Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328006268> ?p ?o ?g. }
- W4328006268 abstract "Road detection plays a vital role in advanced driver assistance systems (ADAS). In recent years, the mainstream methods use the data fusion to combine the advantages of RGB images and depth images. However, the fusion operation utilizes a simple pixel-wise summation and concatenation strategy, leading to lose the correlation between the two types of data. To this end, inspired by the core idea of Transformer, we propose a cross attention transformation module, which effectively fuses the RGB features and depth features using the attention mechanism. Specifically, the correlation attention features of RGB-D are generated by the cross-attention mechanism. Then the attention features are fused to enhance the attention response and capture global context information. Experiments are conducted in the two popular datasets including the KITTI road dataset and Cityscapes dataset. Empirical results show that the accuracy of road detection is improved by our fusion method. In the KITTI road Benchmark, Our method gets the better MaxF in UM_Road(95.02 %) and UMM_Road(97.03%)." @default.
- W4328006268 created "2023-03-22" @default.
- W4328006268 creator A5004635944 @default.
- W4328006268 creator A5005883846 @default.
- W4328006268 creator A5010193927 @default.
- W4328006268 creator A5049881552 @default.
- W4328006268 creator A5069139562 @default.
- W4328006268 creator A5071701075 @default.
- W4328006268 creator A5081034893 @default.
- W4328006268 creator A5083766710 @default.
- W4328006268 date "2022-08-01" @default.
- W4328006268 modified "2023-10-16" @default.
- W4328006268 title "CAT: Using Cross Attention Transformation to Build Correlation of RGB-D for Road Detection" @default.
- W4328006268 cites W2115579991 @default.
- W4328006268 cites W2194775991 @default.
- W4328006268 cites W2340897893 @default.
- W4328006268 cites W2565639579 @default.
- W4328006268 cites W2607626645 @default.
- W4328006268 cites W2765382011 @default.
- W4328006268 cites W2791440580 @default.
- W4328006268 cites W2792727293 @default.
- W4328006268 cites W2891529090 @default.
- W4328006268 cites W2932012013 @default.
- W4328006268 cites W2954496794 @default.
- W4328006268 cites W2963446712 @default.
- W4328006268 cites W2963591855 @default.
- W4328006268 cites W2978321147 @default.
- W4328006268 cites W2995118031 @default.
- W4328006268 cites W3024771345 @default.
- W4328006268 cites W3096609285 @default.
- W4328006268 cites W3108704700 @default.
- W4328006268 cites W3130089842 @default.
- W4328006268 cites W3170841864 @default.
- W4328006268 cites W3190666950 @default.
- W4328006268 cites W3203286921 @default.
- W4328006268 cites W3207814250 @default.
- W4328006268 cites W3212682082 @default.
- W4328006268 cites W3214586131 @default.
- W4328006268 doi "https://doi.org/10.1109/bigcom57025.2022.00046" @default.
- W4328006268 hasPublicationYear "2022" @default.
- W4328006268 type Work @default.
- W4328006268 citedByCount "0" @default.
- W4328006268 crossrefType "proceedings-article" @default.
- W4328006268 hasAuthorship W4328006268A5004635944 @default.
- W4328006268 hasAuthorship W4328006268A5005883846 @default.
- W4328006268 hasAuthorship W4328006268A5010193927 @default.
- W4328006268 hasAuthorship W4328006268A5049881552 @default.
- W4328006268 hasAuthorship W4328006268A5069139562 @default.
- W4328006268 hasAuthorship W4328006268A5071701075 @default.
- W4328006268 hasAuthorship W4328006268A5081034893 @default.
- W4328006268 hasAuthorship W4328006268A5083766710 @default.
- W4328006268 hasConcept C104317684 @default.
- W4328006268 hasConcept C114614502 @default.
- W4328006268 hasConcept C13280743 @default.
- W4328006268 hasConcept C154945302 @default.
- W4328006268 hasConcept C160633673 @default.
- W4328006268 hasConcept C166957645 @default.
- W4328006268 hasConcept C185592680 @default.
- W4328006268 hasConcept C185798385 @default.
- W4328006268 hasConcept C204241405 @default.
- W4328006268 hasConcept C205649164 @default.
- W4328006268 hasConcept C2779343474 @default.
- W4328006268 hasConcept C31972630 @default.
- W4328006268 hasConcept C33923547 @default.
- W4328006268 hasConcept C33954974 @default.
- W4328006268 hasConcept C41008148 @default.
- W4328006268 hasConcept C55493867 @default.
- W4328006268 hasConcept C82990744 @default.
- W4328006268 hasConcept C87619178 @default.
- W4328006268 hasConcept C87833898 @default.
- W4328006268 hasConceptScore W4328006268C104317684 @default.
- W4328006268 hasConceptScore W4328006268C114614502 @default.
- W4328006268 hasConceptScore W4328006268C13280743 @default.
- W4328006268 hasConceptScore W4328006268C154945302 @default.
- W4328006268 hasConceptScore W4328006268C160633673 @default.
- W4328006268 hasConceptScore W4328006268C166957645 @default.
- W4328006268 hasConceptScore W4328006268C185592680 @default.
- W4328006268 hasConceptScore W4328006268C185798385 @default.
- W4328006268 hasConceptScore W4328006268C204241405 @default.
- W4328006268 hasConceptScore W4328006268C205649164 @default.
- W4328006268 hasConceptScore W4328006268C2779343474 @default.
- W4328006268 hasConceptScore W4328006268C31972630 @default.
- W4328006268 hasConceptScore W4328006268C33923547 @default.
- W4328006268 hasConceptScore W4328006268C33954974 @default.
- W4328006268 hasConceptScore W4328006268C41008148 @default.
- W4328006268 hasConceptScore W4328006268C55493867 @default.
- W4328006268 hasConceptScore W4328006268C82990744 @default.
- W4328006268 hasConceptScore W4328006268C87619178 @default.
- W4328006268 hasConceptScore W4328006268C87833898 @default.
- W4328006268 hasLocation W43280062681 @default.
- W4328006268 hasOpenAccess W4328006268 @default.
- W4328006268 hasPrimaryLocation W43280062681 @default.
- W4328006268 hasRelatedWork W2139599928 @default.
- W4328006268 hasRelatedWork W2283162247 @default.
- W4328006268 hasRelatedWork W2563827614 @default.
- W4328006268 hasRelatedWork W2593793146 @default.
- W4328006268 hasRelatedWork W2739874619 @default.
- W4328006268 hasRelatedWork W2767823485 @default.
- W4328006268 hasRelatedWork W2980049530 @default.
- W4328006268 hasRelatedWork W3005455252 @default.