Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205933765> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3205933765 abstract "Gradual advances have occurred in the design of micro-artificial intelligence for resource-limited hardware. A high-resolution (HR) image reconstruction module is indispensable for video analytics chips or devices at the edge. This paper proposes a low-cost and learning-based interpolation method for HR image reconstruction. The proposed method generates reconstructed pixels by processing reference pixels with optimal weights, which are pre-trained by solving the minimum mean square error problem for real images. To reduce the number of computation units and the usage of learned weights, a cross-directional interpolation architecture, which includes a vertical kernel and a horizontal kernel, is adopted. Moreover, a one-dimensional feature discriminator is proposed to improve the quality of up-scaled images efficiently. The main benefit of the proposed method is that it requires a small number of computation units but can still produce high-quality images. The hardware architecture of the proposed method was implemented on a field-programmable gate array (FPGA) by using Xilinx UltraScale+ ZCU102 and an application-specific integrated circuit (ASIC) by using TSMC’s 0.13-μm technology. On the ASIC, the proposed hardware required only approximately 60K gate counts and 50 KBytes of memory. The experimental results indicate that the average peak signal-to-noise ratio of the up-scaled images reached 35.92 dB for the Set-5 dataset. The throughput of the proposed hardware was at least 1000 Mpixels/s on the FPGA and 1200 Mpixels/s on the ASIC, which indicates that the proposed hardware can handle a target resolution higher than 4K in real time." @default.
- W3205933765 created "2021-10-25" @default.
- W3205933765 creator A5010008276 @default.
- W3205933765 creator A5035077218 @default.
- W3205933765 creator A5067884201 @default.
- W3205933765 creator A5079051364 @default.
- W3205933765 date "2021-01-01" @default.
- W3205933765 modified "2023-09-24" @default.
- W3205933765 title "A Low-cost Hardware Design of Learning-based One-dimensional Interpolation for Real-time Video Applications at the Edge" @default.
- W3205933765 doi "https://doi.org/10.1109/jetcas.2021.3121070" @default.
- W3205933765 hasPublicationYear "2021" @default.
- W3205933765 type Work @default.
- W3205933765 sameAs 3205933765 @default.
- W3205933765 citedByCount "1" @default.
- W3205933765 countsByYear W32059337652022 @default.
- W3205933765 crossrefType "journal-article" @default.
- W3205933765 hasAuthorship W3205933765A5010008276 @default.
- W3205933765 hasAuthorship W3205933765A5035077218 @default.
- W3205933765 hasAuthorship W3205933765A5067884201 @default.
- W3205933765 hasAuthorship W3205933765A5079051364 @default.
- W3205933765 hasBestOaLocation W32059337651 @default.
- W3205933765 hasConcept C114237110 @default.
- W3205933765 hasConcept C114614502 @default.
- W3205933765 hasConcept C115961682 @default.
- W3205933765 hasConcept C137800194 @default.
- W3205933765 hasConcept C154945302 @default.
- W3205933765 hasConcept C160633673 @default.
- W3205933765 hasConcept C199360897 @default.
- W3205933765 hasConcept C2777904410 @default.
- W3205933765 hasConcept C33923547 @default.
- W3205933765 hasConcept C41008148 @default.
- W3205933765 hasConcept C42935608 @default.
- W3205933765 hasConcept C43521106 @default.
- W3205933765 hasConcept C65232700 @default.
- W3205933765 hasConcept C74193536 @default.
- W3205933765 hasConcept C77390884 @default.
- W3205933765 hasConcept C9390403 @default.
- W3205933765 hasConceptScore W3205933765C114237110 @default.
- W3205933765 hasConceptScore W3205933765C114614502 @default.
- W3205933765 hasConceptScore W3205933765C115961682 @default.
- W3205933765 hasConceptScore W3205933765C137800194 @default.
- W3205933765 hasConceptScore W3205933765C154945302 @default.
- W3205933765 hasConceptScore W3205933765C160633673 @default.
- W3205933765 hasConceptScore W3205933765C199360897 @default.
- W3205933765 hasConceptScore W3205933765C2777904410 @default.
- W3205933765 hasConceptScore W3205933765C33923547 @default.
- W3205933765 hasConceptScore W3205933765C41008148 @default.
- W3205933765 hasConceptScore W3205933765C42935608 @default.
- W3205933765 hasConceptScore W3205933765C43521106 @default.
- W3205933765 hasConceptScore W3205933765C65232700 @default.
- W3205933765 hasConceptScore W3205933765C74193536 @default.
- W3205933765 hasConceptScore W3205933765C77390884 @default.
- W3205933765 hasConceptScore W3205933765C9390403 @default.
- W3205933765 hasLocation W32059337651 @default.
- W3205933765 hasOpenAccess W3205933765 @default.
- W3205933765 hasPrimaryLocation W32059337651 @default.
- W3205933765 hasRelatedWork W11437179 @default.
- W3205933765 hasRelatedWork W12889342 @default.
- W3205933765 hasRelatedWork W2925775 @default.
- W3205933765 hasRelatedWork W386281 @default.
- W3205933765 hasRelatedWork W4265437 @default.
- W3205933765 hasRelatedWork W4470474 @default.
- W3205933765 hasRelatedWork W6552217 @default.
- W3205933765 hasRelatedWork W7620075 @default.
- W3205933765 hasRelatedWork W7914692 @default.
- W3205933765 hasRelatedWork W905178 @default.
- W3205933765 isParatext "false" @default.
- W3205933765 isRetracted "false" @default.
- W3205933765 magId "3205933765" @default.
- W3205933765 workType "article" @default.