Industrial Technology Research Institute

Kun-Lung Tseng

An-Chun Luo

Chung-Wei Lin

Ming-Hui Lin

Chy-Lin Wang

Yi-Jen Chan

Ludovic Angot

Wei-Jia Huang

Shang-Yi Lin

Golden Tiao

Chang-Ying Chen

Yueh-Yi Lai

Chih-Hsiang Yu

Shih-Wen Yang

Ming Wu

Yi-Heng Chou

Wei-Hao Huang

Zih-Jian Jhang

Hong-Tu Yu

An object recognition system based on machine learning includes a 2D image capture module, a 3D space capture module, a data selection module, a data alignment module, a feature capture module and a detection module. The 2D image capture module captures a 2D image. The 3D space capture module captures 3D point cloud data. The data selection module performs object segmentation and depth recognition to select at least one region of interest (ROI). The data alignment module maps coordinates of the at least one ROI to coordinates of the 2D image. The feature capture module calculates features of the 2D image and extracts at least one feature of interest corresponding to the coordinates of the ROI from the features of the 2D image. The detection module obtains the feature of interest and identifies at least one object in the 2D image according to the feature of interest.

Object recognition system based on machine learning and method thereof

A measurement system comprises an illumination module, an image pickup device, an angle adjustment module, and a control unit. The illumination module is configured to illuminate an object. The image pickup device is configured to pick up an image of the object. The angle adjustment module is configured to adjust an relative angle between the object and the image pickup device. The control unit is electrically connected to the image pickup device and the angle adjustment module and configured to receive an image signal from the image pickup device. The control unit is configured to command the angle adjustment module to adjust the relative angle to at least three values. The image pickup device is configured to pick up images of the object respectively corresponding to the at least three values. The control unit is configured to calculate the relative angle between the object and the image pickup device.

Measurement system comprising angle adjustment module

Measurement system and method for measuring multi-dimensions of an object are provided. A two-dimensional (2D) image capturing device captures at least one macro-2D image of the object. A three-dimensional (3D) information acquisition device acquires micro-3D measured data of the object. A integration and estimation device performs 2D and 3D image correction on macro-2D image and micro-3D measured data to map micro-3D measured data into macro-2D image to output 3D-topography data corresponding to macro-2D image of the object, and based on machine learning mechanism, performs matching procedure on at least one connection feature between any two positions in 3D-topography data with a database to elect an adapted model. Based on its corresponding to at least one fitting function, the integration and estimation device estimates the connection features of 3D-topography data to output at least one estimated feature amount, thereby obtaining measurement results corresponding to the object.

Measurement system and method for measuring multi-dimensions

An apparatus and a method for dual mode depth measurement are provided. The apparatus is used for measuring a depth information of a specular surface in a depth from defocus (DFD) mode or measuring a depth information of a textured surface in a depth from focus (DFF) mode. The apparatus includes a light source, a controller, a processor, a lighting optical system, an imaging optical system, a beam splitter and a camera. The controller is for switching between the depth from defocus mode and the depth from focus mode. The lighting optical system is used to focus a light from the light source on an object surface in the depth from defocus mode, and the lighting optical system is used to illuminate the object surface with a uniform irradiance in the depth from focus mode.

Apparatus and method for dual mode depth measurement

This disclosure provides an image composition system and its method. The system includes: an image capturing unit configured for capturing at least one first image of a real object; a depth information generating unit disposed on the image capturing unit and configured for measuring a depth information between the depth information generating unit and the real object; a computing unit receiving the at least one first image and the depth information, performing the computation of removing a noise caused by a moving object other than the real object from the received depth information, and computing a moving trajectory of the image capturing unit; and a composition unit compositing the at least one first image and a second image of a virtual scene, and display the composited result on a display unit.

System and method for image composition thereof

A stereo camera apparatus including an image capturing device, an optical axis controlling module and a calculating module is provided. The image capturing device is suitable for obtaining a stereo image, and the image capturing device includes a plurality of image capturing units. The optical axis controlling module is coupled to the image capturing device. The calculating module is coupled to the image capturing device and the optical axis controlling module, wherein the calculating module calculates a calibration condition according to the stereo image. The optical axis controlling module adjusts directions of imaging optical axes of the image capturing units. After being adjusted by the optical axis controlling modules, the imaging optical axes of the image capturing units are aligned. Besides, a self-calibration apparatus and a method of calibration are also provided.

Stereo camera apparatus, self-calibration apparatus and calibration method

A display apparatus including an image generator, a projection lens set, a depth detecting module detecting the position of user, and a control unit is provided, wherein the control unit is electrically connected to the image generator, the projection lens set and the depth detecting module. An image displayed by the image generator is projected through the projection lens set and generates a floating real image between the projection lens set and the user. Each beam forming the floating real image has a light-cone angle &#x3b8;. The image generator and the projection lens adjust the position of the floating real image according to the position of user. The size of the floating real image is L, the distance between two eyes of the user is W, the distance between the user and the floating real image is D, and the light-cone angle &#x3b8; satisfies the formula of 

Growing community of inventors

Taipei, Taiwan

Kun-Lung Tseng