Sewer Inlets Detection in UAV Images Clouds based on Convolution Neural Networks

Background

Unmanned aerial vehicle (UAV) systems have underwent significant advancements in recent years, which enabled the capture of high-resolution images and accurate measurements, with the tremendous development in artificial intelligence, especially deep learning techniques, Which allows it to be used in the development of Drainage infrastructures that represent a major challenge to confront the flood risks in urban areas and represent a considerable investment, but they are often not as well classified as they should be.

Methods

In this study, we present an automatic framework for the detection of sewer inlets and Ground Control Points (GCPs) from image clouds acquired by an Unmanned Aerial Vehicle (UAV) based on a YOLO CNN architecture. The framework depends on the high image overlap of unmanned aerial vehicle imaging surveys. The framework uses the latest YOLO model trained to detect and localize sewer inlets and Ground Control Points (GCPs) in aerial images with a ground sampling distance (GSD) of 1 cm/pixel. Novel Object-detection algorithms, including YOLOv5, YOLOv7, and YOLOv8 were compared in terms of the classification and localization of sewer inlets and GCPs marks. The approach is evaluated by cross-validating results from an image cloud of 500 UAV images captured over a 40,000-m² study area with 30 sewer inlets and 90 GCPs. To analyze the model accuracy among classes, two-way ANOVA is used.

Results

Images with models’ performances from the literature, the new YOLO model tested on UAV images in this study demonstrates satisfactory performance, improving both precision and recall. The results show that YOLOv5 offers the best precision (91%) and recall (96%), whereas YOLOv8 achieved less accuracy in precision and recall (82%) and (80%), respectively. Additionally, increasing image size in the training stage is a very important modification in the model.

Conclusion

The study approach has a remarkable ability to detect sewer inlets and can be used to develop the inventory of drainage infrastructure in urban areas.