High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2

The combination of gesture recognition and aerospace exploration robots can realize the efficient non-contact control of the robots. In the harsh aerospace environment, the captured gesture images are usually blurred and damaged inevitably. The motion blurred images not only cause part of the transm...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongchao Zhuang, Yilu Xia, Ning Wang, Lei Dong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	gesture recognition YOLOv4 CBAM deep learning image blur restoration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/0946b84efb9c4529824b1fb1dfc58d9d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0946b84efb9c4529824b1fb1dfc58d9d
record_format	dspace
spelling	oai:doaj.org-article:0946b84efb9c4529824b1fb1dfc58d9d2021-11-11T15:04:07ZHigh Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv210.3390/app112199822076-3417https://doaj.org/article/0946b84efb9c4529824b1fb1dfc58d9d2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9982https://doaj.org/toc/2076-3417The combination of gesture recognition and aerospace exploration robots can realize the efficient non-contact control of the robots. In the harsh aerospace environment, the captured gesture images are usually blurred and damaged inevitably. The motion blurred images not only cause part of the transmitted information to be lost, but also affect the effect of neural network training in the later stage. To improve the speed and accuracy of motion blurred gestures recognition, the algorithm of YOLOv4 (You Only Look Once, vision 4) is studied from the two aspects of motion blurred image processing and model optimization. The DeblurGanv2 is employed to remove the motion blur of the gestures in YOLOv4 network input pictures. In terms of model structure, the K-means++ algorithm is used to cluster the priori boxes for obtaining the more appropriate size parameters of the priori boxes. The CBAM attention mechanism and SPP (spatial pyramid pooling layer) structure are added to YOLOv4 model to improve the efficiency of network learning. The dataset for network training is designed for the human–computer interaction in the aerospace space. To reduce the redundant features of the captured images and enhance the effect of model training, the Wiener filter and bilateral filter are superimposed on the blurred images in the dataset to simply remove the motion blur. The augmentation of the model is executed by imitating different environments. A YOLOv4-gesture model is built, which collaborates with K-means++ algorithm, the CBAM and SPP mechanism. A DeblurGanv2 model is built to process the input images of the YOLOv4 target recognition. The YOLOv4-motion-blur-gesture model is composed of the YOLOv4-gesture and the DeblurGanv2. The augmented and enhanced gesture data set is used to simulate the model training. The experimental results demonstrate that the YOLOv4-motion-blur-gesture model has relatively better performance. The proposed model has the high inclusiveness and accuracy recognition effect in the real-time interaction of motion blur gestures, it improves the network training speed by 30%, the target detection accuracy by 10%, and the value of mAP by about 10%. The constructed YOLOv4-motion-blur-gesture model has a stable performance. It can not only meet the real-time human–computer interaction in aerospace space under real-time complex conditions, but also can be applied to other application environments under complex backgrounds requiring real-time detection.Hongchao ZhuangYilu XiaNing WangLei DongMDPI AGarticlegesture recognitionYOLOv4CBAMdeep learningimage blur restorationTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9982, p 9982 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	gesture recognition YOLOv4 CBAM deep learning image blur restoration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	gesture recognition YOLOv4 CBAM deep learning image blur restoration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hongchao Zhuang Yilu Xia Ning Wang Lei Dong High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
description	The combination of gesture recognition and aerospace exploration robots can realize the efficient non-contact control of the robots. In the harsh aerospace environment, the captured gesture images are usually blurred and damaged inevitably. The motion blurred images not only cause part of the transmitted information to be lost, but also affect the effect of neural network training in the later stage. To improve the speed and accuracy of motion blurred gestures recognition, the algorithm of YOLOv4 (You Only Look Once, vision 4) is studied from the two aspects of motion blurred image processing and model optimization. The DeblurGanv2 is employed to remove the motion blur of the gestures in YOLOv4 network input pictures. In terms of model structure, the K-means++ algorithm is used to cluster the priori boxes for obtaining the more appropriate size parameters of the priori boxes. The CBAM attention mechanism and SPP (spatial pyramid pooling layer) structure are added to YOLOv4 model to improve the efficiency of network learning. The dataset for network training is designed for the human–computer interaction in the aerospace space. To reduce the redundant features of the captured images and enhance the effect of model training, the Wiener filter and bilateral filter are superimposed on the blurred images in the dataset to simply remove the motion blur. The augmentation of the model is executed by imitating different environments. A YOLOv4-gesture model is built, which collaborates with K-means++ algorithm, the CBAM and SPP mechanism. A DeblurGanv2 model is built to process the input images of the YOLOv4 target recognition. The YOLOv4-motion-blur-gesture model is composed of the YOLOv4-gesture and the DeblurGanv2. The augmented and enhanced gesture data set is used to simulate the model training. The experimental results demonstrate that the YOLOv4-motion-blur-gesture model has relatively better performance. The proposed model has the high inclusiveness and accuracy recognition effect in the real-time interaction of motion blur gestures, it improves the network training speed by 30%, the target detection accuracy by 10%, and the value of mAP by about 10%. The constructed YOLOv4-motion-blur-gesture model has a stable performance. It can not only meet the real-time human–computer interaction in aerospace space under real-time complex conditions, but also can be applied to other application environments under complex backgrounds requiring real-time detection.
format	article
author	Hongchao Zhuang Yilu Xia Ning Wang Lei Dong
author_facet	Hongchao Zhuang Yilu Xia Ning Wang Lei Dong
author_sort	Hongchao Zhuang
title	High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
title_short	High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
title_full	High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
title_fullStr	High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
title_full_unstemmed	High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2
title_sort	high inclusiveness and accuracy motion blur real-time gesture recognition based on yolov4 model combined attention mechanism and deblurganv2
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0946b84efb9c4529824b1fb1dfc58d9d
work_keys_str_mv	AT hongchaozhuang highinclusivenessandaccuracymotionblurrealtimegesturerecognitionbasedonyolov4modelcombinedattentionmechanismanddeblurganv2 AT yiluxia highinclusivenessandaccuracymotionblurrealtimegesturerecognitionbasedonyolov4modelcombinedattentionmechanismanddeblurganv2 AT ningwang highinclusivenessandaccuracymotionblurrealtimegesturerecognitionbasedonyolov4modelcombinedattentionmechanismanddeblurganv2 AT leidong highinclusivenessandaccuracymotionblurrealtimegesturerecognitionbasedonyolov4modelcombinedattentionmechanismanddeblurganv2
_version_	1718437097464922112

High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2

Ejemplares similares