Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297922476> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4297922476 endingPage "1346" @default.
- W4297922476 startingPage "1346" @default.
- W4297922476 abstract "In recent years, convolutional neural network (CNN)-based object detection algorithms have made breakthroughs, and much of the research corresponds to hardware accelerator designs. Although many previous works have proposed efficient FPGA designs for one-stage detectors such as Yolo, there are still few accelerator designs for faster regions with CNN features (Faster R-CNN) algorithms. Moreover, CNN's inherently high computational complexity and high memory complexity bring challenges to the design of efficient accelerators. This paper proposes a software-hardware co-design scheme based on OpenCL to implement a Faster R-CNN object detection algorithm on FPGA. First, we design an efficient, deep pipelined FPGA hardware accelerator that can implement Faster R-CNN algorithms for different backbone networks. Then, an optimized hardware-aware software algorithm was proposed, including fixed-point quantization, layer fusion, and a multi-batch Regions of interest (RoIs) detector. Finally, we present an end-to-end design space exploration scheme to comprehensively evaluate the performance and resource utilization of the proposed accelerator. Experimental results show that the proposed design achieves a peak throughput of 846.9 GOP/s at the working frequency of 172 MHz. Compared with the state-of-the-art Faster R-CNN accelerator and the one-stage YOLO accelerator, our method achieves 10× and 2.1× inference throughput improvements, respectively." @default.
- W4297922476 created "2022-10-01" @default.
- W4297922476 creator A5024869142 @default.
- W4297922476 creator A5044768121 @default.
- W4297922476 creator A5045574896 @default.
- W4297922476 creator A5076711942 @default.
- W4297922476 date "2022-09-23" @default.
- W4297922476 modified "2023-09-26" @default.
- W4297922476 title "An OpenCL-Based FPGA Accelerator for Faster R-CNN" @default.
- W4297922476 cites W1995562189 @default.
- W4297922476 cites W2031489346 @default.
- W4297922476 cites W2088049833 @default.
- W4297922476 cites W2094756095 @default.
- W4297922476 cites W2276486856 @default.
- W4297922476 cites W2294282016 @default.
- W4297922476 cites W2597692291 @default.
- W4297922476 cites W2618530766 @default.
- W4297922476 cites W2739789140 @default.
- W4297922476 cites W2790167166 @default.
- W4297922476 cites W2792503273 @default.
- W4297922476 cites W2793950911 @default.
- W4297922476 cites W2798742349 @default.
- W4297922476 cites W2916484109 @default.
- W4297922476 cites W2953162405 @default.
- W4297922476 cites W2997106510 @default.
- W4297922476 cites W3023624105 @default.
- W4297922476 cites W3035946844 @default.
- W4297922476 cites W3160929742 @default.
- W4297922476 cites W4283747519 @default.
- W4297922476 cites W639708223 @default.
- W4297922476 doi "https://doi.org/10.3390/e24101346" @default.
- W4297922476 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37420365" @default.
- W4297922476 hasPublicationYear "2022" @default.
- W4297922476 type Work @default.
- W4297922476 citedByCount "1" @default.
- W4297922476 countsByYear W42979224762023 @default.
- W4297922476 crossrefType "journal-article" @default.
- W4297922476 hasAuthorship W4297922476A5024869142 @default.
- W4297922476 hasAuthorship W4297922476A5044768121 @default.
- W4297922476 hasAuthorship W4297922476A5045574896 @default.
- W4297922476 hasAuthorship W4297922476A5076711942 @default.
- W4297922476 hasBestOaLocation W42979224761 @default.
- W4297922476 hasConcept C113775141 @default.
- W4297922476 hasConcept C11413529 @default.
- W4297922476 hasConcept C13164978 @default.
- W4297922476 hasConcept C154945302 @default.
- W4297922476 hasConcept C157764524 @default.
- W4297922476 hasConcept C199360897 @default.
- W4297922476 hasConcept C2777904410 @default.
- W4297922476 hasConcept C28855332 @default.
- W4297922476 hasConcept C41008148 @default.
- W4297922476 hasConcept C42935608 @default.
- W4297922476 hasConcept C555944384 @default.
- W4297922476 hasConcept C76155785 @default.
- W4297922476 hasConcept C81363708 @default.
- W4297922476 hasConcept C9390403 @default.
- W4297922476 hasConceptScore W4297922476C113775141 @default.
- W4297922476 hasConceptScore W4297922476C11413529 @default.
- W4297922476 hasConceptScore W4297922476C13164978 @default.
- W4297922476 hasConceptScore W4297922476C154945302 @default.
- W4297922476 hasConceptScore W4297922476C157764524 @default.
- W4297922476 hasConceptScore W4297922476C199360897 @default.
- W4297922476 hasConceptScore W4297922476C2777904410 @default.
- W4297922476 hasConceptScore W4297922476C28855332 @default.
- W4297922476 hasConceptScore W4297922476C41008148 @default.
- W4297922476 hasConceptScore W4297922476C42935608 @default.
- W4297922476 hasConceptScore W4297922476C555944384 @default.
- W4297922476 hasConceptScore W4297922476C76155785 @default.
- W4297922476 hasConceptScore W4297922476C81363708 @default.
- W4297922476 hasConceptScore W4297922476C9390403 @default.
- W4297922476 hasIssue "10" @default.
- W4297922476 hasLocation W42979224761 @default.
- W4297922476 hasLocation W42979224762 @default.
- W4297922476 hasLocation W42979224763 @default.
- W4297922476 hasOpenAccess W4297922476 @default.
- W4297922476 hasPrimaryLocation W42979224761 @default.
- W4297922476 hasRelatedWork W2295680811 @default.
- W4297922476 hasRelatedWork W2466675884 @default.
- W4297922476 hasRelatedWork W2524802307 @default.
- W4297922476 hasRelatedWork W2786216825 @default.
- W4297922476 hasRelatedWork W2951390974 @default.
- W4297922476 hasRelatedWork W2997828269 @default.
- W4297922476 hasRelatedWork W3035662153 @default.
- W4297922476 hasRelatedWork W3185363859 @default.
- W4297922476 hasRelatedWork W4293025835 @default.
- W4297922476 hasRelatedWork W4316658533 @default.
- W4297922476 hasVolume "24" @default.
- W4297922476 isParatext "false" @default.
- W4297922476 isRetracted "false" @default.
- W4297922476 workType "article" @default.