Matches in SemOpenAlex for { <https://semopenalex.org/work/W3158594189> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3158594189 abstract "In this paper, we present the first (to the best of our knowledge) demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). The design leverages on a 9-core RISC-V processor, GAP8, coupled with a QVGA ultra-low-power greyscale imager. The proposed visual processing pipeline uses a multi-model inference approach based on SSDlite-MobilenetV2 for license plate detection and LPRNet for optical character recognition, reaching a 38.9% mAP score for the first task and a recognition rate of >99.13% for the latter on public datasets. On real-world data, the pipeline recognizes registration numbers when the size of LP crops is as small as 30×5 pixels. Thanks to the applied compression and optimization strategies, the multi-model inference (687 MMAC) achieves a throughput of 1.09 FPS at a power cost of 117 mW when running on GAP8. Our solution is the first MCU-class device embedding such a level of network complexity, resulting to be 73× more energy-efficient w.r.t. precedent mobile-class ALPR system featuring a Raspberry Pi3. The proposed design does not resort to any hardwired acceleration engines, thus retaining full flexibility for future algorithmic improvements." @default.
- W3158594189 created "2021-05-10" @default.
- W3158594189 creator A5028966277 @default.
- W3158594189 creator A5030025275 @default.
- W3158594189 creator A5035367442 @default.
- W3158594189 creator A5043408422 @default.
- W3158594189 creator A5048627694 @default.
- W3158594189 date "2021-05-01" @default.
- W3158594189 modified "2023-10-10" @default.
- W3158594189 title "Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System" @default.
- W3158594189 cites W1573267348 @default.
- W3158594189 cites W2611966310 @default.
- W3158594189 cites W2788907956 @default.
- W3158594189 cites W2889339831 @default.
- W3158594189 cites W2897185734 @default.
- W3158594189 cites W2909953480 @default.
- W3158594189 cites W2936929788 @default.
- W3158594189 cites W2949749214 @default.
- W3158594189 cites W2951898149 @default.
- W3158594189 cites W2963122961 @default.
- W3158594189 cites W2981774126 @default.
- W3158594189 cites W3000002142 @default.
- W3158594189 cites W3004846386 @default.
- W3158594189 cites W3013186616 @default.
- W3158594189 cites W3013382035 @default.
- W3158594189 cites W3103292482 @default.
- W3158594189 cites W3106250896 @default.
- W3158594189 cites W4288083516 @default.
- W3158594189 doi "https://doi.org/10.1109/iscas51556.2021.9401730" @default.
- W3158594189 hasPublicationYear "2021" @default.
- W3158594189 type Work @default.
- W3158594189 sameAs 3158594189 @default.
- W3158594189 citedByCount "2" @default.
- W3158594189 countsByYear W31585941892023 @default.
- W3158594189 crossrefType "proceedings-article" @default.
- W3158594189 hasAuthorship W3158594189A5028966277 @default.
- W3158594189 hasAuthorship W3158594189A5030025275 @default.
- W3158594189 hasAuthorship W3158594189A5035367442 @default.
- W3158594189 hasAuthorship W3158594189A5043408422 @default.
- W3158594189 hasAuthorship W3158594189A5048627694 @default.
- W3158594189 hasConcept C111919701 @default.
- W3158594189 hasConcept C149635348 @default.
- W3158594189 hasConcept C154945302 @default.
- W3158594189 hasConcept C160633673 @default.
- W3158594189 hasConcept C173018170 @default.
- W3158594189 hasConcept C31972630 @default.
- W3158594189 hasConcept C41008148 @default.
- W3158594189 hasConcept C43521106 @default.
- W3158594189 hasConcept C9390403 @default.
- W3158594189 hasConceptScore W3158594189C111919701 @default.
- W3158594189 hasConceptScore W3158594189C149635348 @default.
- W3158594189 hasConceptScore W3158594189C154945302 @default.
- W3158594189 hasConceptScore W3158594189C160633673 @default.
- W3158594189 hasConceptScore W3158594189C173018170 @default.
- W3158594189 hasConceptScore W3158594189C31972630 @default.
- W3158594189 hasConceptScore W3158594189C41008148 @default.
- W3158594189 hasConceptScore W3158594189C43521106 @default.
- W3158594189 hasConceptScore W3158594189C9390403 @default.
- W3158594189 hasLocation W31585941891 @default.
- W3158594189 hasOpenAccess W3158594189 @default.
- W3158594189 hasPrimaryLocation W31585941891 @default.
- W3158594189 hasRelatedWork W1972388196 @default.
- W3158594189 hasRelatedWork W1985703800 @default.
- W3158594189 hasRelatedWork W2089988144 @default.
- W3158594189 hasRelatedWork W2147310439 @default.
- W3158594189 hasRelatedWork W2347749188 @default.
- W3158594189 hasRelatedWork W2351039487 @default.
- W3158594189 hasRelatedWork W2386082753 @default.
- W3158594189 hasRelatedWork W3091627987 @default.
- W3158594189 hasRelatedWork W4362711618 @default.
- W3158594189 hasRelatedWork W3095757606 @default.
- W3158594189 isParatext "false" @default.
- W3158594189 isRetracted "false" @default.
- W3158594189 magId "3158594189" @default.
- W3158594189 workType "article" @default.