权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Object Recognition Using a Multichannel Vision System

使用多通道视觉系统进行物体识别

基本信息

批准号：
15500124
负责人：
TOMINAGA Shoji
金额：
$ 2.24万
依托单位：
Osaka Electro-Communication University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
2003
资助国家：
日本
起止时间：
2003 至 2004
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-15500124/
关键词：
Vision system Multichannel Spectral image Color Object recognition Reflection model

项目摘要

1.Estimation of reflection models of objects by using multichannel imagesA method is proposed for estimating various parameters of a reflection model using both the image data and the range data of an object surface. A unified measuring system, combining a laser range and a multi-band camera system, is made for acquiring the 3D shape data and the spectral reflectance data of the object surface. First, the diffuse reflection component and the specular reflection component at every pixel are obtained using the observed images at two illumination directions and the surface normal vectors calculated from the range data. The spectral reflectance is then estimated from the diffuse reflection component. Next, the extracted specular reflection component is fitted to the specular function of the Torrance-Sparrow model.2.Measuring and rendering of art paintings by using a multichannel vision systemWe propose a method for measuring an art painting by using the simple imaging system of an RGB came … More ra and a light source, and rendering the painting as CG images under any conditions of illumination and viewing. The surface shape is considered as the rough plane with paints on a flat canvas. We capture some images of the same painting under different illumination directions. First, the surface normal is estimated from the diffuse component, based on a photometric stereo. Next, the surface-spectral reflectance is estimated from the RGB values for the diffuse component. Moreover, the Torrance-Sparrow model is used for image rendering.3.Recognition of printed circuit boards by using a multichannel vision systemWe propose a method for classifying object materials on a raw circuit board based on surface-spectral reflectance. The multi-spectral imaging system is composed of a liquid-crystal tunable filter, a monochrome CCD camera, macro-lens and a personal computer. We have shown that dielectric materials like plastics can be distinguished from metals based on the reflectance difference in changing illumination geometries. Then an algorithm is presented for classifying the objects into several circuit elements. Region segmentation results of the circuit board are demonstrated in an experiment using a real board. Less

1.利用多通道图像估计目标的反射模型提出了一种利用目标表面的图像数据和距离数据估计反射模型的各种参数的方法。将激光测距仪和多波段摄像系统相结合，构成了一个统一的测量系统，用于获取物体表面的三维形貌数据和光谱反射率数据。首先，使用在两个照明方向上的观察图像和从距离数据计算的表面法线矢量来获得每个像素处的漫反射分量和镜面反射分量。然后从漫反射分量估计光谱反射率。其次，将提取的镜面反射分量拟合到Torrance-Sparrow模型的镜面函数中。2.利用多通道视觉系统对艺术画进行测量和绘制我们提出了一种利用简单的RGB摄像系统对艺术画进行测量的方法 ...更多信息 ra和光源，并在任何照明和观看条件下将画作渲染为CG图像。表面形状被认为是粗糙的平面与油漆在一个平坦的画布上。我们在不同的照明方向下捕捉同一幅画的一些图像。首先，基于光度立体，从漫射分量估计表面法线。接下来，从漫射分量的RGB值估计表面光谱反射率。此外，Torrance-Sparrow模型用于图像渲染。3.利用多通道视觉系统识别印刷电路板提出了一种基于表面光谱反射率的印刷电路板材料分类方法。多光谱成像系统由液晶可调滤光片、单色CCD摄像机、宏透镜和计算机组成。我们已经表明，塑料等介电材料可以根据改变照明几何形状时的反射率差异与金属区分开来。然后提出了一种算法，用于将对象分类为几个电路元件。在一个真实的电路板上进行了实验，验证了该方法的有效性。少