Date of Award:
12-2025
Document Type:
Thesis
Degree Name:
Master of Science (MS)
Department:
Civil and Environmental Engineering
Committee Chair(s)
Jeffery S. Horsburgh
Committee
Jeffery S. Horsburgh
Committee
Steve Petruzza
Committee
Sierra Young
Abstract
This thesis introduces a modern and automated method for monitoring rivers and streams using cameras and cloud-based software tools. Traditional monitoring methods often rely on sensors placed directly in the water, which can be expensive, hard to install, and difficult to maintain, especially in remote or rough terrain. In contrast, this approach uses cameras to observe water flow from a distance, offering a safer and more cost-effective alternative. However, camera systems come with their own challenges, such as collecting large amounts of image data, transferring it reliably from the field, and analyzing it quickly enough to be useful. This research addresses those challenges by developing a complete solution made up of two connected parts. The first part is focused on operations at the monitoring site, where images are captured automatically and sent to online storage in a consistent and organized way. This system was tested at real stream monitoring locations and worked smoothly for months, successfully collecting and delivering thousands of images without missing data. The second part is focused on analyzing the images. Once an image arrives in storage, it is automatically processed using computer vision to identify and measure areas of water in the scene. The information is then saved in a database, along with time and location details, so it can be used to understand river conditions over time. The entire system works without the need for constant human involvement and does not require any dedicated physical infrastructure beyond the camera and the datalogger used to capture the images. It is designed to be affordable and easily expandable to more sites as needed. By combining automated image collection with cloud-based analysis, this work offers a practical way for scientists and agencies to monitor rivers more efficiently. It provides a dependable and cost-effective alternative to traditional monitoring methods and helps support better decision making about water resources.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Neupane, Sajan, "Enabling Scalable Camera-Based Streamflow Monitoring With Serverless Cloud Computing" (2025). All Graduate Theses and Dissertations, Fall 2023 to Present. 636.
https://digitalcommons.usu.edu/etd2023/636
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .