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

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 ti...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Sensors (Basel, Switzerland) Ročník 20; číslo 9; s. 2557
Hlavní autori:	Augustauskas, Rytis, Lipnickas, Arūnas
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Switzerland MDPI 30.04.2020 MDPI AG
Predmet:	atrous spatial pyramid pooling attention gate CNN (Convolutional neural networks) deep learning pavement defects residual connection deep learning pavement defects atrous spatial pyramid pooling CNN (Convolutional neural networks) residual connection attention gate
ISSN:	1424-8220, 1424-8220
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1424-8220 1424-8220
DOI:	10.3390/s20092557