During their growth, crops may experience a variety of health issues, which often lead to a reduction in crop yield. In order to avoid financial loss and sustain crop survival, it is imperative for farmers to detect and treat crop health issues. Interest in the use of unmanned aerial vehicles (UAVs) for precision agriculture has continued to grow as the cost of these platforms and sensing payloads has decreased. The increase in availability of this technology may enable farmers to scout their fields and react to issues more quickly and inexpensively than current satellite and other airborne methods. In the work of this thesis, methods have been developed for applications of UAV remote sensing using visible spectrum and multispectral imagery. An algorithm has been developed to work on a server for the remote processing of images acquired of a crop field with a UAV. This algorithm first enhances the images to adjust the contrast and then classifies areas of the image based upon the vigor and greenness of the crop. The classification is performed using a support vector machine with a Gaussian kernel, which achieved a classification accuracy of 86.4%. Additionally, an analysis of multispectral imagery was performed to determine indices which correlate with the health of corn crops. Through this process, a method for correcting hyperspectral images for lighting issues was developed. The Normalized Difference Vegetation Index values did not show a significant correlation with the health, but several indices were created from the hyperspectral data. Optimal correlation was achieved by using the reflectance values for 740 nm and 760 nm wavelengths, which produced a correlation coefficient of 0.84 with the yield of corn. In addition to this, two algorithms were created to detect stink bugs on crops with aerial visible spectrum images. The first method used a superpixel segmentation approach and achieved a recognition rate of 93.9%, although the processing time was high. The second method used an approach based upon texture and color and achieved a recognition rate of 95.2% while improving upon the processing speed of the first method. While both methods achieved similar accuracy, the superpixel approach allows for detection from higher altitudes, but this comes at the cost of extra processing time. / Master of Science / Crops can experience a variety of issues as they grow, which can reduce the amount of resulting crop. In order to avoid losing their crops and money, it is critical for farmers to detect and treat these issues. The current methods for detecting the issues can be expensive and have slow turnaround time to find the results. Unmanned aerial vehicles (UAVs) have emerged as a potential to improve upon the current methods and reduce the cost and turnaround time for determining issues. The UAVs can use a wide array of sensors to quickly and easily acquire information about the crop field. Using a variety of cameras, data can be gathered from the wavelengths which can be seen by humans as well as many other wavelengths outside of our visible spectrum. The work in this thesis uses images acquired from visible spectrum cameras as well as multispectral data, which uses a different range of wavelengths. A method was created to process the visible spectrum images to classify areas of the field based upon the health of the crop. This method was implemented on a server to allow a farmer to upload their images through the internet and have the data processed remotely. In addition to this, multispectral images were used to analyze the health of corn crops. The multispectral data can be used to create index values based upon various wavelengths of data. Many index values were analyzed and created to find relationships between these values and the health of the crops and strong relationships were found between some of the indices and the crop health. The final portion of this work uses standard visible spectrum images to detect the presence of stink bugs on crops. Two separate methods were created for this detection and both of these methods were able to accurately find stink bugs with a high success rate. The first method was able to detect the stink bugs from farther away than the second method, however the second method was able to perform the detection much faster.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/73048 |
| Date | 27 September 2016 |
| Creators | Whitehurst, Daniel Scott |
| Contributors | Mechanical Engineering, Kochersberger, Kevin B., Parikh, Devi, Thomason, Wade E., Furukawa, Tomonari |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | ETD, application/pdf, application/vnd.openxmlformats-officedocument.wordprocessingml.document |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0019 seconds