Presentation Title

Unmanned Aerial Vehicles for Precision Agriculture in Orchard Crops

Faculty Mentor

Subodh Bhandari, Amar Raheja

Start Date

18-11-2017 2:15 PM

End Date

18-11-2017 3:15 PM

Location

BSC-Ursa Minor 82

Session

Poster 3

Type of Presentation

Poster

Subject Area

biological_agricultural_sciences

Abstract

The goal of this project is to develop an unmanned aerial vehicle (UAV) for precision agriculture using two different approaches. A UAV is equipped with a multispectral camera. The UAV is flown over an orchard of Orange trees at Cal Poly Pomona’s Spadra farm. The multispectral images are used in the determination of normalized differential vegetation index (NDVI) that provides information on the quality of the plant. Second approach uses machine learning algorithms for automated assessment of the plant performance using RGB images. The results are verified using handheld spectroradiometer and water potential meter. The outcome of the proposed project is the reduced cost and complexity associated with the use of UAVs for precision agriculture so that UAVs can be cost-effectively and readily used by farmers on a routine basis for stress detection, crop management, and crop dusting without requiring too much work and effort on their part. The project will be helpful in site specific management of the crops, thereby helping optimize the amount of fertilizer, pesticides, and water. The economic and societal impact of the project will be the development of a technology that will result in significant cost saving for farmers, increase in yield, and water conservation. Also, reduced use of fertilizers such as nitrogen will alleviate environmental impact. Soil moisture and soil nitrogen contents are determined prior to beginning the study by sending soil samples to soil testing lab. Future work will involve using hyperspectral sensors that can better detect stresses due to water and nutrient deficiencies than multispectral sensors.

Summary of research results to be presented

Strong correlations between hyperspectral data images from the UAVs and on the ground have been established, which improves the validity and reliability of data collected through flyover devices such as UAVs. Strong correlations have also been established between the NDVI, Spectroradiometer, and other ground truthing data such as the water potential measurements. This allows us to improve the precision of our instrumentation and the data collecting process itself for future research and development in this field.

This document is currently not available here.

Share

COinS
 
Nov 18th, 2:15 PM Nov 18th, 3:15 PM

Unmanned Aerial Vehicles for Precision Agriculture in Orchard Crops

BSC-Ursa Minor 82

The goal of this project is to develop an unmanned aerial vehicle (UAV) for precision agriculture using two different approaches. A UAV is equipped with a multispectral camera. The UAV is flown over an orchard of Orange trees at Cal Poly Pomona’s Spadra farm. The multispectral images are used in the determination of normalized differential vegetation index (NDVI) that provides information on the quality of the plant. Second approach uses machine learning algorithms for automated assessment of the plant performance using RGB images. The results are verified using handheld spectroradiometer and water potential meter. The outcome of the proposed project is the reduced cost and complexity associated with the use of UAVs for precision agriculture so that UAVs can be cost-effectively and readily used by farmers on a routine basis for stress detection, crop management, and crop dusting without requiring too much work and effort on their part. The project will be helpful in site specific management of the crops, thereby helping optimize the amount of fertilizer, pesticides, and water. The economic and societal impact of the project will be the development of a technology that will result in significant cost saving for farmers, increase in yield, and water conservation. Also, reduced use of fertilizers such as nitrogen will alleviate environmental impact. Soil moisture and soil nitrogen contents are determined prior to beginning the study by sending soil samples to soil testing lab. Future work will involve using hyperspectral sensors that can better detect stresses due to water and nutrient deficiencies than multispectral sensors.