National Taiwan University

Himax Technologies, Inc.

Mediatek Corporation

Lite-on Technology Corporation

Himax Media Solutions, Inc.

Chao-Chung Cheng

Liang-Gee Chen

Ling-Hsiu Huang

Chung-Te Li

Yen-Chieh Lai

Yu-Lin Chang

Te-Hao Chang

Cheng-Ming Chen

Chia-Kai Liang

Chen-Hao Wei

Liang-Chun Lin

Yu-Ying Wang

Chien Wu

Homer H Chen

Po-Hao Huang

Ying-Jui Chen

Ying-Ru Chen

Wan-Yu Chen

Yu-Chun Chen

Sheng-Chun Niu

Han-Yang Wang

Yi-Min Tsai

Various examples with respect to visual depth sensing with accurate and full-range depth fusion and sensing are described. A control circuit of an apparatus receives a plurality of sensor signals that are heterogeneous in type from a plurality of sensors. The control circuit generates first depth-related information of a scene and second depth-related information of the scene based on the plurality of sensor signals. The control circuit then fuses the first depth-related information and the second depth-related information to generate a fused depth map of the scene.

Method and apparatus of depth fusion

Various examples with respect to infrared (IR) patter characteristics for stereo matching are described. A control circuit of an apparatus controls an IR projector to project a patterned IR light. In response, the control circuit receives first data of a left image of a scene from a first camera and second data of a right image of the scene from a second camera. The control circuit then performs stereo matching of the left image and the right image to generate a depth map of the scene. The patterned IR light satisfies one or more characteristic requirements.

IR pattern characteristics for active stereo matching

Various examples with respect to method and apparatus for active stereo vision are described. An apparatus may include an electromagnetic (EM) wave emitter, a first sensor and a second sensor. During operation, the EM wave emitter emits EM waves toward a scene, the first sensor captures a first image of the scene in an infrared (IR) spectrum, and the second sensor captures a second image of the scene in a light spectrum. The first image and second image, when processed, may enable active stereo vision.

Method and apparatus for active stereo vision

A method for generating a target perspective model referenced for depth map generation includes at least following steps: receiving a first input image; utilizing a region-based analysis unit for analyzing a plurality of regions in the first input image to extract image characteristics of the regions; and determining the target perspective model according to at least the image characteristics. Another method for generating a target perspective model referenced for depth map generation includes: receiving a first input image; determining a first perspective model in response to the first input image; and utilizing a perspective model generation unit for generating the target perspective model by a weighted sum of the first perspective model and at least one second perspective model.

Method and apparatus of determining perspective model for depth map generation by utilizing region-based analysis and/or temporal smoothing

An example process to enhance a two-dimensional (2D) image may include generating a depth map for the 2D image based on edges detected from the 2D image, wherein the depth map can be used to convert the 2D image to a 3D image. The process may further include enhancing the 2D image using the depth map.

Real-time depth-aware image enhancement system

In accordance with at least some embodiments of the present disclosure, a processor for performing stereo matching of a first image and a second image is described. The processor may include a first pipeline stage configured to generate data costs associated with a first tile selected from the first image, wherein the data costs is generated based on pixels in the first tile and corresponding pixels in the second image. The processor may include a second pipeline stage configured to generate disparity values associated with the first tile and an outbound message from the first tile to one of neighboring tiles in the first image, wherein the disparity values and the outbound message are generated based on the data costs and inbound messages from the neighboring tiles to the first tile. The processor may further include a third pipeline stage configured to store the disparity values and the outbound message in a memory, wherein the outbound message is used by the second pipeline stage as one of the inbound messages during processing of a second tile selected from the first image.

Stereo-matching processor using belief propagation

A system and method of correcting a depth map for 3D image is disclosed. A spatial spectral transform unit extracts pixels of object boundaries according to an input image, wherein the spatial spectral transform unit adopts Hilbert-Huang transform (HHT). A correction unit corrects an input depth map corresponding to the input image according to the pixels of object boundaries, thereby resulting in an output depth map.

System and method of correcting a depth map for 3D image

A method of revising depth of a three-dimensional (3D) image is disclosed. The method comprises the following steps: firstly, at least one initial depth map associated with one image of the 3D image pair based on stereo matching technique is received, wherein the one image comprises a plurality of pixels, and the initial depth map carries an initial depth value of each pixel. Then, the inconsistence among the pixels of the one image of the 3D image pair is detected to estimate a reliable map. Finally, the initial depth value is interpolated according to the reliable map and the proximate pixels, so as to generate a revised depth map by revising the initial depth value.

System and method of revising depth of a 3D image pair

In accordance with at least some embodiments of the present disclosure, a process for generating a depth map for converting a two-dimensional (2D) image to a three-dimensional (3D) image is described. The process may include generating a depth gradient map from the 2D image, wherein the depth gradient map is configured to associate one or more edge counts with one or more depth values, extracting an image component from the 2D image, wherein the image component is associated with a color component in a color space, determining a set of gains to adjust the depth gradient map based on the image component, and generating the depth map by performing depth fusion based on the depth gradient map and the set of gains.

Depth map generation for a video conversion system

In a method of block-based motion estimation a motion vector map is obtained by obtaining a motion vector of each macroblock (MB) in the current frame with respect to the reference frame. The motion vector of each MB in an interpolated frame is then determined according to the motion vector map.

Method of block-based motion estimation

A method and apparatus of tile-based belief propagation are disclosed. An image is split into a number of tiles. Messages are iteratively generated within each of the tiles based on the messages from neighboring pixels to the tile at a previous iteration, wherein each message represents information of a state of the pixel. The generated messages for sending out of the tiles are stored. Labels are then determined based on the stored messages, wherein each label represents the state of the pixel.

Method and apparatus of tile-based belief propagation

A driving support system with plural dimension processing units (DPUs) for indicating a condition of a surrounding area is disclosed. The driving support system of a vehicle includes plural image capturing devices disposed around the vehicle; at least a dimension processing unit (DPU) connected with the plural image capturing devices for receiving images from the plural image capturing devices and then producing plural related depth maps; a controller connected with the DPU for receiving the plural related depth maps and then producing an indicating data; and a display device connected with the controller for displaying the indicating data around the vehicle in a vertical view.

Driving support system with plural dimension processing units

The invention presents a system and method for obtaining object depth through digital signal processing. The auto depth-field capturing method for a camera includes the steps of a) taking plural images; b) estimating plural epipolar data of the plural images for obtaining a matrix describing motion and directional vectors; c) estimating a location data in response to the plural epipolar data and the matrix; d) rectifying the plural images corresponding to the plural epipolar data for obtaining plural rectified images; e) calculating the location data for obtaining disparity vectors of the rectified images; f) obtaining a depth map in response to the disparity vectors and the location data; and g) painting a 3D image in correspondence with the depth map. The depth estimation method of the present invention is fully automatic without change of the camera itself.

Auto depth field capturing system and method thereof

A depth-based image enhancement system is disclosed. A depth estimation unit generates three-dimensional (3D) depth information from a two-dimensional (2D) image. Subsequently, an image enhancement unit enhances the 2D image according to the 3D depth information.

Depth-based image enhancement

A system of generating three-dimensional (3D) depth information is disclosed. A color and object independent local blurriness estimation unit analyzes blurriness of each pixel of a two-dimensional (2D) image. Subsequently, a depth assignment unit assigns depth information to the 2D image according to the analyzed blurriness.

Growing community of inventors

Taipei, Taiwan

Chao-Chung Cheng