光学学报, 2017, 37 (1): 0115002, 网络出版: 2017-01-13
融合红外深度信息的视觉交互手部跟踪算法
Visually Interactive Hand Tracking Algorithm Combined with Infrared Depth Information
机器视觉 视觉跟踪 粒子滤波 人工蜂群算法 红外深度信息 梯度方向二值模式特征 machine vision visual tracking particle filtering artificial bee colony algorithm infrared depth information oriented gradient local binary pattern
摘要
在虚拟现实环境中手部跟踪是视觉交互系统的基础和核心。针对现有视觉跟踪方法在手部运动姿态、尺度变化及复杂背景条件下出现的稳健性等问题, 结合纹理和轮廓信息, 利用基于梯度方向局部二值模式特征为基础的粒子滤波跟踪算法, 建立局部和全局的特征直方图描述, 实现手部跟踪。针对粒子匮乏问题, 利用红外深度信息, 并引入基于群智能的人工蜂群算法, 将当前时刻的观测信息融合在粒子预测的采样和更新阶段, 高效完成目标的搜索和优化, 降低粒子集衰减程度, 改善状态估计精度。实验结果表明, 该方法在各种复杂背景下可以实现手部的稳健跟踪。
Abstract
Hand tracking is the basis and core problem of vision interaction in virtual reality. Due to the poor performance resulted from the existing hand tracking methods in the instances of movement, scale change, complex background, etc., a new hand tracking algorithm is presented. The proposed algorithm is under particle filtering and tracking framework, which adopts oriented gradient local binary pattern descriptor integrating with texture and contour information. Furthermore, the infrared depth information is introduced. The proposed tracking algorithm combines the observation information of current frame in the stages of particle sampling and updating by the artificial bee colony algorithm, which overcomes the degeneracy problem in particle filtering and improves hand tracking precision by optimization of the space search. Experimental results show that the proposed algorithm can achieve accurate and robust hand tracking in complex background.
孙瑾, 丁永晖, 周来. 融合红外深度信息的视觉交互手部跟踪算法[J]. 光学学报, 2017, 37(1): 0115002. Sun Jin, Ding Yonghui, Zhou Lai. Visually Interactive Hand Tracking Algorithm Combined with Infrared Depth Information[J]. Acta Optica Sinica, 2017, 37(1): 0115002.