Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386768907> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386768907 endingPage "18" @default.
- W4386768907 startingPage "1" @default.
- W4386768907 abstract "The detection and identification of individual cattle plays an integral role in precision feeding and insurance claims, among others. Most current research is based on high-performance computing devices, which limits the application of deep learning techniques to mobile terminals. To this end, in this paper, we propose a channel-pruned YOLOv5 network-based method for cattle face detection on mobile terminals, referred to as NS-YOLO. First, the original model is sparsely trained and a sparse regularization penalty term is applied to the BN layers, then the corresponding mask values are labeled according to different weight thresholds, and the channels are pruned with global thresholds. Second, the detection precision is recovered by fine-tuning the model. Finally, the NCNN forward inference framework is used to quantize the model and an Android-based cattle face detection application is developed. Experimental results show that the model size, number of parameters and FLOPs are reduced by 86.10%, 88.19% and 63.25%, respectively, and the inference time is reduced by 35.53% compared to the original model, while mAP0.5 is reduced by only 1.6%. In particular, the 16-bit quantized model reduces the model size by 93.97% and the inference time by 34.97% compared to the original model on the mobile side. The results show that the proposed method can be easily deployed in resource-constrained mobile devices and has great advantages in practical engineering applications." @default.
- W4386768907 created "2023-09-16" @default.
- W4386768907 creator A5025918703 @default.
- W4386768907 creator A5067911220 @default.
- W4386768907 creator A5072833759 @default.
- W4386768907 date "2023-09-13" @default.
- W4386768907 modified "2023-09-26" @default.
- W4386768907 title "Cattle face detection method based on channel pruning YOLOv5 network and mobile deployment" @default.
- W4386768907 cites W1545789497 @default.
- W4386768907 cites W1974577935 @default.
- W4386768907 cites W2055781575 @default.
- W4386768907 cites W2110823168 @default.
- W4386768907 cites W2154183834 @default.
- W4386768907 cites W2318391375 @default.
- W4386768907 cites W2781155685 @default.
- W4386768907 cites W2884306088 @default.
- W4386768907 cites W3017357154 @default.
- W4386768907 cites W3176631406 @default.
- W4386768907 cites W3208737656 @default.
- W4386768907 cites W4200090587 @default.
- W4386768907 cites W4220908486 @default.
- W4386768907 cites W4281623363 @default.
- W4386768907 cites W4283697105 @default.
- W4386768907 cites W4293103565 @default.
- W4386768907 cites W4294133279 @default.
- W4386768907 cites W4308522431 @default.
- W4386768907 cites W4309461062 @default.
- W4386768907 doi "https://doi.org/10.3233/jifs-232213" @default.
- W4386768907 hasPublicationYear "2023" @default.
- W4386768907 type Work @default.
- W4386768907 citedByCount "0" @default.
- W4386768907 crossrefType "journal-article" @default.
- W4386768907 hasAuthorship W4386768907A5025918703 @default.
- W4386768907 hasAuthorship W4386768907A5067911220 @default.
- W4386768907 hasAuthorship W4386768907A5072833759 @default.
- W4386768907 hasConcept C108583219 @default.
- W4386768907 hasConcept C111919701 @default.
- W4386768907 hasConcept C11413529 @default.
- W4386768907 hasConcept C119857082 @default.
- W4386768907 hasConcept C127162648 @default.
- W4386768907 hasConcept C144024400 @default.
- W4386768907 hasConcept C153180895 @default.
- W4386768907 hasConcept C154945302 @default.
- W4386768907 hasConcept C186967261 @default.
- W4386768907 hasConcept C2776135515 @default.
- W4386768907 hasConcept C2776214188 @default.
- W4386768907 hasConcept C2779304628 @default.
- W4386768907 hasConcept C36289849 @default.
- W4386768907 hasConcept C41008148 @default.
- W4386768907 hasConcept C76155785 @default.
- W4386768907 hasConceptScore W4386768907C108583219 @default.
- W4386768907 hasConceptScore W4386768907C111919701 @default.
- W4386768907 hasConceptScore W4386768907C11413529 @default.
- W4386768907 hasConceptScore W4386768907C119857082 @default.
- W4386768907 hasConceptScore W4386768907C127162648 @default.
- W4386768907 hasConceptScore W4386768907C144024400 @default.
- W4386768907 hasConceptScore W4386768907C153180895 @default.
- W4386768907 hasConceptScore W4386768907C154945302 @default.
- W4386768907 hasConceptScore W4386768907C186967261 @default.
- W4386768907 hasConceptScore W4386768907C2776135515 @default.
- W4386768907 hasConceptScore W4386768907C2776214188 @default.
- W4386768907 hasConceptScore W4386768907C2779304628 @default.
- W4386768907 hasConceptScore W4386768907C36289849 @default.
- W4386768907 hasConceptScore W4386768907C41008148 @default.
- W4386768907 hasConceptScore W4386768907C76155785 @default.
- W4386768907 hasLocation W43867689071 @default.
- W4386768907 hasOpenAccess W4386768907 @default.
- W4386768907 hasPrimaryLocation W43867689071 @default.
- W4386768907 hasRelatedWork W2795261237 @default.
- W4386768907 hasRelatedWork W3014300295 @default.
- W4386768907 hasRelatedWork W3164822677 @default.
- W4386768907 hasRelatedWork W4223943233 @default.
- W4386768907 hasRelatedWork W4225161397 @default.
- W4386768907 hasRelatedWork W4312200629 @default.
- W4386768907 hasRelatedWork W4360585206 @default.
- W4386768907 hasRelatedWork W4364306694 @default.
- W4386768907 hasRelatedWork W4380075502 @default.
- W4386768907 hasRelatedWork W4380086463 @default.
- W4386768907 isParatext "false" @default.
- W4386768907 isRetracted "false" @default.
- W4386768907 workType "article" @default.