UAV Remote Sensing Image Mosaic and Its Application in Agriculture

Yinjiang Jia,Zhongbin Su,Weizheng Shen,Jianqing Yuan,Zhenan Xu 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.5

UAV remote sensing image has the characteristics of higher spatial resolution, fine timeliness and high flexibility. It is widely used in many fields such as agriculture, forestry, soil resources and so on. Especially in agriculture, it plays an important role in information acquisition of agricultural production and agricultural condition monitoring. In the experiment, high-definition digital camera and multi-spectral camera are used to capture the visible light and near-infrared remote sensing image. Two pieces of 3m*3m calibration cloth is used for radiometric calibration and SIFT algorithm was used for image mosaic. This paper discusses the application of remote sensing image in agriculture, including rice lodging monitoring, diseases and pests monitoring, crop growth monitoring and crop nutrient diagnosis. The results show that UAV remote sensing provides an effective means for agricultural condition information acquisition, and has wide application prospect.

Hyperspectral Response of Rice Canopy and Prediction of Its Chlorophyll Content in Cold Regions

Jianqing Yuan,Zhongbin Su,Qingming Kong,Li Kang,Qi Zhang,Yu Zhang 보안공학연구지원센터 2015 International Journal of u- and e- Service, Scienc Vol.8 No.10

Based on field trials of different nitrogen levels, rice canopy chlorophyll content and canopy spectrum of its booting stage were respectively measured using the nitrogen balance index meter and the hyperspectral imager, in the Northeast of china. Analyzing the rice canopy spectral response characteristics under nitrogen gradient after canopy reflectance spectra were first extracted and filtered for noise, then the original reflectance spectra were transformed into the first derivative reflectance for further analysis. Stepwise analysis was carried out to select sensitive bands for canopy chlorophyll content by making correlation analysis and to build spectral indexes, and then chlorophyll content prediction models were generated and tested. After comparing, the two models with better estimation precision were the model with reflectivity at 572nm as a variable and the model with the index DSI(572,682) constructed the reflectivity at 572 and 682nm as a variable, the coefficients of determination R2 were 0.733 and 0.694, the root mean square errors RMSE were 2.9656 and 3.0346, and the relative errors RE% were 7.07% and 7.43%.

Intercomparison of ADC-Lite Images on UAV and TM Simulation Data for Soybean Leaf Area Index Retrieval

Qi Zhang,Zhongbin Su,Guijun Yang,Minghui Wang,Weizheng Shen,Xiaowei Teng,Jinhui Dong 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.7

Currently, TM images has a very high practical value and widely used in all aspects of agricultural. Unmanned Aerial Vehicles (UAV) remote sensing platform mounted ADC-Lite multi-spectral sensor has consistent channels response functions with TM sensor in TM2, TM3 and TM4, demonstrated to compete with TM sensor, due to low operational cost, high operational flexibility, high spatial resolution of imagery (0.018m with flight altitude 50m) and heterogeneity both at time and spatial-scale. In order to make sure whether it has widely used as TM sensor, moreover, the aim of this work is to assess ADC-Lite performance such as its adaptability and practicability. In this paper, ADC-Lite multi-spectral data, ground truth ASD hyperspectral and Leaf area index (LAI) data were acquired in soybean planting area, Jiaxiang County, Shandong Province on September18th, 2015. Since the ADC-Lite has different spatial scales with TM, this paper used TM simulation data transformed by ground truth ASD data, constructed LAI inversion model by empirical model based on two sensors and ground measured data, using 5 vegetation indices: ratio vegetation index (RVI), normalized difference vegetation index (NDVI), soil adjust vegetation index (SAVI), difference vegetation index (DVI) and triangular vegetation index (TVI). Determination coefficient R2, root mean square error (RMSE) and the estimation accuracy (EA) 3 indicators were acquired to assess the model. This work suggests that the established model of ADC-Lite sensor with TM simulation sensor has high consistency in accuracy. NDVI linear regression model derived from both of them presented a strong correlation with ground-measured LAI. It’s preliminarily shown that ADC-Lite images assess soybean LAI is feasible. This is anticipated to have tremendous implications that ADC-Lite can be made supplement for existing satellites, aerial and ground sensing, provide important information for Crop condition monitoring and critical data to support crop maturity, nutrition monitoring and fertilization management.

