基于微透镜阵列的实时三维物体识别

提出一种基于微透镜阵列多视角成像特点,将三维物体的深度信息转化为二维透射像阵列的角度信息,利用光学二维图像识别技术,实现对三维物体识别的方法.对识别过程进行了理论分析和计算,用匹配滤波的方法实现了对三维物体骰子的实时识别.实验结果表明,本方法的相关识别能力较高,并且具有很强的灵活性,对于有微小旋转、微小平移的三维物体也可进行识别.

Real-time Three-dimensional Object Recognition with Microlens Array

A novel method for three-dimensional(3-D) object recognition using microlens array is proposed. The conversion of depth information of 3-D objects to 2-D elemental images by use of the characteristic of microlens array makes the recognition possible by optical processing. Correlative analysis and calculations have been done for the process of recognition. Real-time recognition of dice has been accomplished with the method of match filtering. The result shows that the proposed method can be used to recognise slightly rotated and slightly shifted objects flexibly.