Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285346075> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4285346075 abstract "Timely and accurate detection of the initiation and expansion of crack is of great significance for improving safe operation of civil infrastructures. Image-based visual surface inspection has been an indispensable way for long-time infrastructure monitoring. However, existing crack detection methods generally suffer from the interference of complex background, leading to obvious performance drops. To tackle this, an improved encoder-decoder architecture based on SegNet is proposed in this paper, namely crack-SegNet. The encoder network hierarchically learns visual features from the original image, and the decoder network gradually up-samples and maps the encoded features to the input size for the pixel-level classification. In order to enhance the feature capacity of cracks in complex background, a channel attention mechanism is integrated into the encoder, as well as a spatial attention module in the decoder to improve the feature representation of cracks. Meanwhile, a spatial pyramid pooling is also attached to the last convolutional layer of the encoder to capture crack with different scales. To better validate the proposed method, a challenging metal surface crack dataset with much more complex background is collected. Experimental results on the datasets show that the proposed crack-SegNet outperforms other state-of-the-art crack detection methods, especially in complex background." @default.
- W4285346075 created "2022-07-14" @default.
- W4285346075 creator A5027936122 @default.
- W4285346075 creator A5041458559 @default.
- W4285346075 creator A5046468326 @default.
- W4285346075 creator A5084292057 @default.
- W4285346075 creator A5085904194 @default.
- W4285346075 date "2021-10-15" @default.
- W4285346075 modified "2023-09-27" @default.
- W4285346075 title "Crack-SegNet: Surface Crack Detection in Complex Background Using Encoder-Decoder Architecture" @default.
- W4285346075 cites W1849277567 @default.
- W4285346075 cites W1884395441 @default.
- W4285346075 cites W1963857321 @default.
- W4285346075 cites W2031703128 @default.
- W4285346075 cites W2109255472 @default.
- W4285346075 cites W2242960398 @default.
- W4285346075 cites W2407692387 @default.
- W4285346075 cites W2471601214 @default.
- W4285346075 cites W2511065100 @default.
- W4285346075 cites W2794732825 @default.
- W4285346075 cites W2902195199 @default.
- W4285346075 cites W2920768970 @default.
- W4285346075 cites W2963881378 @default.
- W4285346075 cites W2982564821 @default.
- W4285346075 cites W3009712583 @default.
- W4285346075 cites W3010717703 @default.
- W4285346075 doi "https://doi.org/10.1145/3502814.3502817" @default.
- W4285346075 hasPublicationYear "2021" @default.
- W4285346075 type Work @default.
- W4285346075 citedByCount "2" @default.
- W4285346075 countsByYear W42853460752022 @default.
- W4285346075 countsByYear W42853460752023 @default.
- W4285346075 crossrefType "proceedings-article" @default.
- W4285346075 hasAuthorship W4285346075A5027936122 @default.
- W4285346075 hasAuthorship W4285346075A5041458559 @default.
- W4285346075 hasAuthorship W4285346075A5046468326 @default.
- W4285346075 hasAuthorship W4285346075A5084292057 @default.
- W4285346075 hasAuthorship W4285346075A5085904194 @default.
- W4285346075 hasConcept C111919701 @default.
- W4285346075 hasConcept C118505674 @default.
- W4285346075 hasConcept C138885662 @default.
- W4285346075 hasConcept C142575187 @default.
- W4285346075 hasConcept C153180895 @default.
- W4285346075 hasConcept C154945302 @default.
- W4285346075 hasConcept C160633673 @default.
- W4285346075 hasConcept C2524010 @default.
- W4285346075 hasConcept C2776401178 @default.
- W4285346075 hasConcept C31972630 @default.
- W4285346075 hasConcept C33923547 @default.
- W4285346075 hasConcept C41008148 @default.
- W4285346075 hasConcept C41895202 @default.
- W4285346075 hasConcept C70437156 @default.
- W4285346075 hasConcept C81363708 @default.
- W4285346075 hasConceptScore W4285346075C111919701 @default.
- W4285346075 hasConceptScore W4285346075C118505674 @default.
- W4285346075 hasConceptScore W4285346075C138885662 @default.
- W4285346075 hasConceptScore W4285346075C142575187 @default.
- W4285346075 hasConceptScore W4285346075C153180895 @default.
- W4285346075 hasConceptScore W4285346075C154945302 @default.
- W4285346075 hasConceptScore W4285346075C160633673 @default.
- W4285346075 hasConceptScore W4285346075C2524010 @default.
- W4285346075 hasConceptScore W4285346075C2776401178 @default.
- W4285346075 hasConceptScore W4285346075C31972630 @default.
- W4285346075 hasConceptScore W4285346075C33923547 @default.
- W4285346075 hasConceptScore W4285346075C41008148 @default.
- W4285346075 hasConceptScore W4285346075C41895202 @default.
- W4285346075 hasConceptScore W4285346075C70437156 @default.
- W4285346075 hasConceptScore W4285346075C81363708 @default.
- W4285346075 hasLocation W42853460751 @default.
- W4285346075 hasOpenAccess W4285346075 @default.
- W4285346075 hasPrimaryLocation W42853460751 @default.
- W4285346075 hasRelatedWork W2090093270 @default.
- W4285346075 hasRelatedWork W2291847203 @default.
- W4285346075 hasRelatedWork W2756241593 @default.
- W4285346075 hasRelatedWork W2758063741 @default.
- W4285346075 hasRelatedWork W2760085659 @default.
- W4285346075 hasRelatedWork W2940661641 @default.
- W4285346075 hasRelatedWork W2944724518 @default.
- W4285346075 hasRelatedWork W2951391129 @default.
- W4285346075 hasRelatedWork W2969680539 @default.
- W4285346075 hasRelatedWork W4283454150 @default.
- W4285346075 isParatext "false" @default.
- W4285346075 isRetracted "false" @default.
- W4285346075 workType "article" @default.