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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2557 |
| _version_ | 1827717708811075584 |
|---|---|
| author | Rytis Augustauskas Arūnas Lipnickas |
| author_facet | Rytis Augustauskas Arūnas Lipnickas |
| author_sort | Rytis Augustauskas |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T20:07:14Z |
| format | Article |
| id | doaj.art-3057663424d34d04b25a96ef0cf64f77 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:07:14Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3057663424d34d04b25a96ef0cf64f772023-11-19T23:09:02ZengMDPI AGSensors1424-82202020-04-01209255710.3390/s20092557Improved Pixel-Level Pavement-Defect Segmentation Using a Deep AutoencoderRytis Augustauskas0Arūnas Lipnickas1Department of Automation, Kaunas University of Technology, 51367 Kaunas, LithuaniaDepartment of Automation, Kaunas University of Technology, 51367 Kaunas, LithuaniaConvolutional 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.https://www.mdpi.com/1424-8220/20/9/2557CNN (Convolutional neural networks)deep learningpavement defectsresidual connectionattention gateatrous spatial pyramid pooling |
| spellingShingle | Rytis Augustauskas Arūnas Lipnickas Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder Sensors CNN (Convolutional neural networks) deep learning pavement defects residual connection attention gate atrous spatial pyramid pooling |
| title | Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder |
| title_full | Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder |
| title_fullStr | Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder |
| title_full_unstemmed | Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder |
| title_short | Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder |
| title_sort | improved pixel level pavement defect segmentation using a deep autoencoder |
| topic | CNN (Convolutional neural networks) deep learning pavement defects residual connection attention gate atrous spatial pyramid pooling |
| url | https://www.mdpi.com/1424-8220/20/9/2557 |
| work_keys_str_mv | AT rytisaugustauskas improvedpixellevelpavementdefectsegmentationusingadeepautoencoder AT arunaslipnickas improvedpixellevelpavementdefectsegmentationusingadeepautoencoder |