Remote Monitoring of Heading Rice Growing and Nitrogen Content Based on UAV Images

Yu Zhang,Zhongbin Su,Weizheng Shen,Renshan Jia,Jiling Luan 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.7

Rice heading is the critical stage of the growth of rice, rice plants are relatively large, field canopy, poor resistance, and coincided with the high temperature and rainy weather, pests and diseases are more prone period. Therefore, the use of UAV to monitor the growth status of rice, easy to understand rice growth and nutritional status, in order to achieve high-quality, high yield, efficient purpose. This article is the field experiments under different nitrogen levels, using UAV monitoring multispectral images of rice, by reference remote sensing spectral indices, derived green normalized difference vegetation index (GNDVI) relative to other spectral index is more suitable for rice field biomass inversion modeling. At the same time, this study is based on the inversion model, implemented the rice growing and nitrogen content graded by ISODATA methods in ENVI. Achieved classification on rice growth and nitrogen remote sensing thematic map in ArcGIS, to provide timely and accurate information for rice seedling diagnosis and management decision, has reached the purpose of rice production precise management.

Research on UAV Remote Sensing Image Mosaic Method Based on SIFT

Yinjiang Jia,Zhongbin Su,Qi Zhang,Yu Zhang,Yunhao Gu,Zhongqiu Chen 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.11

UAV remote sensing, as a new method of remote sensing, has the characteristics of higher spatial resolution, fine timeliness and high flexibility. It is widely used in the field of natural disaster monitoring, urban planning, resource investigation, and has become one of the indispensable method of remote sensing data acquisition. However, because the UAV remote sensing platform is limited by the flight height and focal length of camera, the acquired image size is smaller, single image can’t cover the entire target area. Therefore, image mosaic has become a key technology to solve the problem. Image matching and image fusion are the key techniques of image mosaic. Due to the good robustness of image scaling, translation and rotation, this paper uses the SIFT algorithm to realize image matching of UAV. Since the feature extraction may produce false matches, RANSAC algorithm is applied to the feature point purification points. According to the seam-line in jointing overlap region, weighted fusion algorithm is applied to realize the image seamless splicing.

Design and Implementation of Soil Nutrient Monitoring System Based on “3S” Technology

Di Zu,Zhongbin Su,Xiaodong Yang,Xiaohe Gu,Yancang Wang 보안공학연구지원센터 2015 International Journal of Smart Home Vol.9 No.5

Soil nutrient monitoring system is to master the nutrient status of the bare ground, and quickly extract the information of farmland nutrient. Because of having a significant impact on the crop, the soil nutrient monitoring is important. For the lack of monitoring soil nutrient monitoring currently, combined with “3S” technology, spatial database technology, computer network technology and modern agricultural information technology as the basis, using WebGIS Service standard spatial database engine, the soil nutrient monitoring system based on soil nutrient information of Yangling was scientifically constructed. It achieved soil nutrient management from the large-scale, made the monitoring process towards standardization, improved management efficiency and scientific level, and provided technical support for farmland quality decisions.

The Construction of the Animal Husbandry Information System Based on the Technology of Map Conflation

Yue Guo,Zhongbin Su,Weizheng Shen,Zhipeng Guo,Qingming Kong 보안공학연구지원센터 2015 International Journal of Smart Home Vol.9 No.3

The research aims to merge the sections of geographic information distribution of the large-scale farms information monitoring system and the farming enterprises filing system which are under the Animal Husbandry Bureau in Heilongjiang Province as a Geographic Information System (GIS) that based on the map conflation technology of topological relation. Applying a variety of algorithms of points, lines, surfaces to this study, and using optimized "Spider code" and matching algorithm based on area overlay rate to solve the map database conflation problem of two different sources but consistent geographic target. It not only improves the map accuracy and consistency, but also adds new space characteristics, and updates attribute information which associated with dataset spatial characteristics. It makes the personnel at all levels in the Animal Husbandry Bureau in Heilongjiang Province realize information sharing. It is conductive to promote the work of staff at all levels and provide decision support of data to the Animal Husbandry Bureau in Heilongjiang Province.

