专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20150228080A1 ONE METHOD OF DEPTH PERCEPTION BASED ON BINARY LASER SPECKLE IMAGES 有权
标题翻译：一种基于二进制激光标记图像的深度感知方法
公开(公告)号：US20150228080A1
公开(公告)日：2015-08-13
申请号：US14591101
申请日：2015-01-07
申请人： Chenyang GE , Yanhui ZHOU
发明人： Chenyang GE , Huimin YAO , Yanhui ZHOU
IPC分类号： G06T7/00
CPC分类号： G06T7/0065 , G06K9/2036 , G06T7/231 , G06T7/521 , G06T7/55 , G06T2207/10048
摘要： The present invention discloses a method of depth perception based on binary laser speckle images: read in binary input and reference speckle images (pattern fixed, distance known) to generate the input and reference speckle windows, extract an image block of a certain size in the input speckle window, search the matching block in the matching search window of the reference speckle window, then use the method for block XOR similarity calculation to compare and output the minimum similarity value or use the block IAD method to compare and output the maximum similarity value to get the optimal matching block and the optimal offset, then to work out the central point depth information of this image block via the formula for depth calculation. The present invention not only can complete hardware implementation easily, greatly simplify the calculation, also generate high-resolution and high-precision depth information in a fast and accurate manner.
摘要翻译：本发明公开了一种基于二进制激光散斑图像的深度感知方法：在二进制输入和参考散斑图像（图案固定，已知距离）中读取，以生成输入和参考散斑窗口，提取一定尺寸的图像块输入散斑窗口，在参考散斑窗口的匹配搜索窗口中搜索匹配块，然后使用块XOR相似度计算方法比较和输出最小相似度值，或使用块IAD方法来比较和输出最大相似度值获得最优匹配块和最优偏移，然后通过深度计算公式计算出该图像块的中心点深度信息。本发明不仅可以轻松完成硬件实现，大大简化计算，还能以快速准确的方式生成高分辨率，高精度的深度信息。

2. 发明申请

US20170270670A1 METHOD AND APPARATUS FOR GENERATING A STRUCTURED LIGHT SPECKLE ENCODED PATTERN 审中-公开
公开(公告)号：US20170270670A1
公开(公告)日：2017-09-21
申请号：US15074049
申请日：2016-03-18
申请人： Chenyang GE , Huimin YAO , Yanhui ZHOU
发明人： Chenyang GE , Huimin YAO , Yanhui ZHOU
IPC分类号： G06T7/00
CPC分类号： G06T7/80 , G06T7/521
摘要： The present invention discloses a method of generating a structured light speckle encoded pattern, comprising: fabricating an initial speckle pattern with evenly distributed speckle particles; screening positions that all speckle particles can be disturbed to in the initial speckle pattern according to a speckle particle isolation principle; performing random disturbance to each speckle particle in the initial speckle pattern according to a generated random array and the screened positions that can be disturbed to; performing window uniqueness analysis to the disturbed speckle encoded pattern to determine whether the disturbed speckle encoded pattern meets requirements of a window uniqueness distribution. The present invention further discloses an apparatus for generating a structured light speckle encoded pattern. The present invention may generate, rapidly and accurately, a speckle encoded pattern that meets requirements of window uniqueness distribution and has good anti-noise and anti-deformation competences; besides, the generated speckle encoded pattern has a high randomness and is not restricted by pattern size.

3. 发明申请

US20150229911A1 ONE METHOD OF BINOCULAR DEPTH PERCEPTION BASED ON ACTIVE STRUCTURED LIGHT 审中-公开
标题翻译：一种基于活动结构光的双向深度感知方法
公开(公告)号：US20150229911A1
公开(公告)日：2015-08-13
申请号：US14591083
申请日：2015-01-07
申请人： Chenyang GE , Nanning ZHENG
发明人： Chenyang GE , Nanning ZHENG , Huimin YAO , Yanhui ZHOU , Jiankun LUN
IPC分类号： H04N13/02
CPC分类号： H04N13/239 , G06T7/521 , G06T7/593 , H04N13/128 , H04N13/254 , H04N2013/0081
摘要： The present invention provides a method of binocular depth perception based on active structured light, adopting a coded pattern projector to project a coded pattern for structured light coding of the projective space or target object (characteristic calibration), then obtaining the coded pattern by means of two cameras on the same baseline and respectively located symmetrically on both sides of the coded pattern projector, after preprocessing and projection shadow detection, estimating the block matching movement in two modes based on the image blocks (binocular block matching and automatic matching) to obtain the offset of the optimal matching block, finally working out the depth value according to the formula for depth calculation and compensating the depth of the projection shadows to generate high-resolution and high-precision depth information.
摘要翻译：本发明提供一种基于有源结构光的双目深度感知方法，采用编码图案投影仪投影投影空间或目标对象（特征校准）的结构光编码的编码图案，然后通过在相同基线上的两个相机并且分别对准编码图案投影仪的两侧，在预处理和投影阴影检测之后，基于图像块（双目块匹配和自动匹配）估计两种模式中的块匹配运动，以获得最终匹配块的偏移量，最终根据深度计算公式计算深度值，并补偿投影阴影的深度，生成高分辨率和高精度的深度信息。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式