Aspeed Technology Inc.

Silicon Integrated Systems Corporation

Mediatek Corporation

Chung-Yen Lu

Kuo-Wei Yeh

Hung-Ju Huang

Hsin-Yu Chen

Te-Hao Chang

Ruen-rone Lee

Wen-Kuo Lin

Ming-Hao Liao

Fu-Chou Hsu

Pei-Hen Hung

Jing-Chuan Chen

Hung-Ming Lin

Cheng-Yi Hsu

Yung-Ching Chang

Jo-Tan Yao

Hong-Hui Chen

Yung-Feng Chiu

Ta-Lun Huang

Chi-Hui Huang

Hai-Wei Wang

Ming-Chi Bai

Bing-Chia Peng

Lung-Hsiang Kai

A texture prefetching apparatus in a graphics processing system having a texture memory is disclosed, comprising a first FIFO memory, a second FIFO memory, a main rasterizer, an auxiliary rasterizer and a cache data memory. The cache data memory is coupled between the first FIFO memory and the texture memory. The main rasterizer converts destination coordinates of a first pixel in a primitive into a cache entry and a tag for a first integer texel according to texture coordinates and destination coordinates of multiple vertices of the primitive. The auxiliary rasterizer coupled to the second FIFO memory converts destination coordinates of N second pixels in the primitive into multiple cache entries, multiple tags and multiple memory addresses for multiple second integer texels according to the texture coordinates and the destination coordinates of the multiple vertices, where N is a multiple of 4.

Texture prefetching scheme for graphics processing system

A video encoding apparatus for Bayer pattern images is disclosed, comprising: a quantizer, a variable-length coder and a predictor. The quantizer is configured to perform quantization over a difference value D between an input pixel and a current predicted pixel to generate a quantized value Δ in a quantization sequence based on a quantization parameter Q and the following equation: Δ=└(|D|+└Q/2┘+1)×A/N┘. The variable-length coder is configured to count a number ZR of consecutive zeros that either precede a following non-zero integer in the quantization sequence or are arranged in the end of the quantization sequence, to encode the number ZR of consecutive zeros into a first codeword by a first codeword set, and to encode the following non-zero integer into a second codeword by a second codeword set to produce an encoded bitstream.

Apparatus and method for encoding and decoding Bayer pattern images

An image processing system is disclosed, comprising a multiple-lens camera, a vertex list generator and an image processing apparatus. The multiple-lens camera captures a X-degree horizontal field of view (FOV) and a Y-degree vertical FOV to generate multiple lens images, where X<=360, Y<=180. The vertex list generator generates a first main vertex list according to a correspondence table, and generates a first region of interest (ROI) vertex list according to the first main vertex list and a position information of the ROI when the ROI overlaps at least one measuring region inside an overlap region in a projection image. The image processing apparatus generates the projection image according to the multiple lens images and a second main vertex list related to first main vertex list in a rendering mode.

System and method of generating projection image with region of interest

An image processing method for receiving M lens images and generating a projection image is disclosed. The method comprises: determining P optimal warping coefficients of P control regions in the projection image according to a 2D error table and the M lens images from an image capture module; generating M projection images according to the M lens images, a first vertex list and the P optimal warping coefficients; determining a seam for each of N seam regions; and, stitching two overlapping seam images to generate a stitched seam image for each seam region according to its corresponding seam. The 2D error table comprises multiple test warping coefficients and multiple accumulation pixel value differences in the P control regions. The P control regions are respectively located in the N seam regions respectively located in N overlap regions, where M>=2, N>=1 and P>=3.

Method for generating projection image with scaling adjustment and seam cut stitching

A multiple-processor system for a multiple-lens camera is disclosed. The system comprises multiple processor components (PCs) and multiple links. Each PC comprises multiple I/O ports and a processing unit. The multiple-lens camera captures a X-degree horizontal field of view and a Y-degree vertical field of view, where X&#x3c;=360 and Y&#x3c;180. Each link conjects one of the I/O ports of one of the PCs to one of the I/O ports of another one of the PCs such that each PC is conjected by two or more respective links to one or two neighboring PCs. Each link is configured to transfer data in one direction.

Multiple-processor system for multiple-lens camera and method thereof

A polyhedron lens architecture is disposed in a virtual sphere. The virtual sphere has a horizontal plane, an upper hemisphere above the horizontal plane and a lower hemisphere below the horizontal plane. The polyhedron lens architecture has an upper half part above the horizontal plane, and a lower half part below the horizontal plane. The polyhedron lens architecture includes: multiple bases, which are respectively disposed on the upper half part and the lower half part; and multiple lenses respectively disposed on surfaces of the bases. Optical axes of the lenses intersect at a central point, which is located at the horizontal plane and is a structural center of the polyhedron lens architecture.

Polyhedron lens architecture and lens scanning method suitable for the polyhedron lens architecture

A method of compensating for color differences between adjacent lens images in a panoramic image is disclosed. The method comprises: calculating color differences of each pair of character regions between any two adjacent lens images out of multiple lens images from a multiple-lens camera according to average color values of the character regions, each character region having a character point; determining color adjustment amounts of character points in each lens image according to the color differences of each pair of character regions; calculating a color adjustment amount of an element according to positions of the element and its two adjacent character points and the color adjustment amounts of the two adjacent character points.

