Real-time hand tracking based on YOLOV4 model and Kalman filter

被引：0

作者：

Xuwe D. ^{[1
]}

Dong C. ^{[1
]}

Huajiang L. ^{[1
]}

Zhaokun M. ^{[1
]}

Qianqian Y. ^{[1
]}

机构：

[1] School of Mechanical and Electrical Engineering, Qingdao University of Science and Technology, Qingdao

来源：

Journal of China Universities of Posts and Telecommunications | 2021年 / 28卷 / 03期

关键词：

Hand tracking; Kalman filter; Real-time; You Only Look Once version 4 (YOLOv4) model;

D O I：

10.19682/j.cnki.1005-8885.2021.0011

中图分类号：

学科分类号：

摘要：

Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4 (YOLOv4) model, a new YOLOv4 model combined with Kalman filter real-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network (CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43% at speed of 41.822 frame/ s, achieving superior results than other algorithms. © 2021, Beijing University of Posts and Telecommunications. All rights reserved.

引用

页码：86 / 94

页数：8

共 23 条

[1]

Ng C.W., Ranganath S., Real-time gesture recognition system and application, Image and Vision Computing, 20, 13-14, pp. 993-1007, (2002)

[2]

Kolahi A., Hoviattalab M., Rezaeian T., Et al., Design of a marker- based human motion tracking system, Biomedical Signal Processing and Control, 2, 1, pp. 59-67, (2007)

[3]

Kirk A.G., O'Brien J.F., Forsyth D.A., Skeletal parameter estimation from optical motion capture data, Computer Vision and Pattern Recognition, 2, 2, pp. 782-788, (2005)

[4]

Rosales R., Athitsos V., Sclaroff S., 3D hand pose reconstruction using specialized mappings, Proceedings of the 8Th IEEE International Conference on Computer Vision (ICCV-01): Vol 1, pp. 378-385, (2001)

[5]

Oikonomidis I., Kyriazis N., Argyros A.A., Efficient model-based 3D tracking of hand articulations using Kinect, Proceedings of the 22Nd British Machine Vision Conference (BMVC-11), pp. 1-11, (2011)

[6]

Xu C., Cheng L., Efficient hand pose estimation from a single depth image, Proceedings of the 14Th IEEE International Conference on Computer Vision, pp. 3456-3462, (2013)

[7]

Keskin C., Klrac F., Kara Y.E., Et al., Real time hand pose estimation using depth sensors, Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops-11), pp. 1228-1234, (2011)

[8]

Huang X., An adaptive KLT algorithm for hand gesture tracking, Advanced Materials Research, 706, 707, pp. 623-628, (2013)

[9]

Bhuyan M.K., Ghosh D., Bora P.K., Hand motion tracking and trajectory matching for dynamic hand gesture recognition, Journal of Experimental & Theoretical Artificial Intelligence, 18, 4, pp. 435-447, (2006)

[10]

Asaari M., Rosdi B.A., Azmin S.A., Adaptive Kalman filter incorporated eigenhand (AKFIE) for real-time hand tracking system, Multimedia Tools and Applications, 74, pp. 9231-9257, (2015)

← 1 2 3 →