Thesis
Engineering a Smart Scarecrow: bird deterrence with drones
Washington State University
Master of Science (MS), Washington State University
2017
Handle:
https://hdl.handle.net/2376/103548
Abstract
Cherry, grape, and blueberry growers lose around 80 million dollars annually to bird damage in the state of Washington state alone. Growers of a wide range of crops have a critical need for a safe and cost-effective method for persistent bird deterrence, which would lead to significantly reduced production costs. The goal of this research is to build a completely autonomous Unmanned Aerial System (UAS) to deter birds from the blueberry fields. The objective of this thesis is to propose a method to use an Unmanned Aerial Vehicle (UAV) to deter birds from the farms. In the effort to build an autonomous system using UAV, the most vital part of its implementation is the vision system. The primary objective is to test a successful system for bird detection and then build a stereo vision system to estimate the distance of the birds, the distance can further be used to intercept the birds using UAVs. In order to do bird detection, background subtraction algorithms have been used and performances of various background subtraction algorithms is measured. It is found out that ViBe, a background subtraction algorithm performs best in the bird detection scenario providing an accuracy of 63.1% in terms of bird detection. In the quest of improving the bird detection speed and obtaining it in real time, a split window technique is used to improve the detection speed by 12.6%. In order to estimate the distance of the detected bird, a unique approach of a stereo vision system is proposed and compared with other methods to estimate the depth measure. In the quest of basing stereo vision system as a tool for bird distance estimation a prototype stereo vision system’s accuracy is determined. With this system an accurate measure of distance of the object is done up to 7 meters with an error accuracy of 30 centimeter. The long-term goal is to combine the efforts of the thesis to successfully create a completely autonomous Smart Scarecrow that can safely, effectively and reliably scare and deter birds.
Metrics
128 File views/ downloads
287 Record Views
Details
- Title
- Engineering a Smart Scarecrow
- Creators
- Shivam Goel
- Contributors
- Matthew E. Taylor (Chair)Manoj Karkee (Committee Member) - Washington State University, Biological Systems Engineering, Department ofHassan Ghasemzadeh (Committee Member) - Washington State University, Electrical Engineering and Computer Science, School of
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525272901842
- Language
- English
- Resource Type
- Thesis