[1]丁 驰,林 军,游 俊,等.基于深度学习的手势识别方法[J].控制与信息技术,2018,(06):96-99.[doi:10.13889/j.issn.2096-5427.2018.06.016]
 DING Chi,LIN Jun,YOU Jun,et al.A Gesture Recognition Method Based on Deep Learning[J].High Power Converter Technology,2018,(06):96-99.[doi:10.13889/j.issn.2096-5427.2018.06.016]
点击复制

基于深度学习的手势识别方法()
分享到:

《控制与信息技术》[ISSN:2095-3631/CN:43-1486/U]

卷:
期数:
2018年06期
页码:
96-99
栏目:
人工智能技术与应用
出版日期:
2018-12-05

文章信息/Info

Title:
A Gesture Recognition Method Based on Deep Learning
文章编号:
2096-5427(2018)06-0096-04
作者:
丁 驰林 军游 俊袁 浩
(中车株洲所电气技术与材料工程研究院,湖南 株洲 412001)
Author(s):
DING ChiLIN Jun YOU JunYUAN Hao
( CRRC ZIC Research Institute of Electrical Technology & Material Engineering, Zhuzhou, Hunan 412001, China )
关键词:
深度学习卷积神经网络目标检测手势识别
Keywords:
deep learning convolutional neural networks object detection gesture recognition
分类号:
TP391.41
DOI:
10.13889/j.issn.2096-5427.2018.06.016
文献标志码:
A
摘要:
为了提高视频手势识别的准确率与鲁棒性,更好地利用不同深度神经网络的优势,文章提出一种集成多种卷积神经网络的手势识别方法。其利用基于SSD架构的深度卷积神经网络进行多尺度的人手目标检测,通过将多个预选框与画面中存在的各个不同大小的人手标定选框进行匹配筛选,以获取图像中所有人手的精确位置并返回位置坐标向量;采用基于Multiview Bootstrapping方法的卷积神经网络,通过多视角引导对二维输入图像实现复杂环境下的手势关键点检测;将几种常用的手势进行定义并建立手势分类模型,基于前一步获得的手势关键点特征进行手势分类。实验结果表明,该方法对于复杂环境下不同类型的手势识别都具有较好的准确率和鲁棒性。
Abstract:
In order to increase the accuracy and robustness of gesture recognition in video, and better utilize the advantages of different deep neural network architectures, it presented an approach to realize gesture recognition by combining multiple advanced convolutional neural network architectures. This method implements multi-scale human hand detection with a depth convolutional neural network based on the SSD architecture. Through matching and screening of multiple predictive boxes with different sizes ground truth boxes, it acquired the position of all hands in the input image and return the position coordinates. Then, another convolutional neural network based on Multiview Bootstrapping method was used to detect the hand key points from 2D images in complex environment through multiple perspectives. Finally, several common gestures were defined and a gesture classifier was established to classify the gestures based on the hand key point features. The experimental result shows that the proposed method is robust and accurate for different types of gestures in complex environment.

参考文献/References:

