Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042171668> ?p ?o ?g. }
- W3042171668 abstract "Understanding the complex urban infrastructure with centimeter-level accuracy is essential for many applications from autonomous driving to mapping, infrastructure monitoring, and urban management. Aerial images provide valuable information over a large area instantaneously; nevertheless, no current dataset captures the complexity of aerial scenes at the level of granularity required by real-world applications. To address this, we introduce SkyScapes, an aerial image dataset with highly-accurate, fine-grained annotations for pixel-level semantic labeling. SkyScapes provides annotations for 31 semantic categories ranging from large structures, such as buildings, roads and vegetation, to fine details, such as 12 (sub-)categories of lane markings. We have defined two main tasks on this dataset: dense semantic segmentation and multi-class lane-marking prediction. We carry out extensive experiments to evaluate state-of-the-art segmentation methods on SkyScapes. Existing methods struggle to deal with the wide range of classes, object sizes, scales, and fine details present. We therefore propose a novel multi-task model, which incorporates semantic edge detection and is better tuned for feature extraction from a wide range of scales. This model achieves notable improvements over the baselines in region outlines and level of detail on both tasks." @default.
- W3042171668 created "2020-07-16" @default.
- W3042171668 creator A5006333653 @default.
- W3042171668 creator A5060914389 @default.
- W3042171668 creator A5074365322 @default.
- W3042171668 creator A5079778751 @default.
- W3042171668 creator A5085317653 @default.
- W3042171668 date "2020-07-12" @default.
- W3042171668 modified "2023-09-27" @default.
- W3042171668 title "SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes" @default.
- W3042171668 cites W1836220311 @default.
- W3042171668 cites W1861492603 @default.
- W3042171668 cites W1901129140 @default.
- W3042171668 cites W1903029394 @default.
- W3042171668 cites W2031489346 @default.
- W3042171668 cites W2032924574 @default.
- W3042171668 cites W2108598243 @default.
- W3042171668 cites W2205800717 @default.
- W3042171668 cites W2292862975 @default.
- W3042171668 cites W2316483928 @default.
- W3042171668 cites W2340897893 @default.
- W3042171668 cites W2412782625 @default.
- W3042171668 cites W2464204616 @default.
- W3042171668 cites W2557406251 @default.
- W3042171668 cites W2559545830 @default.
- W3042171668 cites W2559597482 @default.
- W3042171668 cites W2560023338 @default.
- W3042171668 cites W2563705555 @default.
- W3042171668 cites W2598666589 @default.
- W3042171668 cites W2609402060 @default.
- W3042171668 cites W2612445135 @default.
- W3042171668 cites W2623331213 @default.
- W3042171668 cites W2630837129 @default.
- W3042171668 cites W2736981815 @default.
- W3042171668 cites W2739253758 @default.
- W3042171668 cites W2780861787 @default.
- W3042171668 cites W2799213142 @default.
- W3042171668 cites W2804199516 @default.
- W3042171668 cites W2855340099 @default.
- W3042171668 cites W2886934227 @default.
- W3042171668 cites W2890782586 @default.
- W3042171668 cites W2894878591 @default.
- W3042171668 cites W2895947098 @default.
- W3042171668 cites W2898887767 @default.
- W3042171668 cites W2905509562 @default.
- W3042171668 cites W2962749812 @default.
- W3042171668 cites W2962914239 @default.
- W3042171668 cites W2963136578 @default.
- W3042171668 cites W2963542991 @default.
- W3042171668 cites W2963727650 @default.
- W3042171668 cites W2963881378 @default.
- W3042171668 cites W2963926549 @default.
- W3042171668 cites W2964288706 @default.
- W3042171668 cites W2964309882 @default.
- W3042171668 cites W3024503704 @default.
- W3042171668 cites W3101896960 @default.
- W3042171668 hasPublicationYear "2020" @default.
- W3042171668 type Work @default.
- W3042171668 sameAs 3042171668 @default.
- W3042171668 citedByCount "1" @default.
- W3042171668 countsByYear W30421716682021 @default.
- W3042171668 crossrefType "posted-content" @default.
- W3042171668 hasAuthorship W3042171668A5006333653 @default.
- W3042171668 hasAuthorship W3042171668A5060914389 @default.
- W3042171668 hasAuthorship W3042171668A5074365322 @default.
- W3042171668 hasAuthorship W3042171668A5079778751 @default.
- W3042171668 hasAuthorship W3042171668A5085317653 @default.
- W3042171668 hasConcept C111919701 @default.
- W3042171668 hasConcept C115051666 @default.
- W3042171668 hasConcept C115961682 @default.
- W3042171668 hasConcept C124101348 @default.
- W3042171668 hasConcept C138885662 @default.
- W3042171668 hasConcept C154945302 @default.
- W3042171668 hasConcept C159985019 @default.
- W3042171668 hasConcept C162324750 @default.
- W3042171668 hasConcept C177774035 @default.
- W3042171668 hasConcept C187736073 @default.
- W3042171668 hasConcept C192562407 @default.
- W3042171668 hasConcept C204323151 @default.
- W3042171668 hasConcept C2776401178 @default.
- W3042171668 hasConcept C2776429412 @default.
- W3042171668 hasConcept C2777212361 @default.
- W3042171668 hasConcept C2780451532 @default.
- W3042171668 hasConcept C2781238097 @default.
- W3042171668 hasConcept C31972630 @default.
- W3042171668 hasConcept C41008148 @default.
- W3042171668 hasConcept C41895202 @default.
- W3042171668 hasConcept C76155785 @default.
- W3042171668 hasConcept C89600930 @default.
- W3042171668 hasConceptScore W3042171668C111919701 @default.
- W3042171668 hasConceptScore W3042171668C115051666 @default.
- W3042171668 hasConceptScore W3042171668C115961682 @default.
- W3042171668 hasConceptScore W3042171668C124101348 @default.
- W3042171668 hasConceptScore W3042171668C138885662 @default.
- W3042171668 hasConceptScore W3042171668C154945302 @default.
- W3042171668 hasConceptScore W3042171668C159985019 @default.
- W3042171668 hasConceptScore W3042171668C162324750 @default.
- W3042171668 hasConceptScore W3042171668C177774035 @default.
- W3042171668 hasConceptScore W3042171668C187736073 @default.
- W3042171668 hasConceptScore W3042171668C192562407 @default.