China University of Mining and Technology

Chengdu Boe Optoelectronics Technology Co., Ltd.

Beijing Boe Technology Development Co., Ltd.

China Banknote Printing and Minting Corporation

Ce Li

Feng Yang

Yu Cao

Jing Yang

Feng Pan

Long Jiang

Xiaowei Li

Suping Peng

Zhe Xu

Xinyu Li

Wenxuan Zhang

Qin Han

Caixia Li

Xu Qiao

Fei You

Fei Liao

Tan He

Mingcun Liu

A mask plate is used for manufacturing a pixel definition layer of the display substrate, which includes first transparent patterns and first opaque patterns, and further includes transition structures located between the first transparent patterns and the first opaque patterns. And the transition structures include a plurality of second transparent patterns and second opaque patterns alternately arranged, and a line width of each of the second transparent patterns and each of the second opaque patterns is less than the resolution of an exposure machine by using the mask plate for exposure.

Mask plate, display substrate and manufacturing method thereof, and display device

A monocular video-based three-dimensional reconstruction and depth prediction method and system for a pipeline are provided, relating to the technical field of deep learning and image processing. The method includes the following steps: performing feature extraction and matching and incremental reconstruction on collected image sequences of different pipeline scenes based on the COLMAP method to obtain a camera external parameter matrix corresponding to each image, and constructing a pipeline three-dimensional reconstruction dataset; training the Fast-MVSNet network and the PatchMatchNet network using the existing public datasets, and selecting an optimal network model from multiple trained network models for three-dimensional reconstruction and depth prediction of an actual pipeline scene. A holistic framework from a monocular video to a three-dimensional scene is constructed, which can effectively achieve three-dimensional reconstruction and depth prediction of a drainage pipeline and intuitively display internal structure information of the pipeline.

Monocular video-based three-dimensional reconstruction and depth prediction method and system for pipeline

A method for restoring video data of a pipe based on computer vision is provided. The method includes: performing gray stretching on pipe image/video collected by a pipe robot; processing noise interference by smoothing filtering; extracting an iron chain from the center of a video image as a template for location; performing target recognition on the center of video data by an SIFT corner detection algorithm; detecting ropes on left and right sides of a target by Hough transform; performing gray covering on the iron chain at the center of the video image and the ropes on two sides; and restoring data by an FMM image restoration algorithm.

Method for restoring video data of pipe based on computer vision

The present invention proposes a method for rapidly dehazing an underground pipeline image based on dark channel prior (DCP). The method includes: preprocessing a hazy underground pipeline image to obtain a dark channel image corresponding to the hazy image; average-filtering the obtained dark channel image to estimate an image transmittance; compensating an offset value for an average filtering result to obtain a rough estimate of the transmittance; using a pixel value of the original image and an average-filtered image to estimate a global atmospheric light value; and using a physical restoration model to restore a dehazed image. The method of the present invention realizes the timeliness of the algorithm while ensuring the dehazing effect, and is suitable for scientific fields such as video monitoring of underground pipeline environment and identification of underground pipeline defects.

Method for rapidly dehazing underground pipeline image based on dark channel prior

The present invention provides a security functional thin film and a security product containing such a thin film. The security functional thin film is of an amorphous structure, and possesses soft magnetic characteristics. Large Barkhausen effect can be detected along the in-plane preferred direction of magnetization; and the Large Barkhausen effect significantly attenuates, or no such signal can be detected, in a direction perpendicular to the in-plane preferred direction of magnetization. The thin film has a thickness of 20-300 nm, and the thin film also possesses element encoding characteristics that can be authenticated by experts. The security functional thin film of the present invention can be fabricated by magnetron sputtering web coating process. The security product provided by the present invention has a security information layer formed of the security functional thin film, and can be combined with other security characteristics for use in fabricating security materials such as security threads, security tapes, paper security strip-like inserts, or security labels, and others. Compared with conventional anti-counterfeiting technologies, the instant security functional thin film has more hidden security information, and facilitates enhancement of safety performance of security products.

Security functional thin film and security product containing the functional thin film

Growing community of inventors

Beijing, China

Ce Li