Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080224> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4384080224 endingPage "1" @default.
- W4384080224 startingPage "1" @default.
- W4384080224 abstract "An emerging internet of video things (IoVT) application, crowd counting is a computer vision task where the number of heads in a crowded scene is estimated. In recent years, it has attracted increasing attention from academia and industry because of its great potential value in public safety and urban planning. However, it has become a challenge to cross the gap between the increasingly heavy and complex network architecture widely used for the pursuit of counting with high accuracy and the constrained computing and storage resources in the edge computing environment. To address this issue, an effective lightweight crowd counting method based on an encoder-decoder network, named LEDCrowdNet, is proposed to achieve an optimal trade-off between counting performance and running speed for edge applications of IoVT. In particular, an improved MobileViT module as an encoder is designed to extract global-local crowd features of various scales. The decoder is composed of the adaptive multiscale large kernel attention module (AMLKA) and the lightweight counting atrous spatial pyramid pooling process module (LC-ASPP), which can perform end-to-end training to obtain the final density map. The proposed LEDCrowdNet is suitable for deployment on two edge computing platforms (NVIDIA Jetson Xavier NX and Coral Edge TPU) to reduce the number of floating point operations (FLOPs) without a significant drop in accuracy. Extensive experiments on five mainstream benchmarks (ShanghaiTech Part_A/B, UCF_CC_50, UCF-QNRF, WorldExpo’10 and RSOC datasets) verify the correctness and efficiency of our method." @default.
- W4384080224 created "2023-07-13" @default.
- W4384080224 creator A5003322678 @default.
- W4384080224 creator A5023598995 @default.
- W4384080224 creator A5033132937 @default.
- W4384080224 creator A5042473218 @default.
- W4384080224 creator A5071248581 @default.
- W4384080224 creator A5090390718 @default.
- W4384080224 date "2023-01-01" @default.
- W4384080224 modified "2023-09-28" @default.
- W4384080224 title "An Effective Lightweight Crowd Counting Method Based on an Encoder-Decoder Network for the Internet of Video Things" @default.
- W4384080224 doi "https://doi.org/10.1109/jiot.2023.3294727" @default.
- W4384080224 hasPublicationYear "2023" @default.
- W4384080224 type Work @default.
- W4384080224 citedByCount "0" @default.
- W4384080224 crossrefType "journal-article" @default.
- W4384080224 hasAuthorship W4384080224A5003322678 @default.
- W4384080224 hasAuthorship W4384080224A5023598995 @default.
- W4384080224 hasAuthorship W4384080224A5033132937 @default.
- W4384080224 hasAuthorship W4384080224A5042473218 @default.
- W4384080224 hasAuthorship W4384080224A5071248581 @default.
- W4384080224 hasAuthorship W4384080224A5090390718 @default.
- W4384080224 hasConcept C111919701 @default.
- W4384080224 hasConcept C113775141 @default.
- W4384080224 hasConcept C118505674 @default.
- W4384080224 hasConcept C138236772 @default.
- W4384080224 hasConcept C154945302 @default.
- W4384080224 hasConcept C158379750 @default.
- W4384080224 hasConcept C162307627 @default.
- W4384080224 hasConcept C204679922 @default.
- W4384080224 hasConcept C2778456923 @default.
- W4384080224 hasConcept C31258907 @default.
- W4384080224 hasConcept C41008148 @default.
- W4384080224 hasConcept C79403827 @default.
- W4384080224 hasConcept C79974875 @default.
- W4384080224 hasConceptScore W4384080224C111919701 @default.
- W4384080224 hasConceptScore W4384080224C113775141 @default.
- W4384080224 hasConceptScore W4384080224C118505674 @default.
- W4384080224 hasConceptScore W4384080224C138236772 @default.
- W4384080224 hasConceptScore W4384080224C154945302 @default.
- W4384080224 hasConceptScore W4384080224C158379750 @default.
- W4384080224 hasConceptScore W4384080224C162307627 @default.
- W4384080224 hasConceptScore W4384080224C204679922 @default.
- W4384080224 hasConceptScore W4384080224C2778456923 @default.
- W4384080224 hasConceptScore W4384080224C31258907 @default.
- W4384080224 hasConceptScore W4384080224C41008148 @default.
- W4384080224 hasConceptScore W4384080224C79403827 @default.
- W4384080224 hasConceptScore W4384080224C79974875 @default.
- W4384080224 hasFunder F4320321001 @default.
- W4384080224 hasLocation W43840802241 @default.
- W4384080224 hasOpenAccess W4384080224 @default.
- W4384080224 hasPrimaryLocation W43840802241 @default.
- W4384080224 hasRelatedWork W2089501902 @default.
- W4384080224 hasRelatedWork W2810084952 @default.
- W4384080224 hasRelatedWork W3046945740 @default.
- W4384080224 hasRelatedWork W3047385856 @default.
- W4384080224 hasRelatedWork W3169087733 @default.
- W4384080224 hasRelatedWork W4285326051 @default.
- W4384080224 hasRelatedWork W4310154675 @default.
- W4384080224 hasRelatedWork W4312975111 @default.
- W4384080224 hasRelatedWork W4322625180 @default.
- W4384080224 hasRelatedWork W4376106090 @default.
- W4384080224 isParatext "false" @default.
- W4384080224 isRetracted "false" @default.
- W4384080224 workType "article" @default.