FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280526090> ?p ?o ?g. }

• W4280526090 abstract "The development of object detection technology makes it possible for robots to interact with people and the environment, but the changeable application scenarios make the detection accuracy of small and medium objects in the practical application of object detection technology low. In this paper, based on multi-scale feature fusion of indoor small target detection method, using the device to collect different indoor images with angle, light, and shade conditions, and use the image enhancement technology to set up and amplify a date set, with indoor scenarios and the SSD algorithm in target detection layer and its adjacent features fusion. The Faster R-CNN, YOLOv5, SSD, and SSD target detection models based on multi-scale feature fusion were trained on an indoor scene data set based on transfer learning. The experimental results show that multi-scale feature fusion can improve the detection accuracy of all kinds of objects, especially for objects with a relatively small scale. In addition, although the detection speed of the improved SSD algorithm decreases, it is faster than the Faster R-CNN, which better achieves the balance between target detection accuracy and speed." @default.
• W4280526090 created "2022-05-22" @default.
• W4280526090 creator A5006580423 @default.
• W4280526090 creator A5014508923 @default.
• W4280526090 creator A5016257935 @default.
• W4280526090 creator A5035701991 @default.
• W4280526090 creator A5042016865 @default.
• W4280526090 creator A5055545502 @default.
• W4280526090 creator A5063035156 @default.
• W4280526090 creator A5064548129 @default.
• W4280526090 date "2022-05-19" @default.
• W4280526090 modified "2023-10-18" @default.
• W4280526090 title "Multi-Scale Feature Fusion Convolutional Neural Network for Indoor Small Target Detection" @default.
• W4280526090 cites W2109255472 @default.
• W4280526090 cites W2168356304 @default.
• W4280526090 cites W2530966705 @default.
• W4280526090 cites W2560757589 @default.
• W4280526090 cites W2609633863 @default.
• W4280526090 cites W2615751500 @default.
• W4280526090 cites W2747876883 @default.
• W4280526090 cites W2757028014 @default.
• W4280526090 cites W2759269579 @default.
• W4280526090 cites W2759611403 @default.
• W4280526090 cites W2761412452 @default.
• W4280526090 cites W2784083162 @default.
• W4280526090 cites W2786423589 @default.
• W4280526090 cites W2787029871 @default.
• W4280526090 cites W2791697444 @default.
• W4280526090 cites W2884367402 @default.
• W4280526090 cites W2894604694 @default.
• W4280526090 cites W2900419434 @default.
• W4280526090 cites W2901402366 @default.
• W4280526090 cites W2908996122 @default.
• W4280526090 cites W2913706771 @default.
• W4280526090 cites W2914113834 @default.
• W4280526090 cites W2921850736 @default.
• W4280526090 cites W2935568451 @default.
• W4280526090 cites W2936583340 @default.
• W4280526090 cites W2941851574 @default.
• W4280526090 cites W2963315052 @default.
• W4280526090 cites W2964793207 @default.
• W4280526090 cites W2965160935 @default.
• W4280526090 cites W2965245384 @default.
• W4280526090 cites W2991197884 @default.
• W4280526090 cites W2995077765 @default.
• W4280526090 cites W2996107740 @default.
• W4280526090 cites W2999062364 @default.
• W4280526090 cites W3000764807 @default.
• W4280526090 cites W3005135132 @default.
• W4280526090 cites W3020913131 @default.
• W4280526090 cites W3036220795 @default.
• W4280526090 cites W3081533949 @default.
• W4280526090 cites W3084196234 @default.
• W4280526090 cites W3092482093 @default.
• W4280526090 cites W3093858584 @default.
• W4280526090 cites W3097096317 @default.
• W4280526090 cites W3118639016 @default.
• W4280526090 cites W3126940553 @default.
• W4280526090 cites W3131866082 @default.
• W4280526090 cites W3158879875 @default.
• W4280526090 cites W3165884139 @default.
• W4280526090 cites W3166728591 @default.
• W4280526090 cites W3169729808 @default.
• W4280526090 cites W3172874036 @default.
• W4280526090 cites W3181345005 @default.
• W4280526090 cites W3195009086 @default.
• W4280526090 cites W3198897197 @default.
• W4280526090 cites W3200146053 @default.
• W4280526090 cites W3201057920 @default.
• W4280526090 cites W3202907092 @default.
• W4280526090 cites W3207465626 @default.
• W4280526090 cites W3211130117 @default.
• W4280526090 cites W3211817439 @default.
• W4280526090 cites W4205903114 @default.
• W4280526090 cites W4205927695 @default.
• W4280526090 cites W4210283068 @default.
• W4280526090 cites W4210519626 @default.
• W4280526090 cites W4211228564 @default.
• W4280526090 cites W4214611286 @default.
• W4280526090 cites W4220752092 @default.
• W4280526090 cites W4220913442 @default.
• W4280526090 cites W4223453160 @default.
• W4280526090 cites W4280521364 @default.
• W4280526090 cites W639708223 @default.
• W4280526090 doi "https://doi.org/10.3389/fnbot.2022.881021" @default.
• W4280526090 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35663726" @default.
• W4280526090 hasPublicationYear "2022" @default.
• W4280526090 type Work @default.
• W4280526090 citedByCount "52" @default.
• W4280526090 countsByYear W42805260902022 @default.
• W4280526090 countsByYear W42805260902023 @default.
• W4280526090 crossrefType "journal-article" @default.
• W4280526090 hasAuthorship W4280526090A5006580423 @default.
• W4280526090 hasAuthorship W4280526090A5014508923 @default.
• W4280526090 hasAuthorship W4280526090A5016257935 @default.
• W4280526090 hasAuthorship W4280526090A5035701991 @default.
• W4280526090 hasAuthorship W4280526090A5042016865 @default.
• W4280526090 hasAuthorship W4280526090A5055545502 @default.
• W4280526090 hasAuthorship W4280526090A5063035156 @default.
• W4280526090 hasAuthorship W4280526090A5064548129 @default.

• next