【摘要】 为实现基于手势的智能人机交互,提出了一种基于视觉的人手跟踪与手势识别算法.该方法以ICON-DENSATION算法为基础,融合颜色与深度信息进行重要采样,结合轮廓信息并通过ASM模型的能量函数进行观测,根据最大后验概率对几种预定义的手势进行识别.实验结果表明,该算法能够有效地实现复杂背景下的人手跟踪与手势识别,为进一步实现智能人机交互奠定了基础.更多还原

【Abstract】 Presents a hand tracking and gesture recognition algorithm for human-computer interaction with two web cameras.ICONDENSATION technique is employed to fuse color and depth to generate importance particles.To improve the efficiency and accuracy of likelihood evaluation,all samples are validated according to the energy function of active contour models,taking into account the contour information.Gesture recognition is realized through the maximum posterior estimation of several pre-defined templates.Experimental results showed that the proposed method works well even in cluttered scenarios.更多还原