Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316039603> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4316039603 endingPage "104628" @default.
- W4316039603 startingPage "104628" @default.
- W4316039603 abstract "For video surveillance, pedestrian detection assists in providing baseline data for crowd monitoring, people counting, and event detection; for smart transport system, pedestrian detection acts as a vital part in the semantic understanding of the environment. Pedestrian detection is frequently confronted with substantial intra-class variability because human tends to have great variation in human appearance and pose. Currently, the emergence of deep learning (DL) model has received considerable attention in computer vision techniques like object detection and object classification, and this application is based on supervised learning which required labels. Convolution neural networks (CNN) have assisted substantial improvement in pedestrian recognition due to the stronger representative capability of the CNN feature. But it is usually hard to decrease false positives on hard negative samples namely poles, tree leaves, traffic lights, and so on. Therefore, this study develops an intelligent multimodal pedestrian detection and classification using hybrid metaheuristic optimization with deep learning (IPDC-HMODL) algorithm. The major aim of the presented IPDC-HMODL model is the recognition and classification of multiple pedestrians exist in the input frames. It follows a three stage process namely multimodal object detection, pedestrian classification, and parameter tuning. At the initial stage, the IPDC-HMODL model uses multimodal object detector using YOLO-v5 and RetinaNet model. In addition, the IPDC-HMODL model applies kernel extreme learning machine (KELM) algorithm for pedestrian classification. Finally, hybrid salp swarm optimization (HSSO) model is used for optimal parameter adjustment. To depict the improvised outcomes of the IPDC-HMODL technique, a wide spread simulation analysis was conducted. The comparison study highlighted the enhanced outcomes of the IPDC-HMODL model over other approaches on multimodal pedestrian detection." @default.
- W4316039603 created "2023-01-14" @default.
- W4316039603 creator A5037357519 @default.
- W4316039603 creator A5077717775 @default.
- W4316039603 date "2023-03-01" @default.
- W4316039603 modified "2023-09-23" @default.
- W4316039603 title "Intelligent multimodal pedestrian detection using hybrid metaheuristic optimization with deep learning model" @default.
- W4316039603 cites W2929607865 @default.
- W4316039603 cites W3007827672 @default.
- W4316039603 cites W3009701286 @default.
- W4316039603 cites W3011312272 @default.
- W4316039603 cites W3022458269 @default.
- W4316039603 cites W3082127293 @default.
- W4316039603 cites W3114958142 @default.
- W4316039603 cites W3164576087 @default.
- W4316039603 cites W3166298833 @default.
- W4316039603 cites W3174491732 @default.
- W4316039603 cites W3182910206 @default.
- W4316039603 cites W3193890888 @default.
- W4316039603 cites W3197622673 @default.
- W4316039603 cites W4200181556 @default.
- W4316039603 cites W4200420567 @default.
- W4316039603 cites W4223424080 @default.
- W4316039603 cites W4225847518 @default.
- W4316039603 cites W4280552281 @default.
- W4316039603 cites W4285215816 @default.
- W4316039603 cites W4285494157 @default.
- W4316039603 doi "https://doi.org/10.1016/j.imavis.2023.104628" @default.
- W4316039603 hasPublicationYear "2023" @default.
- W4316039603 type Work @default.
- W4316039603 citedByCount "2" @default.
- W4316039603 countsByYear W43160396032023 @default.
- W4316039603 crossrefType "journal-article" @default.
- W4316039603 hasAuthorship W4316039603A5037357519 @default.
- W4316039603 hasAuthorship W4316039603A5077717775 @default.
- W4316039603 hasConcept C108583219 @default.
- W4316039603 hasConcept C119857082 @default.
- W4316039603 hasConcept C124101348 @default.
- W4316039603 hasConcept C127413603 @default.
- W4316039603 hasConcept C153180895 @default.
- W4316039603 hasConcept C154945302 @default.
- W4316039603 hasConcept C22212356 @default.
- W4316039603 hasConcept C2776151529 @default.
- W4316039603 hasConcept C2777113093 @default.
- W4316039603 hasConcept C2780156472 @default.
- W4316039603 hasConcept C31972630 @default.
- W4316039603 hasConcept C41008148 @default.
- W4316039603 hasConcept C81363708 @default.
- W4316039603 hasConceptScore W4316039603C108583219 @default.
- W4316039603 hasConceptScore W4316039603C119857082 @default.
- W4316039603 hasConceptScore W4316039603C124101348 @default.
- W4316039603 hasConceptScore W4316039603C127413603 @default.
- W4316039603 hasConceptScore W4316039603C153180895 @default.
- W4316039603 hasConceptScore W4316039603C154945302 @default.
- W4316039603 hasConceptScore W4316039603C22212356 @default.
- W4316039603 hasConceptScore W4316039603C2776151529 @default.
- W4316039603 hasConceptScore W4316039603C2777113093 @default.
- W4316039603 hasConceptScore W4316039603C2780156472 @default.
- W4316039603 hasConceptScore W4316039603C31972630 @default.
- W4316039603 hasConceptScore W4316039603C41008148 @default.
- W4316039603 hasConceptScore W4316039603C81363708 @default.
- W4316039603 hasLocation W43160396031 @default.
- W4316039603 hasOpenAccess W4316039603 @default.
- W4316039603 hasPrimaryLocation W43160396031 @default.
- W4316039603 hasRelatedWork W2014339256 @default.
- W4316039603 hasRelatedWork W2067373798 @default.
- W4316039603 hasRelatedWork W2128694549 @default.
- W4316039603 hasRelatedWork W2497633036 @default.
- W4316039603 hasRelatedWork W2911294201 @default.
- W4316039603 hasRelatedWork W2913302899 @default.
- W4316039603 hasRelatedWork W3015951701 @default.
- W4316039603 hasRelatedWork W4311401716 @default.
- W4316039603 hasRelatedWork W4312417841 @default.
- W4316039603 hasRelatedWork W3142777113 @default.
- W4316039603 hasVolume "131" @default.
- W4316039603 isParatext "false" @default.
- W4316039603 isRetracted "false" @default.
- W4316039603 workType "article" @default.