Abstract

Blockage of culverts by transported debris materials is reported as the salient contributor in originating urban flash floods. Conventional hydraulic modeling approaches had no success in addressing the problem primarily because of the unavailability of peak floods hydraulic data and the highly non-linear behavior of debris at the culvert. This article explores a new dimension to investigate the issue by proposing the use of intelligent video analytics (IVA) algorithms for extracting blockage related information. The presented research aims to automate the process of manual visual blockage classification of culverts from a maintenance perspective by remotely applying deep learning models. The potential of using existing convolutional neural network (CNN) algorithms (i.e., DarkNet53, DenseNet121, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, VGG16, EfficientNetB3, NASNet) is investigated over a dataset from three different sources (i.e., images of culvert openings and blockage (ICOB), visual hydrology-lab dataset (VHD), synthetic images of culverts (SIC)) to predict the blockage in a given image. Models were evaluated based on their performance on the test dataset (i.e., accuracy, loss, precision, recall, F1 score, Jaccard Index, region of convergence (ROC) curve), floating point operations per second (FLOPs) and response times to process a single test instance. Furthermore, the performance of deep learning models was benchmarked against conventional machine learning algorithms (i.e., SVM, RF, xgboost). In addition, the idea of classifying deep visual features extracted by CNN models (i.e., ResNet50, MobileNet) using conventional machine learning approaches was also implemented in this article. From the results, NASNet was reported most efficient in classifying the blockage images with the 5-fold accuracy of 85%; however, MobileNet was recommended for the hardware implementation because of its improved response time with 5-fold accuracy comparable to NASNet (i.e., 78%). Comparable performance to standard CNN models was achieved for the case where deep visual features were classified using conventional machine learning approaches. False negative (FN) instances, false positive (FP) instances and CNN layers activation suggested that background noise and oversimplified labelling criteria were two contributing factors in the degraded performance of existing CNN algorithms. A framework for partial automation of the visual blockage classification process was proposed, given that none of the existing models was able to achieve high enough accuracy to completely automate the manual process. In addition, a detection-classification pipeline with higher blockage classification accuracy (i.e., 94%) has been proposed as a potential future direction for practical implementation.

Highlights

  • Cross-drainage structures are prone to blockage by debris and are reported as one of the leading causes of flash floods in urban areas [1,2,3,4,5,6,7]

  • This paper investigated the potential of convolutional neural network (CNN) algorithms towards classifying culvert images as “clear” or “blocked” as an automated solution for visual blockage inspections of culverts

  • Experimental Setup and Evaluation Measures Experiments were planned to investigate the performance of existing CNN models for binary classification of culvert images as blocked or clear

Read more

Summary

Introduction

Cross-drainage structures (e.g., culverts, bridges) are prone to blockage by debris and are reported as one of the leading causes of flash floods in urban areas [1,2,3,4,5,6,7]. To assess the visual blockage at culverts, manual visual inspections by flood management teams are performed to decide if a culvert needs maintenance towards avoiding the overtopping of flow and flash flooding. This process is inefficient in terms of required human resources and unsafe during peak flood events. This paper attempts to address the problem from a different perspective and proposes the use of visual information extracted using automated analysis in better management of blockage at cross drainage hydraulic structures and automating the process of manual culvert visual blockage status classification. The section lists potential future applications of the presented research

Deep Learning Models
DarkNet53
ResNet
MobileNet
InceptionV3 and InceptionResNet
DensNet121
NASNet
10 Training1E5pochs 20
Detection-Classification Pipeline for Visual Blockage Detection
Findings
Conclusions and Future Directions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call