FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206555067> ?p ?o ?g. }

• W3206555067 endingPage "104484" @default.
• W3206555067 startingPage "104484" @default.
• W3206555067 abstract "This paper describes a novel DNN-based system, named PD3net, that detects multiple people from a single depth image, in real time. The proposed neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a Gaussian-shaped local distribution, centered at each person’s head. This likelihood map encodes both the number of detected people as well as their position in the image, from which the 3D position can be computed. The proposed DNN includes spatially separated convolutions to increase performance, and runs in real-time with low budget GPUs. We use synthetic data for initially training the network, followed by fine tuning with a small amount of real data. This allows adapting the network to different scenarios without needing large and manually labeled image datasets. Due to that, the people detection system presented in this paper has numerous potential applications in different fields, such as capacity control, automatic video-surveillance, people or groups behavior analysis, healthcare or monitoring and assistance of elderly people in ambient assisted living environments. In addition, the use of depth information does not allow recognizing the identity of people in the scene, thus enabling their detection while preserving their privacy. The proposed DNN has been experimentally evaluated and compared with other state-of-the-art approaches, including both classical and DNN-based solutions, under a wide range of experimental conditions. The achieved results allows concluding that the proposed architecture and the training strategy are effective, and the network generalize to work with scenes different from those used during training. We also demonstrate that our proposal outperforms existing methods and can accurately detect people in scenes with significant occlusions." @default.
• W3206555067 created "2021-10-25" @default.
• W3206555067 creator A5014421885 @default.
• W3206555067 creator A5031022520 @default.
• W3206555067 creator A5066655091 @default.
• W3206555067 creator A5067349876 @default.
• W3206555067 creator A5069928827 @default.
• W3206555067 creator A5073480676 @default.
• W3206555067 creator A5078597967 @default.
• W3206555067 date "2021-11-01" @default.
• W3206555067 modified "2023-09-28" @default.
• W3206555067 title "Towards dense people detection with deep learning and depth images" @default.
• W3206555067 cites W2000825879 @default.
• W3206555067 cites W2023456611 @default.
• W3206555067 cites W2026332379 @default.
• W3206555067 cites W2067528992 @default.
• W3206555067 cites W2070217198 @default.
• W3206555067 cites W2080914079 @default.
• W3206555067 cites W2088049833 @default.
• W3206555067 cites W2139461634 @default.
• W3206555067 cites W2198400865 @default.
• W3206555067 cites W2253429366 @default.
• W3206555067 cites W2413954201 @default.
• W3206555067 cites W2535388113 @default.
• W3206555067 cites W2552746466 @default.
• W3206555067 cites W2610165754 @default.
• W3206555067 cites W2765339750 @default.
• W3206555067 cites W2806833697 @default.
• W3206555067 cites W2808204088 @default.
• W3206555067 cites W2893813411 @default.
• W3206555067 cites W2980222335 @default.
• W3206555067 cites W3042870837 @default.
• W3206555067 cites W3045470904 @default.
• W3206555067 cites W3045643850 @default.
• W3206555067 cites W3104557502 @default.
• W3206555067 cites W607748843 @default.
• W3206555067 cites W657467088 @default.
• W3206555067 doi "https://doi.org/10.1016/j.engappai.2021.104484" @default.
• W3206555067 hasPublicationYear "2021" @default.
• W3206555067 type Work @default.
• W3206555067 sameAs 3206555067 @default.
• W3206555067 citedByCount "3" @default.
• W3206555067 countsByYear W32065550672022 @default.
• W3206555067 countsByYear W32065550672023 @default.
• W3206555067 crossrefType "journal-article" @default.
• W3206555067 hasAuthorship W3206555067A5014421885 @default.
• W3206555067 hasAuthorship W3206555067A5031022520 @default.
• W3206555067 hasAuthorship W3206555067A5066655091 @default.
• W3206555067 hasAuthorship W3206555067A5067349876 @default.
• W3206555067 hasAuthorship W3206555067A5069928827 @default.
• W3206555067 hasAuthorship W3206555067A5073480676 @default.
• W3206555067 hasAuthorship W3206555067A5078597967 @default.
• W3206555067 hasBestOaLocation W32065550672 @default.
• W3206555067 hasConcept C10138342 @default.
• W3206555067 hasConcept C108583219 @default.
• W3206555067 hasConcept C115961682 @default.
• W3206555067 hasConcept C119857082 @default.
• W3206555067 hasConcept C121332964 @default.
• W3206555067 hasConcept C153180895 @default.
• W3206555067 hasConcept C154945302 @default.
• W3206555067 hasConcept C159985019 @default.
• W3206555067 hasConcept C162324750 @default.
• W3206555067 hasConcept C163716315 @default.
• W3206555067 hasConcept C192562407 @default.
• W3206555067 hasConcept C193415008 @default.
• W3206555067 hasConcept C198082294 @default.
• W3206555067 hasConcept C204323151 @default.
• W3206555067 hasConcept C24890656 @default.
• W3206555067 hasConcept C2778355321 @default.
• W3206555067 hasConcept C31972630 @default.
• W3206555067 hasConcept C38652104 @default.
• W3206555067 hasConcept C41008148 @default.
• W3206555067 hasConcept C50644808 @default.
• W3206555067 hasConcept C62520636 @default.
• W3206555067 hasConceptScore W3206555067C10138342 @default.
• W3206555067 hasConceptScore W3206555067C108583219 @default.
• W3206555067 hasConceptScore W3206555067C115961682 @default.
• W3206555067 hasConceptScore W3206555067C119857082 @default.
• W3206555067 hasConceptScore W3206555067C121332964 @default.
• W3206555067 hasConceptScore W3206555067C153180895 @default.
• W3206555067 hasConceptScore W3206555067C154945302 @default.
• W3206555067 hasConceptScore W3206555067C159985019 @default.
• W3206555067 hasConceptScore W3206555067C162324750 @default.
• W3206555067 hasConceptScore W3206555067C163716315 @default.
• W3206555067 hasConceptScore W3206555067C192562407 @default.
• W3206555067 hasConceptScore W3206555067C193415008 @default.
• W3206555067 hasConceptScore W3206555067C198082294 @default.
• W3206555067 hasConceptScore W3206555067C204323151 @default.
• W3206555067 hasConceptScore W3206555067C24890656 @default.
• W3206555067 hasConceptScore W3206555067C2778355321 @default.
• W3206555067 hasConceptScore W3206555067C31972630 @default.
• W3206555067 hasConceptScore W3206555067C38652104 @default.
• W3206555067 hasConceptScore W3206555067C41008148 @default.
• W3206555067 hasConceptScore W3206555067C50644808 @default.
• W3206555067 hasConceptScore W3206555067C62520636 @default.
• W3206555067 hasLocation W32065550671 @default.
• W3206555067 hasLocation W32065550672 @default.
• W3206555067 hasOpenAccess W3206555067 @default.

• next