摘要
针对当前手势识别算法易受光线变化、复杂场景等干扰,从而导致手势识别准确性下降的问题,定义了一种体感控制与深度相机的手势识别算法。所提出的手势识别方法结合了体感控制(Leap Motion)传感器和Kinect深度传感器,可以有效提高手势识别精度与鲁棒性。通过体感控制传感器提取指尖与手的质心距离、指尖与手掌平面的高度、指尖与手掌中心的角度,以及指尖在手参照系统中的3D位置;通过Kinect深度传感器来提取手指样本与手部中心的距离、手部轮廓的局部曲率、手部形状的连通区域以及距离特征之间的相似性;为了结合两种不同传感器数据的互补信息,摒弃冗余,通过采集的指尖3D位置,找到旋转平移参数,以最小化所有采集帧中指尖点的平均投影误差来定义一种联合校准方法,确定体感控制传感器和Kinect深度传感器的外部参数,完成两种传感器坐标转换;采用支持向量机(SVM)进行分类学习,完成手势识别任务。实验表明:相对于已有的手势识别算法,所提算法不仅在Jochen.Triesch手势数据库中具有更高的平均识别率,约为97%,而且在不同光线、不同肤色和背景的复杂环境下,其同样具有更高的准确率与稳健性。
Aiming at the situation of occlusion,light change and complex scenes in current gesture recognition,which easily leads to the decline of the accuracy of gesture recognition,a gesture recognition scheme based on the coupled depth camera of somatosensory control is proposed.In order to improve the accuracy of gesture recognition,the proposed gesture recognition scheme includes Leap Motion data and Kinect depth data.Firstly,the distance between the fingertip and the center of mass of the hand,the height between the fingertip and the palm plane,the angle between the fingertip and the center of the palm,and the 3 D position of the fingertip in the hand reference system are extracted from the somatosensory control data.Then,the distance between the finger sample and the center of the hand,the local curvature of the hand contour,the similarity between the distance features and the connected area of the hand shape are extracted from the Kinect depth data.Then,in order to combine the complementary information of two kinds of sensor data and discard redundancy,ajoint calibration method is defined by finding the rotation and translation parameters through the 3Dposition of fingertips collected,and minimizing the average re-projection error of all fingertips in all acquisition frames,determine the external parameters of the somatosensory control sensor and the Kinect depth sensor,and complete the coordinate conversion of the two sensors.Finally,a classification learning method based on multi-class Support Vector Machine(SVM)is proposed.Experiments show that the average recognition rate of Jochen Triesch gesture database is 97%.In different light,skin color and background environments,The proposed algorithm has higher accuracy and robustness than the existing hand gesture recognition algorithms.
作者
龚茜茹
俞惠芳
GONG Qianru;YU Huifang(School of Electronic Information Engineering,Henan Polytechnic Institute,Nanyang 473009,China;School of Cyberspace Science and Technology,Xi’an University of Posts&Telecommunications,Xi'an 710121,China)
出处
《光学技术》
CAS
CSCD
北大核心
2022年第3期341-349,共9页
Optical Technique
基金
国家自然科学基金资助项目(61363080,61772326)
河南省高等学校青年骨干教师培养计划子基金项目(2016GGJS-236)
河南省科技攻关计划基金项目(142102210556)
河南省科技攻关计划项目(142102210556)。
关键词
手势识别
体感控制
深度相机
联合校准
质心距离
平均投影误差
传感器坐标转换
SVM
gesture recognition
somatosensory control
depth camera
joint calibration
centroid distance
average projection error
sensor coordinate conversion
SVM