Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226061185> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4226061185 abstract "Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet. However, running these detectors on each and every frame in resource-constrained edge devices is computationally intensive. By taking the temporal correlation between consecutive video frames into account, we note that detection outputs tend to be overlapping in successive frames. Elimination of similar consecutive frames will lead to a negligible drop in performance while offering significant performance benefits by reducing overall computation and communication costs. The key technical questions are, therefore, (a) how to identify which frames to be processed by the object detector, and (b) how many successive frames can be skipped (called skip-length) once a frame is selected to be processed. The overall goal of the process is to keep the error due to skipping frames as small as possible. We introduce a novel error vs processing rate optimization problem with respect to the object detection task that balances between the error rate and the fraction of frames filtering. Subsequently, we propose an off-line Reinforcement Learning (RL)-based algorithm to determine these skip-lengths as a state-action policy of the RL agent from a recorded video and then deploy the agent online for live video streams. To this end, we develop FrameHopper, an edge-cloud collaborative video analytics framework, that runs a lightweight trained RL agent on the camera and passes filtered frames to the server where the object detection model runs for a set of applications. We have tested our approach on a number of live videos captured from real-life scenarios and show that FrameHopper processes only a handful of frames but produces detection results closer to the oracle solution and outperforms recent state-of-the-art solutions in most cases." @default.
- W4226061185 created "2022-05-05" @default.
- W4226061185 creator A5008222662 @default.
- W4226061185 creator A5029193352 @default.
- W4226061185 creator A5075380639 @default.
- W4226061185 date "2022-03-22" @default.
- W4226061185 modified "2023-09-30" @default.
- W4226061185 title "FrameHopper: Selective Processing of Video Frames in Detection-driven Real-Time Video Analytics" @default.
- W4226061185 doi "https://doi.org/10.48550/arxiv.2203.11493" @default.
- W4226061185 hasPublicationYear "2022" @default.
- W4226061185 type Work @default.
- W4226061185 citedByCount "0" @default.
- W4226061185 crossrefType "posted-content" @default.
- W4226061185 hasAuthorship W4226061185A5008222662 @default.
- W4226061185 hasAuthorship W4226061185A5029193352 @default.
- W4226061185 hasAuthorship W4226061185A5075380639 @default.
- W4226061185 hasBestOaLocation W42260611851 @default.
- W4226061185 hasConcept C111919701 @default.
- W4226061185 hasConcept C124101348 @default.
- W4226061185 hasConcept C126042441 @default.
- W4226061185 hasConcept C153180895 @default.
- W4226061185 hasConcept C154945302 @default.
- W4226061185 hasConcept C162324750 @default.
- W4226061185 hasConcept C187736073 @default.
- W4226061185 hasConcept C202474056 @default.
- W4226061185 hasConcept C26517878 @default.
- W4226061185 hasConcept C2776151529 @default.
- W4226061185 hasConcept C2780451532 @default.
- W4226061185 hasConcept C31972630 @default.
- W4226061185 hasConcept C3261483 @default.
- W4226061185 hasConcept C38652104 @default.
- W4226061185 hasConcept C41008148 @default.
- W4226061185 hasConcept C65483669 @default.
- W4226061185 hasConcept C76155785 @default.
- W4226061185 hasConcept C79158427 @default.
- W4226061185 hasConcept C79403827 @default.
- W4226061185 hasConcept C94915269 @default.
- W4226061185 hasConcept C97541855 @default.
- W4226061185 hasConcept C98045186 @default.
- W4226061185 hasConceptScore W4226061185C111919701 @default.
- W4226061185 hasConceptScore W4226061185C124101348 @default.
- W4226061185 hasConceptScore W4226061185C126042441 @default.
- W4226061185 hasConceptScore W4226061185C153180895 @default.
- W4226061185 hasConceptScore W4226061185C154945302 @default.
- W4226061185 hasConceptScore W4226061185C162324750 @default.
- W4226061185 hasConceptScore W4226061185C187736073 @default.
- W4226061185 hasConceptScore W4226061185C202474056 @default.
- W4226061185 hasConceptScore W4226061185C26517878 @default.
- W4226061185 hasConceptScore W4226061185C2776151529 @default.
- W4226061185 hasConceptScore W4226061185C2780451532 @default.
- W4226061185 hasConceptScore W4226061185C31972630 @default.
- W4226061185 hasConceptScore W4226061185C3261483 @default.
- W4226061185 hasConceptScore W4226061185C38652104 @default.
- W4226061185 hasConceptScore W4226061185C41008148 @default.
- W4226061185 hasConceptScore W4226061185C65483669 @default.
- W4226061185 hasConceptScore W4226061185C76155785 @default.
- W4226061185 hasConceptScore W4226061185C79158427 @default.
- W4226061185 hasConceptScore W4226061185C79403827 @default.
- W4226061185 hasConceptScore W4226061185C94915269 @default.
- W4226061185 hasConceptScore W4226061185C97541855 @default.
- W4226061185 hasConceptScore W4226061185C98045186 @default.
- W4226061185 hasLocation W42260611851 @default.
- W4226061185 hasOpenAccess W4226061185 @default.
- W4226061185 hasPrimaryLocation W42260611851 @default.
- W4226061185 hasRelatedWork W1882680974 @default.
- W4226061185 hasRelatedWork W1966005655 @default.
- W4226061185 hasRelatedWork W2029737934 @default.
- W4226061185 hasRelatedWork W2043290978 @default.
- W4226061185 hasRelatedWork W2101754984 @default.
- W4226061185 hasRelatedWork W2182044822 @default.
- W4226061185 hasRelatedWork W2242389414 @default.
- W4226061185 hasRelatedWork W2894428579 @default.
- W4226061185 hasRelatedWork W3004244592 @default.
- W4226061185 hasRelatedWork W4214574710 @default.
- W4226061185 isParatext "false" @default.
- W4226061185 isRetracted "false" @default.
- W4226061185 workType "article" @default.