Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207061639> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3207061639 abstract "Camera-equipped UAVs, or drones, are increasingly employed in a wide range of applications. Thus, ensuring their safe flight in areas containing people is a top priority. In this paper, a deep neural network-based method is proposed for the task of visual human crowd detection from UAV footage, allowing a drone to rapidly extract semantic segmentation maps from captured video frames during flight. These maps can be exploited (e.g., by a path planner) to define no-fly zones over, or near human crowds and, hence, enhance UAV flight safety. To this end, a novel neural architecture for binary (crowd/non- crowd) semantic segmentation from single RGB images is proposed, based on Convolutional Neural Networks (CNNs). It consists of a semantic segmentation and an image-to-image translation (I2I) neural branch. The overall network is trained using a novel multi-task loss function that addresses both tasks by processing the output of the corresponding branch. During inference, information flows across branches through additional skip synapses to further assist the crowd detection task. In order to evaluate the proposed method, we introduce a real and a synthetic human crowd RGB image dataset. The proposed method outperforms previous aerial crowd detection methods by a large margin and without any post-processing. Moreover, it demonstrates increased generalization ability, while running at real-time and near-real-time speeds on a ground computer and on embedded AI hardware, respectively." @default.
- W3207061639 created "2021-10-25" @default.
- W3207061639 creator A5024066107 @default.
- W3207061639 creator A5061130224 @default.
- W3207061639 creator A5070716976 @default.
- W3207061639 date "2021-05-30" @default.
- W3207061639 modified "2023-10-17" @default.
- W3207061639 title "Autonomous UAV Safety by Visual Human Crowd Detection Using Multi-Task Deep Neural Networks" @default.
- W3207061639 cites W1492541562 @default.
- W3207061639 cites W1903029394 @default.
- W3207061639 cites W1910776219 @default.
- W3207061639 cites W2019400639 @default.
- W3207061639 cites W2102947763 @default.
- W3207061639 cites W2112796928 @default.
- W3207061639 cites W2147002980 @default.
- W3207061639 cites W2165139660 @default.
- W3207061639 cites W2194775991 @default.
- W3207061639 cites W2463631526 @default.
- W3207061639 cites W2517615595 @default.
- W3207061639 cites W2615547864 @default.
- W3207061639 cites W2765781654 @default.
- W3207061639 cites W2891915391 @default.
- W3207061639 cites W2892288001 @default.
- W3207061639 cites W2904981122 @default.
- W3207061639 cites W2914859139 @default.
- W3207061639 cites W2918636049 @default.
- W3207061639 cites W2938905778 @default.
- W3207061639 cites W2963073614 @default.
- W3207061639 cites W2963231953 @default.
- W3207061639 cites W2963693541 @default.
- W3207061639 cites W2964209782 @default.
- W3207061639 cites W2965759948 @default.
- W3207061639 cites W2967069910 @default.
- W3207061639 cites W2972407766 @default.
- W3207061639 cites W2982130202 @default.
- W3207061639 cites W2999161229 @default.
- W3207061639 cites W3089306886 @default.
- W3207061639 doi "https://doi.org/10.1109/icra48506.2021.9560830" @default.
- W3207061639 hasPublicationYear "2021" @default.
- W3207061639 type Work @default.
- W3207061639 sameAs 3207061639 @default.
- W3207061639 citedByCount "11" @default.
- W3207061639 countsByYear W32070616392022 @default.
- W3207061639 countsByYear W32070616392023 @default.
- W3207061639 crossrefType "proceedings-article" @default.
- W3207061639 hasAuthorship W3207061639A5024066107 @default.
- W3207061639 hasAuthorship W3207061639A5061130224 @default.
- W3207061639 hasAuthorship W3207061639A5070716976 @default.
- W3207061639 hasBestOaLocation W32070616392 @default.
- W3207061639 hasConcept C108583219 @default.
- W3207061639 hasConcept C124504099 @default.
- W3207061639 hasConcept C127413603 @default.
- W3207061639 hasConcept C154945302 @default.
- W3207061639 hasConcept C201995342 @default.
- W3207061639 hasConcept C2780451532 @default.
- W3207061639 hasConcept C31972630 @default.
- W3207061639 hasConcept C41008148 @default.
- W3207061639 hasConcept C50644808 @default.
- W3207061639 hasConcept C54355233 @default.
- W3207061639 hasConcept C59519942 @default.
- W3207061639 hasConcept C81363708 @default.
- W3207061639 hasConcept C82990744 @default.
- W3207061639 hasConcept C86803240 @default.
- W3207061639 hasConcept C89600930 @default.
- W3207061639 hasConceptScore W3207061639C108583219 @default.
- W3207061639 hasConceptScore W3207061639C124504099 @default.
- W3207061639 hasConceptScore W3207061639C127413603 @default.
- W3207061639 hasConceptScore W3207061639C154945302 @default.
- W3207061639 hasConceptScore W3207061639C201995342 @default.
- W3207061639 hasConceptScore W3207061639C2780451532 @default.
- W3207061639 hasConceptScore W3207061639C31972630 @default.
- W3207061639 hasConceptScore W3207061639C41008148 @default.
- W3207061639 hasConceptScore W3207061639C50644808 @default.
- W3207061639 hasConceptScore W3207061639C54355233 @default.
- W3207061639 hasConceptScore W3207061639C59519942 @default.
- W3207061639 hasConceptScore W3207061639C81363708 @default.
- W3207061639 hasConceptScore W3207061639C82990744 @default.
- W3207061639 hasConceptScore W3207061639C86803240 @default.
- W3207061639 hasConceptScore W3207061639C89600930 @default.
- W3207061639 hasLocation W32070616391 @default.
- W3207061639 hasLocation W32070616392 @default.
- W3207061639 hasOpenAccess W3207061639 @default.
- W3207061639 hasPrimaryLocation W32070616391 @default.
- W3207061639 hasRelatedWork W3029198973 @default.
- W3207061639 hasRelatedWork W3133861977 @default.
- W3207061639 hasRelatedWork W3167935049 @default.
- W3207061639 hasRelatedWork W3193565141 @default.
- W3207061639 hasRelatedWork W4226493464 @default.
- W3207061639 hasRelatedWork W4229448053 @default.
- W3207061639 hasRelatedWork W4247925126 @default.
- W3207061639 hasRelatedWork W4312417841 @default.
- W3207061639 hasRelatedWork W4312858960 @default.
- W3207061639 hasRelatedWork W4386036939 @default.
- W3207061639 isParatext "false" @default.
- W3207061639 isRetracted "false" @default.
- W3207061639 magId "3207061639" @default.
- W3207061639 workType "article" @default.