FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308659718> ?p ?o ?g. }

• W4308659718 abstract "Today’s high resolution, high frame rate cameras in autonomous vehicles generate a large volume of data that needs to be transferred and processed by a downstream processor or machine learning (ML) accelerator to enable intelligent computing tasks, such as multi-object detection and tracking. The massive amount of data transfer incurs significant energy, latency, and bandwidth bottlenecks, which hinders real-time processing. To mitigate this problem, we propose an algorithm-hardware co-design framework called Processing-in-Pixel-in-Memory-based object Detection and Tracking (P <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> M-DeTrack). P <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> M-DeTrack is based on a custom faster R-CNN-based model that is distributed partly inside the pixel array (front-end) and partly in a separate FPGA/ASIC (back-end). The proposed front-end in-pixel processing down-samples the input feature maps significantly with judiciously optimized strided convolution and pooling. Compared to a conventional baseline design that transfers frames of RGB pixels to the back-end, the resulting P <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> M-DeTrack designs reduce the data bandwidth between sensor and back-end by up to 24×. The designs also reduce the sensor and total energy (obtained from in-house circuit simulations at Globalfoundries 22nm technology node) per frame by 5.7× and 1.14×, respectively. Lastly, they reduce the sensing and total frame latency by an estimated 1.7× and 3×, respectively. We evaluate our approach on the multi-object object detection (tracking) task of the large-scale BDD100K dataset and observe only a 0.5% reduction in the mean average precision (0.8% reduction in the identification F1 score) compared to the state-of-the-art." @default.
• W4308659718 created "2022-11-13" @default.
• W4308659718 creator A5003606780 @default.
• W4308659718 creator A5017435097 @default.
• W4308659718 creator A5020303448 @default.
• W4308659718 creator A5028455158 @default.
• W4308659718 creator A5028776484 @default.
• W4308659718 creator A5031812850 @default.
• W4308659718 creator A5032145675 @default.
• W4308659718 creator A5036145381 @default.
• W4308659718 creator A5037825143 @default.
• W4308659718 creator A5044588871 @default.
• W4308659718 creator A5076002956 @default.
• W4308659718 creator A5082003632 @default.
• W4308659718 creator A5084205024 @default.
• W4308659718 creator A5088675634 @default.
• W4308659718 date "2022-10-03" @default.
• W4308659718 modified "2023-10-14" @default.
• W4308659718 title "P²M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking" @default.
• W4308659718 cites W2004823737 @default.
• W4308659718 cites W2069756028 @default.
• W4308659718 cites W2766967989 @default.
• W4308659718 cites W2954664695 @default.
• W4308659718 cites W2962818002 @default.
• W4308659718 cites W2972984303 @default.
• W4308659718 cites W2991479671 @default.
• W4308659718 cites W3006098440 @default.
• W4308659718 cites W3009653238 @default.
• W4308659718 cites W3009994855 @default.
• W4308659718 cites W3042493405 @default.
• W4308659718 cites W3049037182 @default.
• W4308659718 cites W3090800460 @default.
• W4308659718 cites W3102169921 @default.
• W4308659718 cites W3128829362 @default.
• W4308659718 cites W3137507574 @default.
• W4308659718 cites W3165926952 @default.
• W4308659718 cites W3191343975 @default.
• W4308659718 cites W4226192365 @default.
• W4308659718 doi "https://doi.org/10.1109/vlsi-soc54400.2022.9939582" @default.
• W4308659718 hasPublicationYear "2022" @default.
• W4308659718 type Work @default.
• W4308659718 citedByCount "5" @default.
• W4308659718 countsByYear W43086597182023 @default.
• W4308659718 crossrefType "proceedings-article" @default.
• W4308659718 hasAuthorship W4308659718A5003606780 @default.
• W4308659718 hasAuthorship W4308659718A5017435097 @default.
• W4308659718 hasAuthorship W4308659718A5020303448 @default.
• W4308659718 hasAuthorship W4308659718A5028455158 @default.
• W4308659718 hasAuthorship W4308659718A5028776484 @default.
• W4308659718 hasAuthorship W4308659718A5031812850 @default.
• W4308659718 hasAuthorship W4308659718A5032145675 @default.
• W4308659718 hasAuthorship W4308659718A5036145381 @default.
• W4308659718 hasAuthorship W4308659718A5037825143 @default.
• W4308659718 hasAuthorship W4308659718A5044588871 @default.
• W4308659718 hasAuthorship W4308659718A5076002956 @default.
• W4308659718 hasAuthorship W4308659718A5082003632 @default.
• W4308659718 hasAuthorship W4308659718A5084205024 @default.
• W4308659718 hasAuthorship W4308659718A5088675634 @default.
• W4308659718 hasBestOaLocation W43086597182 @default.
• W4308659718 hasConcept C126042441 @default.
• W4308659718 hasConcept C153180895 @default.
• W4308659718 hasConcept C154945302 @default.
• W4308659718 hasConcept C160633673 @default.
• W4308659718 hasConcept C2776151529 @default.
• W4308659718 hasConcept C2776257435 @default.
• W4308659718 hasConcept C31258907 @default.
• W4308659718 hasConcept C31972630 @default.
• W4308659718 hasConcept C3261483 @default.
• W4308659718 hasConcept C41008148 @default.
• W4308659718 hasConcept C76155785 @default.
• W4308659718 hasConcept C77390884 @default.
• W4308659718 hasConcept C82876162 @default.
• W4308659718 hasConcept C9390403 @default.
• W4308659718 hasConceptScore W4308659718C126042441 @default.
• W4308659718 hasConceptScore W4308659718C153180895 @default.
• W4308659718 hasConceptScore W4308659718C154945302 @default.
• W4308659718 hasConceptScore W4308659718C160633673 @default.
• W4308659718 hasConceptScore W4308659718C2776151529 @default.
• W4308659718 hasConceptScore W4308659718C2776257435 @default.
• W4308659718 hasConceptScore W4308659718C31258907 @default.
• W4308659718 hasConceptScore W4308659718C31972630 @default.
• W4308659718 hasConceptScore W4308659718C3261483 @default.
• W4308659718 hasConceptScore W4308659718C41008148 @default.
• W4308659718 hasConceptScore W4308659718C76155785 @default.
• W4308659718 hasConceptScore W4308659718C77390884 @default.
• W4308659718 hasConceptScore W4308659718C82876162 @default.
• W4308659718 hasConceptScore W4308659718C9390403 @default.
• W4308659718 hasLocation W43086597181 @default.
• W4308659718 hasLocation W43086597182 @default.
• W4308659718 hasOpenAccess W4308659718 @default.
• W4308659718 hasPrimaryLocation W43086597181 @default.
• W4308659718 hasRelatedWork W2066730339 @default.
• W4308659718 hasRelatedWork W2090093270 @default.
• W4308659718 hasRelatedWork W2235808292 @default.
• W4308659718 hasRelatedWork W2309573947 @default.
• W4308659718 hasRelatedWork W2318931232 @default.
• W4308659718 hasRelatedWork W2588505718 @default.
• W4308659718 hasRelatedWork W2607572884 @default.
• W4308659718 hasRelatedWork W2739874619 @default.
• W4308659718 hasRelatedWork W4312857205 @default.

• next