[1]胡有树.手势识别技术综述[J]. 中国科技信息,2005(2):42-43.
[2] 李清水,方志刚,沈模卫,等. 手势识别技术及其在人机交互中的应用[J]. 人类工效学,2002,8(1):27-29.
[3] WANG R Y . Real-time hand-tracking with a color glove[J]. Acm Transactions on Graphics, 2009, 28(3):1-8.
[4] PARK J, YOON Y P. LED-Glove based interactions in multimodal displays for teleconferencing[C]// Proceedings of the 16th International Conference on Artificial Reality and Telexistence – Workshops. Washington D C: IEEE Computer Society Press, 2006:395-399 [5] STURMAN D J, ZELTZER D. A survey of glove-based input[J]. IEEE Computer Graphics and Applications, 1994, 14(1):30-39.
[6] PATLLOA C, MAHOTRA S, KEHTARNAVAZ N. Real-time hand-pair gesture recognition using a stereo webcam[C]//Proceedings of IEEE International Conference on Emerging Signal Processing Applications. Piscataway: IEEE Computer Society Press, 2012:135-138. [7] CHAI X J, FANG Y K, WANG K Q. Robust hand gesture analysis and application in gallery browsing[C]//Proceedings of IEEE International Conference on Multimedia and Expo. Piscataway:IEEE Computer Society Press, 2009:938-941.
[8] YAO Y, FU Y. Real-time hand pose estimation from RGB-D sensor[C]//Proceedings of IEEE International Conference on Multimedia and Expo. Australia:IEEE Computer Society Press, 2012:705-710.
[9]HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[10]刘蓉,刘明.基于三轴加速度传感器的手势识别[J].计算机工程,2011, 37(24):141-143.
 LIU R,LIU M.Gesture Recognition Based on Three-axial Accelerometer[J].Computer Engineering,2011, 37(24):141-143.
[11]SUPANCIC J S, ROGEZ G, YANG Y, et al. Depth-Based Hand Pose Estimation: Data, Methods, and Challenges[C]// IEEE International Conference on Computer Vision. Chile:IEEE Computer Society, 2015:1868-1876.
[12]QIAN C, SUN X, WEI Y, et al. Realtime and Robust Hand Tracking from Depth[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). USA :IEEE Computer Society, 2014:1106-1113.
[13]SRIDHAR S, OULASVIRTA A, THEOBALT C. Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data[C]// IEEE International Conference on Computer Vision. Australia:IEEE Computer Society, 2013:2456-2463.
[14]XU C , CHENG L . Efficient Hand Pose Estimation from a Single Depth Image[C]// IEEE International Conference on Computer Vision. Australia :IEEE, 2013:3456-3462.
[15]OIKONOMIDIS I. Tracking the articulated motion of two strongly interacting hands[C]// IEEE Conference on Computer Vision and Pattern Recognition. USA :IEEE Computer Society, 2012:1862-1869.
[16]BALLAN L, TANEJA A, GOOL L V, et al. Motion capture of hands in action using discriminative salient points[C]// European Conference on Computer Vision. S.l. Springer-Verlag, 2012:640-653.
[17]LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multibox Detector[C]// European Conference on computer vision (ECCV),2016:21-37.
[18]MITTAL A, ZISSERMAN A, TORR P H S. Hand detection using multiple proposals[C]// British Machine Vision Conference, 2011.
[19]SIMON T, JOO H, MATTHEWS I, et al. Hand Keypoint Detection in Single Images Using Multiview Bootstrapping[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).USA :IEEE,2017, 2(3):4645-4653.

相似文献/References:

