FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215087236> ?p ?o ?g. }

• W3215087236 endingPage "247" @default.
• W3215087236 startingPage "239" @default.
• W3215087236 abstract "To realize rapid and accurate ripeness detection for walnut on mobile terminals such as mobile phones, we propose a method based on coupling information and lightweight YOLOv4. First, we collected 50 walnuts at each ripeness (Unripe, Mid-ripe, Ripe, Over-ripe) to determine the kernel oil content. Pearson correlation analysis and one-way analysis of variance (ANOVA) prove that the division of walnut ripeness reflects the change in kernel oil content. It is feasible to estimate the kernel oil content by detecting the ripeness of walnut. Next, we achieve ripeness detection based on lightweight YOLOv4. We adopt MobileNetV3 as the backbone feature extractor and adopt depthwise separable convolution to replace the traditional convolution. We design a parallel convolution structure with depthwise convolution stacking (PCSDCS) to reduce parameters and improve feature extraction ability. To enhance the model’s detection ability for walnuts in the growth-intensive areas, we design a Gaussian Soft DIoU non-maximum suppression (GSDIoU-NMS) algorithm. The dataset used for model optimization contains 3600 images, of which 2880 images in the training set, 320 images in the validation set, and 400 images in the test set. We adopt a multi-training strategy based on dynamic learning rate and transfer learning to get training weights. The lightweight YOLOv4 model achieves 94.05%, 90.72%, 88.30%, 76.92 FPS, and 38.14 MB in mean average precision, precision, recall, average detection speed, and weight capacity, respectively. Compared with the Faster R-CNN model, EfficientDet-D1 model, YOLOv3 model, and YOLOv4 model, the lightweight YOLOv4 model improves 8.77%, 4.84%, 5.43%, and 0.06% in mean average precision, 74.60 FPS, 55.60 FPS, 38.83 FPS, and 46.63 FPS in detection speed, respectively. And the lightweight YOLOv4 is 84.4% smaller than the original YOLOv4 model in terms of weight capacity. This paper provides a theoretical reference for the rapid ripeness detection of walnut and exploration for the model’s lightweight." @default.
• W3215087236 created "2021-12-06" @default.
• W3215087236 creator A5042293116 @default.
• W3215087236 creator A5054709496 @default.
• W3215087236 creator A5074252639 @default.
• W3215087236 creator A5091046952 @default.
• W3215087236 date "2022-01-10" @default.
• W3215087236 modified "2023-10-18" @default.
• W3215087236 title "Walnut Ripeness Detection Based on Coupling Information and Lightweight YOLOv4" @default.
• W3215087236 cites W1190895727 @default.
• W3215087236 cites W1467531035 @default.
• W3215087236 cites W1979193967 @default.
• W3215087236 cites W2034229179 @default.
• W3215087236 cites W2137766719 @default.
• W3215087236 cites W2531409750 @default.
• W3215087236 cites W2561037067 @default.
• W3215087236 cites W2588360888 @default.
• W3215087236 cites W2729298216 @default.
• W3215087236 cites W2781900944 @default.
• W3215087236 cites W2893752867 @default.
• W3215087236 cites W2907569541 @default.
• W3215087236 cites W2943687951 @default.
• W3215087236 cites W2954789679 @default.
• W3215087236 cites W2963163009 @default.
• W3215087236 cites W2964121718 @default.
• W3215087236 cites W2981577068 @default.
• W3215087236 cites W2982083293 @default.
• W3215087236 cites W3002834176 @default.
• W3215087236 cites W3003833940 @default.
• W3215087236 cites W3018297536 @default.
• W3215087236 cites W3022796210 @default.
• W3215087236 cites W3042556338 @default.
• W3215087236 cites W3042923411 @default.
• W3215087236 cites W3105147399 @default.
• W3215087236 cites W3107561053 @default.
• W3215087236 cites W3118868152 @default.
• W3215087236 cites W3126185293 @default.
• W3215087236 cites W3128414507 @default.
• W3215087236 cites W3131397654 @default.
• W3215087236 cites W3135145061 @default.
• W3215087236 cites W3174422331 @default.
• W3215087236 cites W3180134609 @default.
• W3215087236 doi "https://doi.org/10.46300/9106.2022.16.29" @default.
• W3215087236 hasPublicationYear "2022" @default.
• W3215087236 type Work @default.
• W3215087236 sameAs 3215087236 @default.
• W3215087236 citedByCount "1" @default.
• W3215087236 countsByYear W32150872362023 @default.
• W3215087236 crossrefType "journal-article" @default.
• W3215087236 hasAuthorship W3215087236A5042293116 @default.
• W3215087236 hasAuthorship W3215087236A5054709496 @default.
• W3215087236 hasAuthorship W3215087236A5074252639 @default.
• W3215087236 hasAuthorship W3215087236A5091046952 @default.
• W3215087236 hasBestOaLocation W32150872361 @default.
• W3215087236 hasConcept C114614502 @default.
• W3215087236 hasConcept C138885662 @default.
• W3215087236 hasConcept C153180895 @default.
• W3215087236 hasConcept C154945302 @default.
• W3215087236 hasConcept C172353545 @default.
• W3215087236 hasConcept C177264268 @default.
• W3215087236 hasConcept C185592680 @default.
• W3215087236 hasConcept C199360897 @default.
• W3215087236 hasConcept C2776401178 @default.
• W3215087236 hasConcept C2780393073 @default.
• W3215087236 hasConcept C31903555 @default.
• W3215087236 hasConcept C33923547 @default.
• W3215087236 hasConcept C41008148 @default.
• W3215087236 hasConcept C41895202 @default.
• W3215087236 hasConcept C45347329 @default.
• W3215087236 hasConcept C50644808 @default.
• W3215087236 hasConcept C52622490 @default.
• W3215087236 hasConcept C74193536 @default.
• W3215087236 hasConcept C81363708 @default.
• W3215087236 hasConceptScore W3215087236C114614502 @default.
• W3215087236 hasConceptScore W3215087236C138885662 @default.
• W3215087236 hasConceptScore W3215087236C153180895 @default.
• W3215087236 hasConceptScore W3215087236C154945302 @default.
• W3215087236 hasConceptScore W3215087236C172353545 @default.
• W3215087236 hasConceptScore W3215087236C177264268 @default.
• W3215087236 hasConceptScore W3215087236C185592680 @default.
• W3215087236 hasConceptScore W3215087236C199360897 @default.
• W3215087236 hasConceptScore W3215087236C2776401178 @default.
• W3215087236 hasConceptScore W3215087236C2780393073 @default.
• W3215087236 hasConceptScore W3215087236C31903555 @default.
• W3215087236 hasConceptScore W3215087236C33923547 @default.
• W3215087236 hasConceptScore W3215087236C41008148 @default.
• W3215087236 hasConceptScore W3215087236C41895202 @default.
• W3215087236 hasConceptScore W3215087236C45347329 @default.
• W3215087236 hasConceptScore W3215087236C50644808 @default.
• W3215087236 hasConceptScore W3215087236C52622490 @default.
• W3215087236 hasConceptScore W3215087236C74193536 @default.
• W3215087236 hasConceptScore W3215087236C81363708 @default.
• W3215087236 hasLocation W32150872361 @default.
• W3215087236 hasOpenAccess W3215087236 @default.
• W3215087236 hasPrimaryLocation W32150872361 @default.
• W3215087236 hasRelatedWork W2146076056 @default.
• W3215087236 hasRelatedWork W2295021132 @default.
• W3215087236 hasRelatedWork W2546942002 @default.

• next