Method of compensating for color differences between adjacent lens images in a panoramic image

An image processing system is disclosed, comprising: an M-lens camera, a compensation device and a correspondence generator. The M-lens camera generates M lens images. The compensation device generates a projection image according to a first vertex list and the M lens images. The correspondence generator is configured to conduct calibration for vertices to define vertex mappings, horizontally and vertically scan each lens image to determine texture coordinates of its image center, determine texture coordinates of control points according to the vertex mappings, and P1 control points in each overlap region in the projection image; and, determine two adjacent control points and a coefficient blending weight for each vertex in each lens image according to the texture coordinates of the control points and the image center in each lens image to generate the first vertex list, where M&#x3e;=2.

Image processing system and method thereof for generating projection images based on inward or outward multiple-lens camera

A transform method applied in an image processing system is disclosed, comprising: when the image capture module is rotated, respectively performing inverse rotation operations over post-rotation space coordinates of three first vertices from a integral vertex stream according to rotation angles of the image capture module to obtain their pre-rotation space coordinates; calculating pre-rotation longitudes and latitudes of the three first vertices according to their pre-rotation space coordinates; selecting one from a pre-rotation panoramic image, a south polar image and a north polar image as a texture image to determine a texture ID for the three first vertices according to their pre-rotation latitudes; and, calculating pre-rotation texture coordinates according to the texture ID and the pre-rotation longitudes and latitudes to form a first complete data structure for each of the three first vertices.

Transform method for rendering post-rotation panoramic images

A calibration method for linking spherical coordinates to texture coordinates is provided. The method comprises: installing a plurality of lamps forming a horizontal semicircle arc and a rotation equipment located at its circle center; mounting a N-lens camera on the rotation equipment; causing the N-lens camera to spin about a spin axis passing through two ends of the horizontal semicircle arc and capture a plurality of lens images for different spin angles by the rotation equipment; and, determining longitude and latitude coordinates of a plurality of calibration points according to the different spin angles and the texture coordinates of the calibration points in the lens images to create a link between the spherical coordinates and the texture coordinates. Different positions of the lamps respectively represent different latitudes and different spin angles respectively represent different longitudes. Heights of the camera and the lamps are the same.

Spherical coordinates calibration method for linking spherical coordinates to texture coordinates

A method of adjusting texture coordinates based on control regions in a panoramic image is disclosed. The method comprises determining warping coefficients of a plurality of control regions in a panoramic image; retrieving two selected warping coefficients out of the warping coefficients for each of a plurality of camera images with respect to each vertex from a first vertex list according to two coefficient indices for each camera image in its data structure; calculating an interpolated warping coefficient for each camera image with respect to each vertex according to the two selected warping coefficients and a coefficient blending weight for each camera image in its data structure; and, calculating modified texture coordinates in each camera image for each vertex according to the interpolated warping coefficient and original texture coordinates for each camera image in its data structure to form a second vertex list.

Method of adjusting texture coordinates based on control regions in a panoramic image

A video encoding apparatus is disclosed. The apparatus is used to process a sequence of frames of video data and each frame comprises a plurality of processing blocks. The apparatus comprises a skip decision circuit and an encoder. The skip decision circuit generates a control signal according to a similarity checking result and a comparison result between a first quantization parameter for a first processing block from a current frame and a second quantization parameter for a second processing block from a previous frame. The encoder encodes the first processing block to generate an encoded bit stream and the first quantization parameter. The second processing block resides at the same location in the previous frame as the first processing block in the current frame.

Method and apparatus for encoding processing blocks of a frame of a sequence of video frames using skip scheme

A transform apparatus applied in an image processing system with an image capture module is disclosed. The transform apparatus comprises a geometry information detector, a parameter setup unit, a primitive assembly unit and a geometry processing circuit. The geometry information detector measures geometry information of the image capture module. The parameter setup unit calculates geometry parameters and determines whether to assert an enable signal according to the geometry information. The primitive assembly unit receives an original vertex list and the enable signal to generate a vertex/ID flow. The geometry processing circuit receives the geometry parameters and performs geometry transform operations over the vertex/ID flow in response to whether the first enable signal is asserted to generate a modified vertex list. The geometry information comprises at least one of a displacement and rotation angles of the image capture module.

Method and apparatus for generating panoramic image with rotation, translation and warping process

A variable length coder is disclosed. The variable length coder comprises a size determining unit and a first residual coder. The size determining unit determines a maximum size based on sizes of quantized residuals in a current group and determines whether to enable the first residual coder according to the maximum size. When the maximum size is equal to 1, the first residual coder is enabled to encode the quantized residuals as one symbol to generate a first encoded suffix according to a variable length coding scheme.

Variable length coding and decoding methods and devices for grouped pixels

A vertex processing device applied in an image processing system having an image capture module is disclosed. The image capture module generates camera images. The vertex processing device comprises a coefficient interpolation unit and a coordinate modifying unit. The coefficient interpolation unit generates an interpolated warping coefficient for each camera image with respect to each vertex from a vertex list based on n number of warping coefficients and its original texture coordinates in each camera image. The coordinate modifying unit calculates modified texture coordinates in each camera image for each vertex according to the interpolated warping coefficient and its original texture coordinates in each camera image. The vertex list comprises vertices with data structures that define vertex mapping between the camera images and a panoramic image. The n number of warping coefficients correspond to n number of overlap regions in the panoramic image.

Growing community of inventors

Hsinchu, Taiwan

Chung-Yen Lu