Implementation of AI on Image Processing for Stormwater Control Measures Using Unmanned Aerial Vehicle (UAV)-Acquired Imagery
Publication: World Environmental and Water Resources Congress 2024
ABSTRACT
Due to lack of technologies, the world is struggling with flooding and water pollution from stormwater runoff. Efficient detection and monitoring of stormwater control measures (SCMs) play a crucial role in urban stormwater management. In order to improve and monitor the quality of our water systems, artificial intelligence (AI), drones, and image processing software are utilized. This research explores the application of AI and unmanned aerial vehicles (UAVs) for identifying SCMs and detecting trash accumulation on site. The use of image classification powered by AI on drone-acquired images provides us real-time monitoring and an aerial view for precise locations and size of the trash. It employs YOLOv8 (You Only Look Once version 8) for object detection model, Roboflow for image processing and AI, DJI Mavic 2 Pro drone, OpenCV, and ArcGIS pro. The methodology involves training the YOLOv8 model with a dataset of 480 images collected from the internet to recognize specific SCM types, such as rain gardens, bioretention basins, and permeable pavements. Once training is complete, we capture images using UAVs over the SCMs around the Centre for Built Environment and Infrastructure Studies (CBEIS) building at Morgan State University in Baltimore, Maryland. The UAV imagery aims to enhance the efficiency of stormwater management practices by showcasing the potential of combining UAVs and AI in a real-world testing environment. This enables the evaluation of the model’s accuracy and performance in detecting SCMs from different angles and conditions.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Calot, J. B., Galang, J. B. R., Lagrata, J. P. R., Marcelino, R. A. T., Buenconsejo, M. V., Poso, F. D., and Escarieses, L. L. E. (2022). Sustainable Drainage System: Low Impact Development Practices to Minimize the Storm Water Runoff. International Journal of Innovative Technology and Exploring Engineering, 1(4), 109–112.
Chen, C., Zhang, C., Schwarz, C., Tian, B., Jiang, W., Wu, W., and Zhou, Y. (2021). Mapping three-dimensional morphological characteristics of tidal salt-marsh channels using UAV structure-from-motion photogrammetry. Remote Sensing, 13(5), 832.
Chen, C., Zhang, C., Schwarz, C., Tian, B., Jiang, W., Wu, W., and Zhou, Y. (2021). Mapping three-dimensional morphological characteristics of tidal salt-marsh channels using UAV structure-from-motion photogrammetry. Remote Sensing, 13(5), 832.
Gathered rainfall data was used to simulate a hydraulic model using the storm water management model SWMM. “Sustainable Drainage System: Low Impact Development Practices to Minimize the Storm Water Runoff.” Jenny B. Calot et al. 01/04/2022.
Li, Y., Gundersen, H., Poulsen, R. N., Xie, L., Ge, Z., and Hancke, K. (2023). Quantifying seaweed and seagrass beach deposits using high-resolution UAV imagery. Marine Pollution Bulletin, 177, 113972.
Li, Y., Gundersen, H., Poulsen, R. N., Xie, L., Ge, Z., and Hancke, K. (2023). Quantifying seaweed and seagrass beach deposits using high-resolution UAV imagery. Marine Pollution Bulletin, 177, 113972.
Pratap, A., and Sardana, N. (2022). Machine learning-based image processing in materials science and engineering: A review. Journal of Materials Research and Technology, 20, 326–336.
Pratap, A., and Sardana, N. (2022). Machine learning-based image processing in materials science and engineering: A review. Journal of Materials Research and Technology, 20, 326–336.
Zhang, X., and Dahu, W. (2019). Application of artificial intelligence algorithms in image processing. Journal of Computer and Communications, 7(4), 16–28.
Zhang, X., and Dahu, W. (2019). Application of artificial intelligence algorithms in image processing. Journal of Computer and Communications, 7(4), 16–28.
Hamlett, J., Oloye, R., Brown, K., and Kang, D. H. (2023). Application of Artificial Intelligence (ai) and Unmanned Aerial Images (UAV) for Trash Detection in Stormwater Control Measures (SCMs).
McDonald, W. (2019). Drones in urban stormwater management: a review and future perspectives.
“Precision-Recall Curves: How to Easily Evaluate Machine Learning Models in No Time.” Better Data Science, betterdatascience.com/precision-recall-curves/. Accessed 5 Dec. 2023.
“Mean Average Precision (MAP) Explained: Everything You Need to Know.” V7, www.v7labs.com/blog/mean-average-precision. Accessed 5 Dec. 2023.
Information & Authors
Information
Published In
World Environmental and Water Resources Congress 2024
Pages: 320 - 326
History
Published online: May 16, 2024
ASCE Technical Topics:
- Aerospace engineering
- Air transportation
- Aircraft and spacecraft
- Artificial intelligence and machine learning
- Computer programming
- Computer vision and image processing
- Computing in civil engineering
- Engineering fundamentals
- Environmental engineering
- Equipment and machinery
- Infrastructure
- Methodology (by type)
- Pollution
- Stormwater management
- Transportation engineering
- Uncrewed vehicles
- Water pollution
- Water quality
- Water treatment
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.