Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319069384> ?p ?o ?g. }
- W4319069384 endingPage "9" @default.
- W4319069384 startingPage "1" @default.
- W4319069384 abstract "Lane mark detection is an important task for autonomous driving. Many researchers have proposed many models. But the driving environment is much more complex, especially for some challenging scenarios, such as vehicle occlusion, severe mark degradation, heavy shadow, and so on. It is difficult to detect lane mark in a limited local receptive field under the above scenarios. For that reason, we propose a lane mark detection network based on multihead self-attention. It can find spatial relationships among lane mark points in the global viewpoint and enlarge its feature map’s receptive field equally. For further extracting global and contextual features, it fuses global information and local information together to predict classification and location regression. Finally, it can promote accuracy of lane mark detection greatly especially in challenging scenarios. In the TuSimple benchmark, its accuracy is 95.76% overwhelming all other methods, and its FPS is 170.2, which is the second-highest one. In CULane benchmark its F1 achieves 75.55% and FPS reaches 170.5. Both of them are the highest compared to other methods. Our proposed model establishes a new state-of-the-art among real-time methods." @default.
- W4319069384 created "2023-02-04" @default.
- W4319069384 creator A5026954083 @default.
- W4319069384 creator A5063521250 @default.
- W4319069384 creator A5068277313 @default.
- W4319069384 date "2023-02-03" @default.
- W4319069384 modified "2023-10-14" @default.
- W4319069384 title "Lane Marker Detection Based on Multihead Self-Attention" @default.
- W4319069384 cites W1901129140 @default.
- W4319069384 cites W1968256263 @default.
- W4319069384 cites W1976362452 @default.
- W4319069384 cites W2082747607 @default.
- W4319069384 cites W2094990266 @default.
- W4319069384 cites W2125022378 @default.
- W4319069384 cites W2131076267 @default.
- W4319069384 cites W2159132531 @default.
- W4319069384 cites W2194775991 @default.
- W4319069384 cites W2529429228 @default.
- W4319069384 cites W2548928501 @default.
- W4319069384 cites W2743418434 @default.
- W4319069384 cites W2780740184 @default.
- W4319069384 cites W2909761845 @default.
- W4319069384 cites W2963351448 @default.
- W4319069384 cites W2963881378 @default.
- W4319069384 cites W2964199920 @default.
- W4319069384 cites W2964332990 @default.
- W4319069384 cites W2981441441 @default.
- W4319069384 cites W2989279786 @default.
- W4319069384 cites W2995724453 @default.
- W4319069384 cites W3014005442 @default.
- W4319069384 cites W3030898108 @default.
- W4319069384 cites W3034985293 @default.
- W4319069384 cites W3100397002 @default.
- W4319069384 cites W3102168793 @default.
- W4319069384 cites W3109790059 @default.
- W4319069384 cites W3152847769 @default.
- W4319069384 cites W3157173860 @default.
- W4319069384 cites W3176566042 @default.
- W4319069384 cites W4213345160 @default.
- W4319069384 cites W4221093948 @default.
- W4319069384 cites W4221101697 @default.
- W4319069384 cites W4282921501 @default.
- W4319069384 cites W4289763872 @default.
- W4319069384 doi "https://doi.org/10.1155/2023/2075022" @default.
- W4319069384 hasPublicationYear "2023" @default.
- W4319069384 type Work @default.
- W4319069384 citedByCount "0" @default.
- W4319069384 crossrefType "journal-article" @default.
- W4319069384 hasAuthorship W4319069384A5026954083 @default.
- W4319069384 hasAuthorship W4319069384A5063521250 @default.
- W4319069384 hasAuthorship W4319069384A5068277313 @default.
- W4319069384 hasBestOaLocation W43190693841 @default.
- W4319069384 hasConcept C117797892 @default.
- W4319069384 hasConcept C119857082 @default.
- W4319069384 hasConcept C13280743 @default.
- W4319069384 hasConcept C138885662 @default.
- W4319069384 hasConcept C153180895 @default.
- W4319069384 hasConcept C154945302 @default.
- W4319069384 hasConcept C15744967 @default.
- W4319069384 hasConcept C162324750 @default.
- W4319069384 hasConcept C185798385 @default.
- W4319069384 hasConcept C187736073 @default.
- W4319069384 hasConcept C202444582 @default.
- W4319069384 hasConcept C205649164 @default.
- W4319069384 hasConcept C2776401178 @default.
- W4319069384 hasConcept C2780451532 @default.
- W4319069384 hasConcept C31972630 @default.
- W4319069384 hasConcept C33923547 @default.
- W4319069384 hasConcept C41008148 @default.
- W4319069384 hasConcept C41895202 @default.
- W4319069384 hasConcept C542102704 @default.
- W4319069384 hasConcept C9652623 @default.
- W4319069384 hasConceptScore W4319069384C117797892 @default.
- W4319069384 hasConceptScore W4319069384C119857082 @default.
- W4319069384 hasConceptScore W4319069384C13280743 @default.
- W4319069384 hasConceptScore W4319069384C138885662 @default.
- W4319069384 hasConceptScore W4319069384C153180895 @default.
- W4319069384 hasConceptScore W4319069384C154945302 @default.
- W4319069384 hasConceptScore W4319069384C15744967 @default.
- W4319069384 hasConceptScore W4319069384C162324750 @default.
- W4319069384 hasConceptScore W4319069384C185798385 @default.
- W4319069384 hasConceptScore W4319069384C187736073 @default.
- W4319069384 hasConceptScore W4319069384C202444582 @default.
- W4319069384 hasConceptScore W4319069384C205649164 @default.
- W4319069384 hasConceptScore W4319069384C2776401178 @default.
- W4319069384 hasConceptScore W4319069384C2780451532 @default.
- W4319069384 hasConceptScore W4319069384C31972630 @default.
- W4319069384 hasConceptScore W4319069384C33923547 @default.
- W4319069384 hasConceptScore W4319069384C41008148 @default.
- W4319069384 hasConceptScore W4319069384C41895202 @default.
- W4319069384 hasConceptScore W4319069384C542102704 @default.
- W4319069384 hasConceptScore W4319069384C9652623 @default.
- W4319069384 hasLocation W43190693841 @default.
- W4319069384 hasOpenAccess W4319069384 @default.
- W4319069384 hasPrimaryLocation W43190693841 @default.
- W4319069384 hasRelatedWork W1497780831 @default.
- W4319069384 hasRelatedWork W1504288058 @default.
- W4319069384 hasRelatedWork W1999949837 @default.