FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378450140> ?p ?o ?g. }

• W4378450140 endingPage "103362" @default.
• W4378450140 startingPage "103362" @default.
• W4378450140 abstract "Slender urban road facilities (SURFs) with extreme aspect ratios are essential roles of the road network and exist everywhere in urban scenarios, such as street lamps, traffic lights, and monitors. Their information provides important knowledge for road safety, traffic control, urban planning, city management, etc. With low cost and high-efficiency benefits, oblique aerial images are easily captured to cover large-scale areas, which can be appropriately used to survey SURFs in urban areas automatically. Meanwhile, instance segmentation methods are frequently applied, predicting bounding boxes and semantic masks of objects simultaneously, yet a minority is delicately designed for SURFs. This research aims to propose an instance segmentation method to automatically extract SURFs from oblique aerial imagery, enhancing both the predicted bounding box and the segmented binary mask. First, we design a dense anchor ratio with an IoU-balanced sampling strategy (DASS) for proposal generation by statistical analysis to improve the predicted bounding box. The proposed sampling strategy can better cover the shape of slender proposals and alleviate the imbalance problem between the target objects and background. Regarding the typical instance segmentation architectures, the binary mask is segmented coarsely due to the downsampling operations. Second, we propose balanced fine-grained features (BFGF) merged into the instance segmentation process via a three-stage architecture, effectively improving the detector’s performance. Specifically, before feature incorporation, the multi-level feature pyramid is refined by rescaling and integrating to obtain balanced features. Moreover, to evaluate the proposed approaches, we contribute an Urban Road Facilities Dataset for our task, URFD, which contains 1075 images and 1378 instances labeled manually and enriches the open resource dataset. By comparative experiments, the proposed method performs superiority in SURF instance segmentation, obtaining an mAP of 0.888 of the predicted bounding box and an mAP of 0.876 of the segmented binary mask." @default.
• W4378450140 created "2023-05-27" @default.
• W4378450140 creator A5015366653 @default.
• W4378450140 creator A5020746892 @default.
• W4378450140 creator A5025557730 @default.
• W4378450140 creator A5033145807 @default.
• W4378450140 creator A5053447705 @default.
• W4378450140 creator A5068686920 @default.
• W4378450140 date "2023-07-01" @default.
• W4378450140 modified "2023-10-17" @default.
• W4378450140 title "Improved instance segmentation for slender urban road facility extraction using oblique aerial images" @default.
• W4378450140 cites W2064985253 @default.
• W4378450140 cites W2465939999 @default.
• W4378450140 cites W2565639579 @default.
• W4378450140 cites W2729822439 @default.
• W4378450140 cites W2920326761 @default.
• W4378450140 cites W2962749812 @default.
• W4378450140 cites W2963091558 @default.
• W4378450140 cites W2963150697 @default.
• W4378450140 cites W2989676862 @default.
• W4378450140 cites W3005378446 @default.
• W4378450140 cites W3011722050 @default.
• W4378450140 cites W3028752951 @default.
• W4378450140 cites W3035358681 @default.
• W4378450140 cites W3087890773 @default.
• W4378450140 cites W3104282073 @default.
• W4378450140 cites W3105577662 @default.
• W4378450140 cites W3110585990 @default.
• W4378450140 cites W3132455321 @default.
• W4378450140 cites W3139593471 @default.
• W4378450140 cites W3177388720 @default.
• W4378450140 cites W3199844134 @default.
• W4378450140 cites W3204545281 @default.
• W4378450140 cites W4212773528 @default.
• W4378450140 cites W4283774201 @default.
• W4378450140 doi "https://doi.org/10.1016/j.jag.2023.103362" @default.
• W4378450140 hasPublicationYear "2023" @default.
• W4378450140 type Work @default.
• W4378450140 citedByCount "0" @default.
• W4378450140 crossrefType "journal-article" @default.
• W4378450140 hasAuthorship W4378450140A5015366653 @default.
• W4378450140 hasAuthorship W4378450140A5020746892 @default.
• W4378450140 hasAuthorship W4378450140A5025557730 @default.
• W4378450140 hasAuthorship W4378450140A5033145807 @default.
• W4378450140 hasAuthorship W4378450140A5053447705 @default.
• W4378450140 hasAuthorship W4378450140A5068686920 @default.
• W4378450140 hasBestOaLocation W43784501401 @default.
• W4378450140 hasConcept C111919701 @default.
• W4378450140 hasConcept C115961682 @default.
• W4378450140 hasConcept C138885662 @default.
• W4378450140 hasConcept C142575187 @default.
• W4378450140 hasConcept C147037132 @default.
• W4378450140 hasConcept C153180895 @default.
• W4378450140 hasConcept C154945302 @default.
• W4378450140 hasConcept C160697094 @default.
• W4378450140 hasConcept C205649164 @default.
• W4378450140 hasConcept C2524010 @default.
• W4378450140 hasConcept C2776401178 @default.
• W4378450140 hasConcept C2776429412 @default.
• W4378450140 hasConcept C31972630 @default.
• W4378450140 hasConcept C33923547 @default.
• W4378450140 hasConcept C41008148 @default.
• W4378450140 hasConcept C41895202 @default.
• W4378450140 hasConcept C63584917 @default.
• W4378450140 hasConcept C89600930 @default.
• W4378450140 hasConcept C98045186 @default.
• W4378450140 hasConceptScore W4378450140C111919701 @default.
• W4378450140 hasConceptScore W4378450140C115961682 @default.
• W4378450140 hasConceptScore W4378450140C138885662 @default.
• W4378450140 hasConceptScore W4378450140C142575187 @default.
• W4378450140 hasConceptScore W4378450140C147037132 @default.
• W4378450140 hasConceptScore W4378450140C153180895 @default.
• W4378450140 hasConceptScore W4378450140C154945302 @default.
• W4378450140 hasConceptScore W4378450140C160697094 @default.
• W4378450140 hasConceptScore W4378450140C205649164 @default.
• W4378450140 hasConceptScore W4378450140C2524010 @default.
• W4378450140 hasConceptScore W4378450140C2776401178 @default.
• W4378450140 hasConceptScore W4378450140C2776429412 @default.
• W4378450140 hasConceptScore W4378450140C31972630 @default.
• W4378450140 hasConceptScore W4378450140C33923547 @default.
• W4378450140 hasConceptScore W4378450140C41008148 @default.
• W4378450140 hasConceptScore W4378450140C41895202 @default.
• W4378450140 hasConceptScore W4378450140C63584917 @default.
• W4378450140 hasConceptScore W4378450140C89600930 @default.
• W4378450140 hasConceptScore W4378450140C98045186 @default.
• W4378450140 hasLocation W43784501401 @default.
• W4378450140 hasOpenAccess W4378450140 @default.
• W4378450140 hasPrimaryLocation W43784501401 @default.
• W4378450140 hasRelatedWork W1564558219 @default.
• W4378450140 hasRelatedWork W2489489317 @default.
• W4378450140 hasRelatedWork W2517104666 @default.
• W4378450140 hasRelatedWork W2756241593 @default.
• W4378450140 hasRelatedWork W3097420222 @default.
• W4378450140 hasRelatedWork W3118944910 @default.
• W4378450140 hasRelatedWork W3197089899 @default.
• W4378450140 hasRelatedWork W4280560571 @default.
• W4378450140 hasRelatedWork W4312691959 @default.
• W4378450140 hasRelatedWork W4386099271 @default.

• next