Novatek Microelectronics Corp.

Novatek (shanghai) Co., Ltd.

Shanghaitech University

Zongmu Technology (shanghai) Co., Ltd.

Heng Yu

Lei Zhou

Chun Wang

Jiande Jiang

Min Wei

Fan Wang

Yajun Ha

Jian-De Jiang

Guang-Zhi Liu

Guangzhi Liu

Fupeng Chen

Rui Tang

Zhenghao Xu

The present disclosure provides an adaptive stereo matching optimization method, apparatus, and device, and a storage medium. The method includes: acquiring images of at least two perspectives of the same target scene, accordingly obtaining, through calculation, disparity value ranges corresponding to pixels in the target scene; and obtaining optimized depth value ranges by adjusting the disparity value ranges of the pixels in the target scene in real time through an adaptive stereo matching model; adjusting an execution cycle in the adaptive stereo matching model in real time through a DVFS algorithm according to a resource constraint condition of the processing system; and/or training on a plurality of scene image data sets through a convolutional neural network, so that the specific function parameters in the adaptive stereo matching model are correspondingly adjusted in real time according to the acquired different scene images.

Adaptive stereo matching optimization method and apparatus, device and storage medium

The present invention provides a method, system, terminal, and storage medium for rapid generation of reference lines. Path planning points are classified according to driving difficulty of different road segments, and the segments with low driving difficulty are assigned reference lines obtained by geometric processing; the segments with high driving difficulty are assigned reference lines obtained by algorithmic processing in combination with vehicle dynamics constraints. Then the reference lines of all segments are combined to form a complete reference line. This method requires little system resource and the algorithm consumes less time.

Method, system, terminal, and storage medium for rapid generation of reference lines

A display apparatus and an image display method of the display apparatus are provided, and the image display method includes following steps. Video contents that include a plurality of single frame images are received. A detection zone of the single frame images is determined according to a current scale mode of the display apparatus, and the different scale modes correspond to the different detection zones. The detection zone of each single frame image is detected to determine an image format of the video contents. A play mode of the display apparatus is adjusted according to the image format, and the video contents which are scaled are displayed by the display apparatus in the play mode.

Display apparatus and image display method thereof

An intensity compensation method for a display control device includes steps of obtaining a plurality of backlight duties of a plurality of backlights according to an image data; calculating a plurality of compensation gains according to the plurality of backlight duties and a non-uniform backlight profile, wherein the non-uniform backlight profile indicates a plurality of respective actual intensity distributions of the plurality of backlights; and compensating a plurality of first image intensities corresponding to a plurality of pixels of the image data according to the plurality of compensation gains, to obtain a plurality of second image intensities.

Intensity compensation method and display control device and image display device applying the same

A device and method are provided for two dimension (2D) to three dimension (3D) conversion. A 2D to 3D conversion device receives a 2D image data. The 2D to 3D conversion device assigns position data of a predetermined window. The 2D to 3D conversion device generates a depth map including a depth data of the 2D image data according to the 2D image data and the position data of the predetermined window. The 2D to 3D conversion device converts the 2D image data into a 3D image data according to the depth data of the depth map and the position data of the predetermined window.

Device and method for 2D to 3D conversion

An auto-detect method for detecting a single-frame image format is provided. A single-frame image is divided into a plurality of macro-blocks. Each of the macro-blocks is divided into a plurality of sub-blocks. A meta-block is allocated in each of the sub-blocks. A pixel luminance sum characteristic value for each of the meta-blocks is calculated. A first confidence between a left half and a right half of the single-frame image is calculated according to the pixel luminance sum characteristic values. A second confidence between an upper half and a lower hap of the single-frame image is calculated according to the pixel luminance sum characteristic values. A format of the single-frame image is determined according to the pixel luminance sum characteristic values, and the first and second confidences of the single-frame image.

Auto-detect method for detecting image format and playback method applying the same

A method of detecting image format includes dividing a single-frame image into a plurality of macro-blocks; calculating a correlation coefficient of a left-half image of the single-frame image and a right-half image of the single-frame image as a first global similarity; calculating a correlation coefficient of a top-half image of the single-frame image and a bottom-half image of the single-frame image as a second global similarity; calculating a portion difference of each macro-block; comparing the portion differences of the left-half image and the right-half image, for acquiring a first local similarity; comparing the portion differences of the top-half image and the bottom-half image, for acquiring a second local similarity; and detecting an image format of the single-frame image according to the first global similarity, the second global similarity, the first local similarity, the second local similarity, a first threshold and a second threshold.

Method of automatically detecting image format and device thereof

The present invention discloses a brightness compensation method. The brightness compensation method includes controlling a plurality of backlights of a plurality of display areas to turn on with a plurality of backlight intensity; calculating a plurality of total backlight intensity; calculating a plurality of actual backlight intensity according to the plurality of total backlight intensity and a backlight scanning ratio; dividing a plurality of maximum backlight intensity when the plurality of backlights are fully turned on by the plurality of actual backlight intensity, to generate a plurality of compensation gains; and displaying a compensated image data with a plurality of compensated image intensity after compensating a plurality of image intensity corresponding to the plurality of display area of an image data with the plurality of compensation gains.

Growing community of inventors

Shanghai, China

Heng Yu