%. The county-level aggregated yield estimates were compared with official statistical yields. The synthetic KF LAI time series produced a more realistic characterization of LAI phenological dynamics. Assimilation of the synthetic KF LAI series produced more accurate estimates of regional winter wheat yield (R2=0.43; root-mean-square error (RMSE)=439kgha-1) than three other approaches: WOFOST without assimilation (determination coefficient R2=0.14; RMSE=647kgha-1), assimilation of Landsat TM LAI (R2=0.37; RMSE=472kgha-1), and assimilation of S-G filtered MODIS LAI (R2=0.49; RMSE=1355kgha-1). Thus, assimilating the synthetic KF LAI series into the WOFOST model with the EnKF strategy provides a reliable and promising method for improving regional estimates of winter wheat yield. © 2015 Elsevier B.V.


Zhang H.,China Agricultural University | Zhang H.,Tianjin Agricultural University | Zhang H.,Applied Technology Internet | Zhang H.,Key Laboratory of Agricultural Information Acquisition Technology | And 5 more authors.
Computers and Electronics in Agriculture | Year: 2014

Cotton is an important crop throughout the world, and its quality plays a significant role in its profitability and marketability. Foreign matter in cotton can cause damage to spinning, weaving, and dyeing and thus seriously affects the quality of cotton products. Conventional methods including inspection by human workers and instrument based approaches such as photoelectric detection and ultrasonic detection are time-consuming, labor-intensive, and sometimes inaccurate. As a non-destructive, cost-effective, rapid, and objective inspection tool, computer vision has been widely used in cotton foreign matter inspection. In this review, the basic concepts, components, and image acquisition modes of computer vision techniques are presented. The improvements in image processing and analysis of foreign matter in cotton are introduced, and several different computer vision systems that have been created to detect foreign matter are reviewed to highlight the potential for the inspection of foreign matter. Considering the progress made to solve this type of problem, we also suggest some directions for future research. © 2014 Elsevier B.V.


Yilong Z.,Jiangsu University | Yilong Z.,Key Laboratory of Agricultural Information Acquisition Technology | Yilong Z.,Applied Technology Internet | Dean Z.,Jiangsu University | And 2 more authors.
International Journal of Electrochemical Science | Year: 2015

Nitrite has been widely used in industrial and agricultural production and is ubiquitous in food, water, biology and the environment. However, nitrite is also a toxic inorganic contaminant that is hazardous to the health of humans and other organisms. A variety of strategies have been proposed for detecting and monitoring nitrite in recent years. This article was compiled as a general review of the strategies proposed for nitrite detection, and relevant detection parameters (such as materials, detection limit, detection range, working pH and stability) were tabulated. This article is organized by the type of signal obtained from strategies, including electric and optical signals. Electrochemical methods receive an electric signal from dissolved nitrite, with voltammetric, potentiometric and impedimetric methods included. Methods that receive an optical signal include fluorescence, absorption and Raman spectrometry. Biosensors are proposed as a new detection method. The advantages/disadvantages and limitations of the techniques are discussed. Finally, methods employed to perform nitrite detection are summarized, and their future development is discussed. © 2015 The Authors.


Zeng L.,Key Laboratory of Agricultural Information Acquisition Technology | Zeng L.,Agricultural University of Hebei | Li D.,Key Laboratory of Agricultural Information Acquisition Technology | Li D.,Applied Technology Internet
Journal of Sensors | Year: 2015

Chlorophyll fuorescence measurement is a sensitive and effective method to quantify and analyze freshwater and sea water phytoplankton in situ. Major improvements in optical design, electronic technology, and calibration protocol have increased the accuracy and reliability of the fuorometer. This review briefy describes the improvement of probe design, excitation light sources, detectors, and calibrations of in situ fuorometers. Firstly, various optical designs for increasing the efficiency of fuorescence measurement are discussed. Next, the development of electronic technology to meet and improve in situ measurement, including various light sources, detectors, and corresponding measurement protocols, is described. In addition, various calibration materials, procedures, and methods are recommended for different kinds of water. The conclusion discusses key trends and future perspectives for in situ fuorescence sensors. Copyright © 2015 L. Zeng and D. Li.


Hu J.,China Agricultural University | Hu J.,Applied Technology Internet | Hu J.,Key Laboratory of Agricultural Information Acquisition Technology | Hu J.,Beijing Engineering Center for Advanced Sensors in Agriculture | And 15 more authors.
Computers and Electronics in Agriculture | Year: 2012

Remote diagnose of fish diseases for farmers is unrealized in China, but use of mobile phones and remote analysis based on image processing can be feasible due to the widespread use of mobile phones with camera features in rural areas. This paper presents a novel method of classifying species of fish based on color and texture features and using a multi-class support vector machine (MSVM). Fish images were acquired and sent by smartphone, and the method utilized was comprised of the following stages. Color and texture subimages of fish skin were obtained from original images. Color features, statistical texture features and wavelet-based texture features of the color and texture subimages were extracted, and six groups of feature vectors were composed. LIBSVM software was tested using leave-one-out cross validation to find the best group for classification in feature selection procedure. Two multi-class support vector machines based on a one-against-one algorithm were constructed for classification. The feature selection results showed that the Bior4.4 wavelet filter in HSV color space achieved greater accuracy than the other feature groups. The classification results indicate that only the DAGMSVM meets the requirement of time efficiency for the system. The results of this study suggest that the best classification model for fish species recognition is composed of a wavelet domain feature extractor with Bior4.4 wavelet filter in HSV color space and a one-against-one algorithm based DAGMSVM classifier. © 2012 Elsevier B.V.