[1]熊群芳,林 军,刘 悦,等.深度学习研究现状及其在轨道交通领域的应用[J].控制与信息技术,2018,(02):1.[doi:10.13889/j.issn.2096-5427.2018.02.001]
 XIONG Qunfang,LIN Jun,LIU Yue,et al.Deep Learning and Its Application in the Field of Rail Transit[J].High Power Converter Technology,2018,(06):1.[doi:10.13889/j.issn.2096-5427.2018.02.001]
[2]刘 悦,林 军,游 俊.语音识别技术在车载领域的应用及发展[J].控制与信息技术,2019,(02):1.[doi:10.13889/j.issn.2096-5427.2019.02.001]
 LIU Yue,LIN Jun,YOU Jun.Application and Development of Automatic Speech Recognition in Vehicle Field[J].High Power Converter Technology,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.02.001]
[3]高 群,朱 均,王芊芊,等. 基于鱼眼图像的目标检测算法研究[J].控制与信息技术,2019,(03):1.[doi:10.13889/j.issn.2096-5427.2019.03.100]
 GAO Qun,ZHU Jun,WANG Qianqian,et al.Research on the Object Detection Algorithm Based on Fisheye Image[J].High Power Converter Technology,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.03.100]
[4]高 群,朱 均,王芊芊,等.基于鱼眼图像的目标检测算法研究[J].控制与信息技术,2019,(03):43.[doi:10.13889/j.issn.2096-5427.2019.03.100]
 GAO Qun,ZHU Jun,WANG Qianqian,et al.Research on the Object Detection Algorithm Based on Fisheye Image[J].High Power Converter Technology,2019,(06):43.[doi:10.13889/j.issn.2096-5427.2019.03.100]
[5]齐 航,袁健全,李 磊,等. 基于深度学习的红外烟幕区域分割技术[J].控制与信息技术,2019,(04):1.[doi:10.13889/j.issn.2096-5427.2019.04.400]
 QI Hang,YUAN Jianquan,LI Lei,et al. A Method of Smoke Area Segmentation for Infrared Images Based on Deep Learning[J].High Power Converter Technology,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.04.400]
[6]齐 航,袁健全,李 磊,等.基于深度学习的红外烟幕区域分割技术[J].控制与信息技术,2019,(04):18.[doi:10.13889/j.issn.2096-5427.2019.04.400]
 QI Hang,YUAN Jianquan,LI Lei,et al.A Method of Smoke Area Segmentation for Infrared Images Based on Deep Learning[J].High Power Converter Technology,2019,(06):18.[doi:10.13889/j.issn.2096-5427.2019.04.400]
[7]王章骏,许 平,王春彭,等. 有限元位移解的生成式对抗网络替代方法[J].控制与信息技术,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.06.300]
 WANG Zhangjun,XU Ping,WANG Chunpeng,et al. A Generative Adversarial Network Approach to Estimate Finite Element Displacement[J].High Power Converter Technology,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.06.300]
[8]王章骏,许 平,王春彭,等.有限元位移解的生成式对抗网络替代方法[J].控制与信息技术,2019,(06):57.[doi:10.13889/j.issn.2096-5427.2019.06.300]
 WANG Zhangjun,XU Ping,WANG Chunpeng,et al.A Generative Adversarial Network Approach to EstimateFinite Element Displacement[J].High Power Converter Technology,2019,(06):57.[doi:10.13889/j.issn.2096-5427.2019.06.300]
[9]熊群芳,林 军,岳 伟,等. 基于深度学习的疲劳驾驶状态检测方法[J].控制与信息技术,2018,(06):1.[doi:10.13889/j.issn.2096-5427.2018.06.400]
 XIONG Qunfang,LIN Jun,YUE Wei,et al. A Method of Fatigue Driving State Detection Based on Deep Learning[J].High Power Converter Technology,2018,(06):1.[doi:10.13889/j.issn.2096-5427.2018.06.400]
[10]熊群芳,林 军,岳 伟.基于深度学习的疲劳驾驶状态检测方法[J].控制与信息技术,2018,(06):91.[doi:10.13889/j.issn.2096-5427.2018.06.400]
 XIONG Qunfang,LIN Jun,YUE Wei.A Method of Fatigue Driving State Detection Based on Deep Learning[J].High Power Converter Technology,2018,(06):91.[doi:10.13889/j.issn.2096-5427.2018.06.400]
[11]熊群芳,林 军,岳 伟,等. 基于深度学习的驾驶员打电话行为检测方法[J].控制与信息技术,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.06.400]
 XIONG Qunfang,LIN Jun,YUE Wei,et al. A Driver Calling Behavior Detection Method Based on Deep Learning[J].High Power Converter Technology,2019,(06):1.[doi:10.13889/j.issn.2096-5427.2019.06.400]
[12]熊群芳,林 军,岳 伟,等.基于深度学习的驾驶员打电话行为检测方法[J].控制与信息技术,2019,(06):53.[doi:10.13889/j.issn.2096-5427.2019.06.400]
 XIONG Qunfang,LIN Jun,YUE Wei,et al.A Driver’s Calling Behavior Detection Method Based on Deep Learning[J].High Power Converter Technology,2019,(06):53.[doi:10.13889/j.issn.2096-5427.2019.06.400]

备注/Memo

备注/Memo:
收稿日期:2018-10-31
作者简介:丁驰(1993—),女,硕士,主要从事基于深度学习的图像识别研究工作。
更新日期/Last Update: 2018-12-25