Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109977897> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3109977897 abstract "With the improvements in the object detection networks, several variations of object detection networks have been achieved impressive performance. However, the performance evaluation of most models has focused on detection accuracy, and performance verification is mostly based on high-end GPU hardware. In this paper, we propose real-time object detectors that guarantee balanced performance for real-time systems on embedded platforms. The proposed model utilizes the basic head structure of the RefineDet model, which is a variant of the single-shot object detector (SSD). In order to ensure real-time performance, CNN models with relatively shallow layers or fewer parameters have been used as the backbone structure. In addition to the basic VGGNet and ResNet structures, various backbone structures such as MobileNet, Xception, ResNeXt, Inception-SENet, and SE-ResNeXt have been used for this purpose. Successful training of object detection networks was achieved through an appropriate combination of intermediate layers. The accuracy of the proposed detector was estimated by the evaluation of the MS-COCO 2017 object detection dataset and the inference speed on the NVIDIA Drive PX2 and Jetson Xavier boards were tested to verify real-time performance in the embedded systems. The experiments show that the proposed models ensure balanced performance in terms of accuracy and inference speed in the embedded system environments. In addition, unlike the high-end GPUs, the use of embedded GPUs involves several additional concerns for efficient inference, which have been identified in this work. The codes and models are publicly available on the web (link)." @default.
- W3109977897 created "2020-12-07" @default.
- W3109977897 creator A5037689754 @default.
- W3109977897 creator A5064276223 @default.
- W3109977897 date "2019-09-24" @default.
- W3109977897 modified "2023-09-27" @default.
- W3109977897 title "Development of Fast Refinement Detectors on AI Edge Platforms" @default.
- W3109977897 cites W1817277359 @default.
- W3109977897 cites W1861492603 @default.
- W3109977897 cites W2102605133 @default.
- W3109977897 cites W2117539524 @default.
- W3109977897 cites W2183341477 @default.
- W3109977897 cites W2194775991 @default.
- W3109977897 cites W2288122362 @default.
- W3109977897 cites W2407521645 @default.
- W3109977897 cites W2531409750 @default.
- W3109977897 cites W2549139847 @default.
- W3109977897 cites W2557728737 @default.
- W3109977897 cites W2579985080 @default.
- W3109977897 cites W2601564443 @default.
- W3109977897 cites W2605557641 @default.
- W3109977897 cites W2612445135 @default.
- W3109977897 cites W2613718673 @default.
- W3109977897 cites W2736691214 @default.
- W3109977897 cites W2769291631 @default.
- W3109977897 cites W2796438033 @default.
- W3109977897 cites W2890715498 @default.
- W3109977897 cites W2891044424 @default.
- W3109977897 cites W2951548327 @default.
- W3109977897 cites W2952122856 @default.
- W3109977897 cites W2962917547 @default.
- W3109977897 cites W2963068995 @default.
- W3109977897 cites W2963087201 @default.
- W3109977897 cites W2963150697 @default.
- W3109977897 cites W2963351448 @default.
- W3109977897 cites W2963420686 @default.
- W3109977897 cites W2963516811 @default.
- W3109977897 cites W2963647178 @default.
- W3109977897 cites W2963786238 @default.
- W3109977897 cites W3106250896 @default.
- W3109977897 hasPublicationYear "2019" @default.
- W3109977897 type Work @default.
- W3109977897 sameAs 3109977897 @default.
- W3109977897 citedByCount "0" @default.
- W3109977897 crossrefType "posted-content" @default.
- W3109977897 hasAuthorship W3109977897A5037689754 @default.
- W3109977897 hasAuthorship W3109977897A5064276223 @default.
- W3109977897 hasConcept C113775141 @default.
- W3109977897 hasConcept C153180895 @default.
- W3109977897 hasConcept C154945302 @default.
- W3109977897 hasConcept C162307627 @default.
- W3109977897 hasConcept C173608175 @default.
- W3109977897 hasConcept C2776151529 @default.
- W3109977897 hasConcept C2776214188 @default.
- W3109977897 hasConcept C2781238097 @default.
- W3109977897 hasConcept C41008148 @default.
- W3109977897 hasConcept C68339613 @default.
- W3109977897 hasConcept C76155785 @default.
- W3109977897 hasConcept C88796919 @default.
- W3109977897 hasConcept C94915269 @default.
- W3109977897 hasConceptScore W3109977897C113775141 @default.
- W3109977897 hasConceptScore W3109977897C153180895 @default.
- W3109977897 hasConceptScore W3109977897C154945302 @default.
- W3109977897 hasConceptScore W3109977897C162307627 @default.
- W3109977897 hasConceptScore W3109977897C173608175 @default.
- W3109977897 hasConceptScore W3109977897C2776151529 @default.
- W3109977897 hasConceptScore W3109977897C2776214188 @default.
- W3109977897 hasConceptScore W3109977897C2781238097 @default.
- W3109977897 hasConceptScore W3109977897C41008148 @default.
- W3109977897 hasConceptScore W3109977897C68339613 @default.
- W3109977897 hasConceptScore W3109977897C76155785 @default.
- W3109977897 hasConceptScore W3109977897C88796919 @default.
- W3109977897 hasConceptScore W3109977897C94915269 @default.
- W3109977897 hasLocation W31099778971 @default.
- W3109977897 hasOpenAccess W3109977897 @default.
- W3109977897 hasPrimaryLocation W31099778971 @default.
- W3109977897 hasRelatedWork W1120166712 @default.
- W3109977897 hasRelatedWork W1541157786 @default.
- W3109977897 hasRelatedWork W2587872917 @default.
- W3109977897 hasRelatedWork W2597692291 @default.
- W3109977897 hasRelatedWork W2901647584 @default.
- W3109977897 hasRelatedWork W2918653705 @default.
- W3109977897 hasRelatedWork W2924139770 @default.
- W3109977897 hasRelatedWork W2935189569 @default.
- W3109977897 hasRelatedWork W2962697884 @default.
- W3109977897 hasRelatedWork W2974412363 @default.
- W3109977897 hasRelatedWork W2975025379 @default.
- W3109977897 hasRelatedWork W2981392049 @default.
- W3109977897 hasRelatedWork W3086934391 @default.
- W3109977897 hasRelatedWork W3127317982 @default.
- W3109977897 hasRelatedWork W3135408567 @default.
- W3109977897 hasRelatedWork W3159018959 @default.
- W3109977897 hasRelatedWork W3175158881 @default.
- W3109977897 hasRelatedWork W3187648707 @default.
- W3109977897 hasRelatedWork W3211298605 @default.
- W3109977897 hasRelatedWork W3135424528 @default.
- W3109977897 isParatext "false" @default.
- W3109977897 isRetracted "false" @default.
- W3109977897 magId "3109977897" @default.
- W3109977897 workType "article" @default.