Wang J.,China Agricultural University | Li L.,China Agricultural University | Mu Y.,Key Laboratory of Agricultural Information Acquisition Technology | Wang H.,China Agricultural University | Fu Q.,Key Laboratory of Agricultural Information Acquisition Technology
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | Year: 2015

Light intensity is one of the indispensable factors for plant growth and transpiration. Real-time monitoring light intensity and guiding irrigation by it can stimulate plant growth, simultaneously, and play a role in saving water and energy. In this paper, a practical light intensity detection system was designed in a simple way with low-cost. The silicon solar panel was used as the solar radiation sensor, which could directly transfer the sun's radiant energy into electric signals. The PIC16F876A MCU was used as the processor. The least square procedure was used to establish the model between the output voltage of silicon solar panel and the light intensity, then experiment was carried out to verify the performance of this system. The result showed that the average relative errors were around 1.19% in sunny days, around 1.57% in cloudy days, around 7.19% in rainy days, around 6.15% in changing weather, respectively. The average relative error was always below 10% in different weathers. The system accuracy was increasing while the light intensity increased. The system worked more precise when the light intensity was above 15000 lx with the average error of 1.41%. The resolution was 0.1 lx. The system repeatability error was very low (<0.63%), which means the system was running in high stability. In summary, this system could work stably in the solar greenhouse in different weathers. © 2015, Chinese Society for Agricultural Machinery. All right reserved.


Meng Q.,China Agricultural University | Qiu R.,China Agricultural University | Zhang M.,China Agricultural University | Liu G.,China Agricultural University | And 2 more authors.
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | Year: 2015

Taking agricultural vehicle with machine vision navigation as study object, a self-adaptive fuzzy control method with improved particle swarm optimization algorithm was designed. Firstly, by establishing 2-DOF steering model and visual preview model, lateral control equations of vehicle were described. Secondly, in order to improve the convergent speed of particle swarm optimization (PSO) algorithm, an improved PSO algorithm was designed. Finally, agricultural vehicle guidance system was a complex system with high nonlinearity, time-varying and large delay; therefore, an adaptive fuzzy controller was used for path tracking control. Correction factors were introduced into the fuzzy controller and particle swarm algorithm was used to optimize the correction factors. Taking the integral time absolute error (ITAE) sum of lateral offset and heading offset as the objective function, optimal correction factors were calculated by using PSO algorithm. Simulation and experimental results showed that the designed control algorithm could eliminate the lateral offset rapidly with less overshoot and rapid response. It retained the advantages of fuzzy control method and improved the control quality of guidance system. Compared with standard fuzzy control method, the improved fuzzy control method has a significant improvement on navigation accuracy under the same parameters condition. When the velocity of vehicle was 0.8 m/s, the maximum lateral offset of straight path and curve path were less than 4.2 cm and 5.9 cm respectively, which could meet the requirement of agricultural vehicle navigation. ©, 2015, Chinese Society of Agricultural Machinery. All right reserved.


Baoquan Y.,Key Laboratory of Agricultural Information Acquisition Technology | Baoquan Y.,China Agricultural University | Ruizhi S.,Key Laboratory of Agricultural Information Acquisition Technology | Hongjun Y.,Key Laboratory of Agricultural Information Acquisition Technology
International Journal of Smart Home | Year: 2015

With the development of technology and communication network, smartphones are increasingly used in emergency platforms. Under disaster environment, however, the information reporting system may confronted with poor communication conditions or low phone battery. In this study we first defined two parameters: the communication signal and the battery status. Based on the definitions, we proposed an algorithm for smartphone based reporting system under disaster environment. With the guarantee that disasters can be reported promptly and accurately and based on the analysis of smartphone power consumption, the algorithm provides power saving mechanisms to obviously increase the system working time. At last, a smartphone based disaster information reporting system (MDIRS) is designed and applied in disaster environment. © 2015 SERSC.


Ma J.,China Agricultural University | Ma J.,Key Laboratory of Agricultural Information Acquisition Technology | Li X.,China Agricultural University | Li X.,Key Laboratory of Agricultural Information Acquisition Technology | And 6 more authors.
Computers and Electronics in Agriculture | Year: 2015

Research reported in this paper aims to improve the identification of greenhouse vegetable diseases based on the greenhouse monitoring video. It presents a method that combines the visual saliency and online clustering to extract the key frame from greenhouse vegetables monitoring video. Firstly X2 histograms are used to measure the similarity of each frame to the first frame, which eliminates the meaningless frames and improve data processing efficiency and costs. Then, all frames will be converted to HSV color space and a saliency map of each frame is generated based on H component value and S component value. According to the saliency map, the salient region can be obtained. During the process of extracting the salient region, there is a possibility that the information of disease spots is lost. Therefore, morphological method would be utilized to restore the lost information. Finally, online clustering is performed to classify the salient regions into different clusters, and mean pixels value is used to select the key frames. The results indicate that this method can obtain information of entire leaf area of vegetables and extract the key frame effectively. © 2014 Elsevier B.V.

Loading Key Laboratory of Agricultural Information Acquisition Technology collaborators
Loading Key Laboratory of Agricultural Information Acquisition Technology collaborators