-
Patent Agency Ranking
公开(公告)号：US09865083B2
公开(公告)日：2018-01-09
申请号：US14662426
申请日：2015-03-19
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Hsin-Jung Chen , Feng-Hsiang Lo , Sheng-Dong Wu , Ming-Yu Lin , Chun-Te Wu , Hao-Wei Peng
CPC classification number: G06T15/205 , G06T5/005 , H04N13/111 , H04N13/261 , H04N13/271
Abstract: An apparatus and a method for rendering three-dimensional stereoscopic images are provided. The apparatus comprises a multi-view processor, an object device, a depth device, and a block filling device. The multi-view processor obtains depth related data of a first pixel and a second pixel which are adjacent to each other on the input image, calculates a difference between the depth related data and determines whether the first pixel and the second pixel are continuous according to the difference. The object device executes a process of object detection to output contour information. The depth device executes a process of object judgment to output distance information. The block filling device detects a hole region in each viewpoint image, searches a search region adjacent to the hole region for a number of original pixels, and fills the hole region.
-
公开(公告)号：US20150237325A1
公开(公告)日：2015-08-20
申请号：US14421716
申请日：2013-03-15
Inventor： Ludovic Angot , Wei-Jia Huang , Chun-Te Wu , Chia-Hang Ho
CPC classification number: H04N13/261 , A61B1/00009 , A61B90/361 , A61B2017/00725 , A61B2090/3614 , A61B2090/367 , G06T7/579 , G06T2207/10012 , G06T2207/10024 , G06T2207/10068 , G06T2207/30004 , H04N13/221 , H04N13/271
Abstract: A method of converting 2D images to 3D images and system thereof is provided. According to one embodiment, the method comprises receiving a plurality of 2D images from an imaging device; obtaining motion parameters from a sensor associated with the imaging device; selecting at least two 2D images from the plurality of 2D images based on the motion parameters; determining a depth map based on the selected 2D images and the motion parameters corresponding to the selected 2D images; and generating a 3D image based on the depth map and one of the plurality of 2D images.
Abstract translation: 提供了一种将2D图像转换为3D图像的方法及其系统。 根据一个实施例，该方法包括从成像设备接收多个2D图像; 从与所述成像装置相关联的传感器获得运动参数; 基于所述运动参数从所述多个2D图像中选择至少两个2D图像; 基于所选择的2D图像和对应于所选择的2D图像的运动参数来确定深度图; 以及基于所述深度图和所述多个2D图像之一生成3D图像。
-
公开(公告)号：US10739439B2
公开(公告)日：2020-08-11
申请号：US16184533
申请日：2018-11-08
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Chun-Te Wu , Chieh-Chih Wang , Chung-Hsun Wang
Abstract: A laser positioning system includes a laser scanner, a first positioning tag, a second positioning tag, and a processing unit. The laser scanner is disposed on a mobile carrier and is for emitting a light beam to a positioning board and receiving a plurality of reflected light spot signals generated by the light beam reflected from the positioning board. The first positioning tag and the second positioning tag are for reflecting the light beam to generate a first positioning signal and a second positioning signal to the laser scanner. The processing unit is for finding information of positions of the light beam projected on the first positioning tag and the second positioning tag, and filtering the reflected light spot signals to define a reference coordinate for the processing to calculate relative positions of the laser scanner and the positioning board according to the reference coordinate.
-
公开(公告)号：US09894255B2
公开(公告)日：2018-02-13
申请号：US14290126
申请日：2014-05-29
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Ludovic Angot , Chun-Te Wu , Wei-Yi Lee
CPC classification number: H04N5/2256 , G06T7/11 , G06T7/136 , G06T7/174 , G06T2207/10016 , G06T2207/10048 , G06T2207/10144 , H04N5/2354 , H04N5/332
Abstract: A method and a system for depth selective segmentation of an object are provided. The method comprises the following steps. An image is captured in an invisible domain of the optical spectrum by illuminating a scene of interest under an illumination corresponding to said invisible domain of the optical spectrum by an invisible light illumination unit. A binary mask is obtained from the image according to a threshold. Part of the image is eliminated by applying the binary mask to the image, and resulting in another image. The threshold is changed and another binary mask is obtained. The latest obtained binary mask is applied to the latest captured image. The step of changing of the threshold, the step of obtaining a mask and the step of applying the latest obtained binary mask on the latest captured image are performed at least once.
-
5.发明申请公开(公告)号：US20150193965A1
公开(公告)日：2015-07-09
申请号：US14662426
申请日：2015-03-19
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Hsin-Jung Chen , Feng-Hsiang Lo , Sheng-Dong Wu , Ming-Yu Lin , Chun-Te Wu , Hao-Wei Peng
CPC classification number: G06T15/205 , G06T5/005 , H04N13/111 , H04N13/261 , H04N13/271
Abstract: An apparatus and a method for rendering three-dimensional stereoscopic images are provided. The apparatus comprises a multi-view processor, an object device, a depth device, and a block filling device. The multi-view processor obtains depth related data of a first pixel and a second pixel which are adjacent to each other on the input image, calculates a difference between the depth related data and determines whether the first pixel and the second pixel are continuous according to the difference. The object device executes a process of object detection to output contour information. The depth device executes a process of object judgment to output distance information. The block filling device detects a hole region in each viewpoint image, searches a search region adjacent to the hole region for a number of original pixels, and fills the hole region.
Abstract translation: 提供了一种用于渲染三维立体图像的装置和方法。 该装置包括多视图处理器，对象设备，深度设备和块填充设备。 多视图处理器获取在输入图像上彼此相邻的第一像素和第二像素的深度相关数据，计算深度相关数据之间的差，并根据第一像素和第二像素是否连续 区别。 对象装置执行对象检测处理以输出轮廓信息。 深度装置执行物体判断处理以输出距离信息。 块填充装置检测每个视点图像中的孔区域，搜索与多个原始像素的孔区域相邻的搜索区域，并填充该孔区域。
-
-
-
-
Search Results
5
records
(took 0.026 seconds)
