Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder release_atdcbyu4gngzjp34rno2px756i

by Rytis Augustauskas, Arunas Lipnickas

Published in Sensors by MDPI AG.

2020   Volume 20, Issue 9, p2557

Abstract

Convolutional neural networks perform impressively in complicated computer-vision image-segmentation tasks. Vision-based systems surpass humans in speed and accuracy in quality inspection tasks. Moreover, the maintenance of big infrastructures, such as roads, bridges, or buildings, is tedious and time-demanding work. In this research, we addressed pavement-quality evaluation by pixelwise defect segmentation using a U-Net deep autoencoder. Additionally, to the original neural network architecture, we utilized residual connections, atrous spatial pyramid pooling with parallel and "Waterfall" connections, and attention gates to perform better defect extraction. The proposed neural network configurations showed a segmentation performance improvement over U-Net with no significant computational overhead. Statistical and visual performance evaluation was taken into consideration for the model comparison. Experiments were conducted on CrackForest, Crack500, GAPs384, and mixed datasets.
In application/xml+jats format

Archived Files and Locations

application/pdf  9.3 MB
file_hgbej53j75anff6rkkct5r2dcq
res.mdpi.com (publisher)
web.archive.org (webarchive)

Web Captures

https://www.mdpi.com/1424-8220/20/9/2557/htm
2022-05-01 08:22:29 | 70 resources
webcapture_wlufh63b5bad3n6damf25dzsdm
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2020-04-30
Language   en ?
DOI  10.3390/s20092557
PubMed  32365925
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  1424-8220
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 78d1be4f-dfa3-4709-8b37-530b71c1a5aa
API URL: JSON