Concrete Dam Inspection with UAV Imagery and DCNN-based Object Detection | IEEE Conference Publication | IEEE Xplore

Concrete Dam Inspection with UAV Imagery and DCNN-based Object Detection


Abstract:

This work aims at developing a solution to aid concrete dam inspections using unmanned aerial vehicle (UAV) imagery and DCNN-based (deep convolutional neural network) obj...Show More

Abstract:

This work aims at developing a solution to aid concrete dam inspections using unmanned aerial vehicle (UAV) imagery and DCNN-based (deep convolutional neural network) object detection. This paper introduces materials used to create the Sentinel dataset, which is a heterogeneous dataset that contains 304 images on the training set and 316 images on the test set from a roller-compacted concrete water dam, with a Creager profile spillway, with annotation of three different types of objects: unwanted objects, harmless objects, and structural damage. This work proposes the use of the Faster R-RCNN and the Single Shot Multibox Detector, which are two deep convolutional neural networks for object detection with singular architectures, to identify nonconformity during an automatic dam inspection system, and analyzes the robustness of both networks considering the accuracy, true positive rate, true negative rate, precision, and F1 metrics. Using the Sentinel dataset, the best result yielded a Faster R-RCNN model with accuracy and an F1 score of 88.9%, which shows the viability of using the proposed solution in an operational environment.
Date of Conference: 24-26 August 2021
Date Added to IEEE Xplore: 27 December 2021
ISBN Information:
Print on Demand(PoD) ISSN: 1558-2809
Conference Location: Kaohsiung, Taiwan

I. Introduction

Civil infrastructures, like dams and bridges, are susceptible to deterioration over time, so Structural Health Monitoring (SHM) techniques are essential to maintain the structure health conditions for a safely daily use [1]. To achieve assurance of safety in dam structure, it requires a series of concomitant, continuous, and organized activities to mitigate the potential risk of collapse, which leads to social, economic, and environmental disasters. Ideally, dam control and inspection operations must contain redundant protocols to guarantee that they extrapolate beyond operational risks [2] and must be done in many and different levels. Monitoring and evaluating the safety of a concrete dam structure is a challenging task, as many uncontrollable variables can influence a dam structure’s, such as temperature, humidity, rain, river level. For this reason, it is relevant to identify indicators that may reflect the dam structure’s health through different sources, as sensors and visual inspection.

References

References is not available for this document.