Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200901983> ?p ?o ?g. }
- W3200901983 endingPage "103941" @default.
- W3200901983 startingPage "103941" @default.
- W3200901983 abstract "Visual damage inspection of steel frames by eyes alone is time-consuming and cumbersome; therefore, it produces inconsistent results. Existing computer vision-based methods for inspecting civil structures using deep learning algorithms have not reached full maturity in exactly locating the damage. This paper presents a deep convolutional neural network-based damage locating (DCNN-DL) method that classifies the steel frame images provided as inputs as damaged and undamaged. DenseNet, a DCNN architecture, was trained to classify the damage. The DenseNet output was upscaled and superimposed on the original image to locate the damaged part of the steel frame. The DCNN-DL method was validated using 144 training and 114 validation sets of steel frame images. DenseNet, with an accuracy of 99.3%, outperformed MobileNet and ResNet with accuracies of 96.2% and 95.4%, respectively. This case study confirms that the DCNN-DL method effectively facilitates the real-time inspection and location of steel frame damage. • Deep learning approaches is proposed to locate the damaged part of the steel frame. • DenseNet based deep convolutional neural network is implemented and validated. • Data augmentation and Grad-CAM visualization techniques is implemented. • The proposed model accurately locates the damages in the steel structures." @default.
- W3200901983 created "2021-09-27" @default.
- W3200901983 creator A5015700005 @default.
- W3200901983 creator A5022553539 @default.
- W3200901983 creator A5042023338 @default.
- W3200901983 creator A5051146250 @default.
- W3200901983 creator A5059470260 @default.
- W3200901983 creator A5073787834 @default.
- W3200901983 date "2021-12-01" @default.
- W3200901983 modified "2023-10-17" @default.
- W3200901983 title "Investigation of steel frame damage based on computer vision and deep learning" @default.
- W3200901983 cites W1221860933 @default.
- W3200901983 cites W1842439412 @default.
- W3200901983 cites W1844128389 @default.
- W3200901983 cites W1976414028 @default.
- W3200901983 cites W1980492672 @default.
- W3200901983 cites W1995130521 @default.
- W3200901983 cites W2002816829 @default.
- W3200901983 cites W2006097152 @default.
- W3200901983 cites W2006879821 @default.
- W3200901983 cites W2020085751 @default.
- W3200901983 cites W2046464073 @default.
- W3200901983 cites W2057727857 @default.
- W3200901983 cites W2073872000 @default.
- W3200901983 cites W2078512023 @default.
- W3200901983 cites W2087119090 @default.
- W3200901983 cites W2091149439 @default.
- W3200901983 cites W2093303892 @default.
- W3200901983 cites W2100293947 @default.
- W3200901983 cites W2128880484 @default.
- W3200901983 cites W2169900910 @default.
- W3200901983 cites W2326670233 @default.
- W3200901983 cites W2435864801 @default.
- W3200901983 cites W2478677992 @default.
- W3200901983 cites W2516502154 @default.
- W3200901983 cites W2518741115 @default.
- W3200901983 cites W2565617119 @default.
- W3200901983 cites W2586750457 @default.
- W3200901983 cites W2598457882 @default.
- W3200901983 cites W2610755591 @default.
- W3200901983 cites W2621144451 @default.
- W3200901983 cites W2748510423 @default.
- W3200901983 cites W2748643398 @default.
- W3200901983 cites W2765527514 @default.
- W3200901983 cites W2768104711 @default.
- W3200901983 cites W2782104565 @default.
- W3200901983 cites W2782685003 @default.
- W3200901983 cites W2790840547 @default.
- W3200901983 cites W2791789798 @default.
- W3200901983 cites W2795998052 @default.
- W3200901983 cites W2803862859 @default.
- W3200901983 cites W2810063804 @default.
- W3200901983 cites W2901931129 @default.
- W3200901983 cites W2905163589 @default.
- W3200901983 cites W2909074876 @default.
- W3200901983 cites W2919816425 @default.
- W3200901983 cites W2922073063 @default.
- W3200901983 cites W2926691444 @default.
- W3200901983 cites W2939696013 @default.
- W3200901983 cites W2945554431 @default.
- W3200901983 cites W2955178892 @default.
- W3200901983 cites W2966168255 @default.
- W3200901983 cites W2972534151 @default.
- W3200901983 cites W2980994438 @default.
- W3200901983 cites W2982665332 @default.
- W3200901983 cites W2983902176 @default.
- W3200901983 cites W2990437404 @default.
- W3200901983 cites W2994143978 @default.
- W3200901983 cites W2999008617 @default.
- W3200901983 cites W3003588722 @default.
- W3200901983 cites W3019990046 @default.
- W3200901983 cites W3024475236 @default.
- W3200901983 cites W3024770686 @default.
- W3200901983 cites W3043870722 @default.
- W3200901983 cites W3088428216 @default.
- W3200901983 cites W3089874287 @default.
- W3200901983 cites W3097603411 @default.
- W3200901983 cites W3116760614 @default.
- W3200901983 cites W3125559191 @default.
- W3200901983 cites W3126210633 @default.
- W3200901983 cites W3146711186 @default.
- W3200901983 cites W3155902738 @default.
- W3200901983 cites W3163623175 @default.
- W3200901983 cites W2169096774 @default.
- W3200901983 doi "https://doi.org/10.1016/j.autcon.2021.103941" @default.
- W3200901983 hasPublicationYear "2021" @default.
- W3200901983 type Work @default.
- W3200901983 sameAs 3200901983 @default.
- W3200901983 citedByCount "22" @default.
- W3200901983 countsByYear W32009019832022 @default.
- W3200901983 countsByYear W32009019832023 @default.
- W3200901983 crossrefType "journal-article" @default.
- W3200901983 hasAuthorship W3200901983A5015700005 @default.
- W3200901983 hasAuthorship W3200901983A5022553539 @default.
- W3200901983 hasAuthorship W3200901983A5042023338 @default.
- W3200901983 hasAuthorship W3200901983A5051146250 @default.
- W3200901983 hasAuthorship W3200901983A5059470260 @default.
- W3200901983 hasAuthorship W3200901983A5073787834 @default.