Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163164080> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3163164080 abstract "Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise Object Detector (TOD) which maximises the real-time object detection accuracy on an edge device by selecting an appropriate Deep Neural Network (DNN) on the fly with negligible computational overhead. TOD makes two key contributions over the state of the art: (1) TOD leverages characteristics of the video stream such as object size and speed of movement to identify networks with high prediction accuracy for the current frames; (2) it selects the best-performing network based on projected accuracy and computational demand using an effective and low-overhead decision mechanism. Experimental evaluation on a Jetson Nano demonstrates that TOD improves the average object detection precision by 34.7 % over the YOLOv4-tiny-288 model on average over the MOT17Det dataset. In the MOT17-05 test dataset, TOD utilises only 45.1 % of GPU resource and 62.7 % of the GPU board power without losing accuracy, compared to YOLOv4-416 model. We expect that TOD will maximise the application of edge devices to real-time object detection, since TOD maximises real-time object detection accuracy given edge devices according to dynamic input features without increasing inference latency in practice." @default.
- W3163164080 created "2021-05-24" @default.
- W3163164080 creator A5019030522 @default.
- W3163164080 creator A5074563743 @default.
- W3163164080 creator A5078925783 @default.
- W3163164080 creator A5086758775 @default.
- W3163164080 date "2021-05-18" @default.
- W3163164080 modified "2023-09-27" @default.
- W3163164080 title "TOD: Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge." @default.
- W3163164080 cites W1521019969 @default.
- W3163164080 cites W1680392829 @default.
- W3163164080 cites W1875422203 @default.
- W3163164080 cites W1950935069 @default.
- W3163164080 cites W2291627510 @default.
- W3163164080 cites W2515329741 @default.
- W3163164080 cites W2557728737 @default.
- W3163164080 cites W2801742018 @default.
- W3163164080 cites W2806318734 @default.
- W3163164080 cites W2887117815 @default.
- W3163164080 cites W2951890823 @default.
- W3163164080 cites W3004633656 @default.
- W3163164080 cites W3033979988 @default.
- W3163164080 cites W2810129309 @default.
- W3163164080 hasPublicationYear "2021" @default.
- W3163164080 type Work @default.
- W3163164080 sameAs 3163164080 @default.
- W3163164080 citedByCount "0" @default.
- W3163164080 crossrefType "posted-content" @default.
- W3163164080 hasAuthorship W3163164080A5019030522 @default.
- W3163164080 hasAuthorship W3163164080A5074563743 @default.
- W3163164080 hasAuthorship W3163164080A5078925783 @default.
- W3163164080 hasAuthorship W3163164080A5086758775 @default.
- W3163164080 hasConcept C111919701 @default.
- W3163164080 hasConcept C126042441 @default.
- W3163164080 hasConcept C138236772 @default.
- W3163164080 hasConcept C153180895 @default.
- W3163164080 hasConcept C154945302 @default.
- W3163164080 hasConcept C162307627 @default.
- W3163164080 hasConcept C2776151529 @default.
- W3163164080 hasConcept C2776214188 @default.
- W3163164080 hasConcept C2779960059 @default.
- W3163164080 hasConcept C31972630 @default.
- W3163164080 hasConcept C3261483 @default.
- W3163164080 hasConcept C41008148 @default.
- W3163164080 hasConcept C76155785 @default.
- W3163164080 hasConcept C79403827 @default.
- W3163164080 hasConcept C79974875 @default.
- W3163164080 hasConcept C82876162 @default.
- W3163164080 hasConceptScore W3163164080C111919701 @default.
- W3163164080 hasConceptScore W3163164080C126042441 @default.
- W3163164080 hasConceptScore W3163164080C138236772 @default.
- W3163164080 hasConceptScore W3163164080C153180895 @default.
- W3163164080 hasConceptScore W3163164080C154945302 @default.
- W3163164080 hasConceptScore W3163164080C162307627 @default.
- W3163164080 hasConceptScore W3163164080C2776151529 @default.
- W3163164080 hasConceptScore W3163164080C2776214188 @default.
- W3163164080 hasConceptScore W3163164080C2779960059 @default.
- W3163164080 hasConceptScore W3163164080C31972630 @default.
- W3163164080 hasConceptScore W3163164080C3261483 @default.
- W3163164080 hasConceptScore W3163164080C41008148 @default.
- W3163164080 hasConceptScore W3163164080C76155785 @default.
- W3163164080 hasConceptScore W3163164080C79403827 @default.
- W3163164080 hasConceptScore W3163164080C79974875 @default.
- W3163164080 hasConceptScore W3163164080C82876162 @default.
- W3163164080 hasLocation W31631640801 @default.
- W3163164080 hasOpenAccess W3163164080 @default.
- W3163164080 hasPrimaryLocation W31631640801 @default.
- W3163164080 hasRelatedWork W2413855997 @default.
- W3163164080 hasRelatedWork W2605173812 @default.
- W3163164080 hasRelatedWork W2768909086 @default.
- W3163164080 hasRelatedWork W2781588173 @default.
- W3163164080 hasRelatedWork W2885915921 @default.
- W3163164080 hasRelatedWork W2911419778 @default.
- W3163164080 hasRelatedWork W2914861440 @default.
- W3163164080 hasRelatedWork W2919935710 @default.
- W3163164080 hasRelatedWork W2925502535 @default.
- W3163164080 hasRelatedWork W2946145905 @default.
- W3163164080 hasRelatedWork W2951503448 @default.
- W3163164080 hasRelatedWork W2962897380 @default.
- W3163164080 hasRelatedWork W2988828868 @default.
- W3163164080 hasRelatedWork W3029267566 @default.
- W3163164080 hasRelatedWork W3080311119 @default.
- W3163164080 hasRelatedWork W3135934332 @default.
- W3163164080 hasRelatedWork W3153288312 @default.
- W3163164080 hasRelatedWork W3157630927 @default.
- W3163164080 hasRelatedWork W3184121761 @default.
- W3163164080 hasRelatedWork W3203806933 @default.
- W3163164080 isParatext "false" @default.
- W3163164080 isRetracted "false" @default.
- W3163164080 magId "3163164080" @default.
- W3163164080 workType "article" @default.