FM‐YOLOv8:Lightweight gesture recognition algorithm
Abstract In practical production applications, the efficiency and success rate of gesture recognition directly affect the user experience and work efficiency. However, the existing gesture recognition models have the problem of a large number of model parameters and high computational complexity, wh...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-11-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.13229 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846169301730459648 |
|---|---|
| author | Fanghai Li Xitai Na Jinshuo Shi Qingbin Sun |
| author_facet | Fanghai Li Xitai Na Jinshuo Shi Qingbin Sun |
| author_sort | Fanghai Li |
| collection | DOAJ |
| description | Abstract In practical production applications, the efficiency and success rate of gesture recognition directly affect the user experience and work efficiency. However, the existing gesture recognition models have the problem of a large number of model parameters and high computational complexity, which makes them unable to meet the needs of end‐to‐end industrial deployment. To solve these problems, this article proposes a gesture recognition model based on YOLOv8. First, FasterNet is adopted as the backbone of YOLOv8, which significantlydecrease the number of parameters and made the model more lightweight. By reducing the number of parameters, the computational complexity of the model can be reduced while maintaining the performance of the model, and the operation efficiency of the model can be improved. Second, recombination convolution ScConv is introduced to replace common convolution operations to further improve the model's efficiency. Recombination convolution can reduce the computation and make up for the loss of precision to some extent. Finally, the MDPIoU loss function is used to optimize target location and prediction, to improve the accuracy of the model. The MDPIoU loss function can better deal with the problem of target boundary frame positioning and prediction so that the model can locate and predict gestures more accurately in gesture recognition tasks. Experiments on a data set containing 10 types of gestures show that the number of parameters and floating point calculations of the improved network model are reduced by 45% and 42.7%, respectively, while the accuracy is unchanged. The improved model can be deployed on edge terminals, providing efficient and accurate gesture recognition. |
| format | Article |
| id | doaj-art-df741cb7a4554906b325e7f7efa96ec5 |
| institution | Kabale University |
| issn | 1751-9659 1751-9667 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj-art-df741cb7a4554906b325e7f7efa96ec52024-11-13T04:42:31ZengWileyIET Image Processing1751-96591751-96672024-11-0118134023403110.1049/ipr2.13229FM‐YOLOv8:Lightweight gesture recognition algorithmFanghai Li0Xitai Na1Jinshuo Shi2Qingbin Sun3Electronic Information Engineering Inner Mongolia University Hohhot ChinaElectronic Information Engineering Inner Mongolia University Hohhot ChinaElectronic Information Engineering Inner Mongolia University Hohhot ChinaElectronic Information Engineering Inner Mongolia University Hohhot ChinaAbstract In practical production applications, the efficiency and success rate of gesture recognition directly affect the user experience and work efficiency. However, the existing gesture recognition models have the problem of a large number of model parameters and high computational complexity, which makes them unable to meet the needs of end‐to‐end industrial deployment. To solve these problems, this article proposes a gesture recognition model based on YOLOv8. First, FasterNet is adopted as the backbone of YOLOv8, which significantlydecrease the number of parameters and made the model more lightweight. By reducing the number of parameters, the computational complexity of the model can be reduced while maintaining the performance of the model, and the operation efficiency of the model can be improved. Second, recombination convolution ScConv is introduced to replace common convolution operations to further improve the model's efficiency. Recombination convolution can reduce the computation and make up for the loss of precision to some extent. Finally, the MDPIoU loss function is used to optimize target location and prediction, to improve the accuracy of the model. The MDPIoU loss function can better deal with the problem of target boundary frame positioning and prediction so that the model can locate and predict gestures more accurately in gesture recognition tasks. Experiments on a data set containing 10 types of gestures show that the number of parameters and floating point calculations of the improved network model are reduced by 45% and 42.7%, respectively, while the accuracy is unchanged. The improved model can be deployed on edge terminals, providing efficient and accurate gesture recognition.https://doi.org/10.1049/ipr2.13229gesture recognitionobject detectionlightweight modelYOLOv8 |
| spellingShingle | Fanghai Li Xitai Na Jinshuo Shi Qingbin Sun FM‐YOLOv8:Lightweight gesture recognition algorithm IET Image Processing gesture recognition object detection lightweight model YOLOv8 |
| title | FM‐YOLOv8:Lightweight gesture recognition algorithm |
| title_full | FM‐YOLOv8:Lightweight gesture recognition algorithm |
| title_fullStr | FM‐YOLOv8:Lightweight gesture recognition algorithm |
| title_full_unstemmed | FM‐YOLOv8:Lightweight gesture recognition algorithm |
| title_short | FM‐YOLOv8:Lightweight gesture recognition algorithm |
| title_sort | fm yolov8 lightweight gesture recognition algorithm |
| topic | gesture recognition object detection lightweight model YOLOv8 |
| url | https://doi.org/10.1049/ipr2.13229 |
| work_keys_str_mv | AT fanghaili fmyolov8lightweightgesturerecognitionalgorithm AT xitaina fmyolov8lightweightgesturerecognitionalgorithm AT jinshuoshi fmyolov8lightweightgesturerecognitionalgorithm AT qingbinsun fmyolov8lightweightgesturerecognitionalgorithm |