Near-infrared Detection of Straw Cellulose by Orthogonal Signal Correction and Partial Least Squares

Qingming Kong,Zhongbin Su,Weizheng Shen,Mingming Han,Bohan Li,Xudong Wang 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.5

Orthogonal signal correction (OSC)and partial least squares(PLS)were used during the pretreatment of straw to reduce environmental noise and prediction models were established for near-infrared detection of straw cellulose. Tests were run with soybean stalk as the object of study. Test results indicated that compared to a model established using a traditional denoising method, the determination coefficients for calibration set models established by second derivative+smoothing and OSC were 0.9318595 and 0.9328905 respectively while the root mean square error for calibration (RMSEC) were 0.6762902 and 0.6696454. For an OSC-PLS regression model with a factor of 8, the relative standard deviation of a prediction model was less than 5%. In the OSC denoising process, the root mean square error fluctuated with the increasing number of PLS factors. Compared to the second derivative-smoothing denoising, OSC-PLS denoising removed the non-correlated variation from spectra and improved interpretation ability of variation while the analysis and convergence were expedited. It was therefore concluded that OSC-PLS denoising could be used to realize the rapid and accurate near-infrared detection of straw cellulose.

Design and Implementation of Livestock House Environmental Perception System Based on Wireless Sensor Networks

Weizheng Shen,Guanting Liu,Zhongbin Su,Rongyu Su,Yu Zhang 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.5

In order to monitor the six factors which is the most crucial influence on livestock production in livestock house, this paper designs a set of livestock house(LH) environmental perception system based on wireless sensor networks. This system is composed by a number of data acquisition nodes(DAN) connected by using Wireless Sensor Networks. Inside of DAN is equipped with six type of sensor which in charge of collecting Real-time environmental data in LH, including carbon dioxide sensor, ammonia gas sensor, illumination sensor, relative humidity sensor and so on. The communication mode between upper-computer and central node is GPRS, to research on remotely control environmental parameters in LH in the future. The upper-computer could treat data which is uploaded by several central nodes through some way, for example, data analysis based on established protocol, threshold judgment, etc. Then, the real-time data is stored by database. The stability and veracity of the system was verified by field tests which set technical grade monitors as control groups. Comparing with industrial-grade high precision monitoring instruments, the error of collecting data and wireless communication network is within normal error range, By SPSS, the result shows that there is no significant difference of P-Value(P>0.05) in different groups at same time.

Research on the Real-time Monitoring System of Cow’s Rumination

Shuang Zhang,Yu Zhang,Weizheng Shen,Lu Xu,Hao Wu,Zhongbin Su 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.7

Cow’s rumination is an important process of food digestion for dairy cows which is a valuable indicator during the cow management. By measuring the cow’s rumination time, it is capable to predict the cow’s estrus, and learn the cow’s health situation. This paper uses MSP430F149 processor with a sound sensor to achieve the design of real-time monitoring system for cow’s rumination. Since the system require high accuracy of the audio signal of the cow’s rumination, the ADC acquisition module and filtering and amplification process was made a special design. For the change of the spectral characteristics of the voice when cows ruminating, this paper designed the endpoint detection algorithm and sound sequence windowed function, and FFT transform is performed on the data in the Hamming window, and then do the frequency domain analysis to the audio of cow’s rumination. Comparing the sound spectrum collected from high precision recording instrument and this system, this system has done a good job in frequency and time domain. Applying the high precision recording instrument to the simulation experiment for cow’s rumination which conduct 50 sets of different time ranging, using this system to do the real-time monitoring, the mean error was 4.38, the R2 value is 0.877, the Pearson correlation was 0.936. This system performed accurate in the acquisition of the sound signal, and more accurately in identifying cows ruminating, and it can also provide effective means for the intelligent management of the pasture on cow’s health and breeding.