China University of Mining and Technology (CUMT)

China National Petroleum Corporation

Beijing Sankuai Online Technology Co., Ltd

Cnpc Engineering Technology R&d Company Limited

Beijing Huamei Inc Cnpc

Newish Technology (Beijing) Co., Ltd.

Newish Technology Co., Ltd.

Qin Han

Jing Wang

Lili Chen

Ming Xu

Jing Li

Wei Liu

Feng Yang

Chi Zhang

Yong Ma

Deheng Qian

Hua Zhang

Dongchun Ren

Suping Peng

Sheng Fu

Yao Wang

Jianhe Chen

Jianzhou Jin

Yongjin Yu

Fengzhong Qi

Shuoqiong Liu

Zhiwei Ding

Ce Li

Zishuai Liu

Youzhi Zheng

Yuchao Guo

Congfeng Qu

Chongfeng Zhou

Bin Lyu

Xiaobing Zhang

Yusi Feng

Shunping Zhang

Pu Xu

Fuchen Liu

Shuguang Ding

Chunhua Zhao

Hongling Li

Jiaying Zhang

Kanghua Li

Haizhi Zhang

Guifu Wang

Chenyang Zhou

Songbing Yan

Yiliu Sun

Jiwei Jiang

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

An ultra-high temperature resistant cement slurry system comprising cement, an ultra-high temperature strength stabilizer, an ultra-high temperature reinforcing material, a density regulator, an ultra-high temperature suspension stabilizer, a dispersant, a fluid loss additive, a retarder, a defoaming agent and water, wherein the ultra-high temperature suspension stabilizer comprises an ether-based starch, an aluminosilicate and a polyalcohol polymer. The method for preparing the cement slurry system includes dry mixing and wet mixing raw materials homogeneously, respectively, and then homogeneously mixing the dry mix and wet mix to obtain the cement slurry system. The cement slurry system can be used for cementing in deep wells and ultra-deep wells at high and ultra-high temperatures.

Ultra-high temperature resistant cement slurry system for cementing and preparation method and use thereof

Various embodiments a method and apparatus for unmanned driving behavior decision-making and model training, and an electronic device. The method includes: acquiring sample data, wherein the sample data includes a sample image; extracting a sample feature vector corresponding to the sample data, wherein a feature vector of the sample image is extracted by manifold dimension reduction; and based on the sample feature vector, training by semi-supervised learning to obtain a target decision-making model, wherein the target decision-making model is used for decision-making classification.

Unmanned driving behavior decision-making and model training

Provided are a sub-totipotent stem cell product and epigenetic modification label thereof, a method for inducing the generation of the sub-totipotent stem cell product and identification for the epigenetic modification label of the differentiation potential of stem cells. Also provided is a use of histone modification states of sub-totipotent genes and/or differentiation related genes to predict the epigenetic modification label of the differentiation potentials of stem cells.

Sub-totipotent stem cell product and apparent hereditary modifying label thereof

Growing community of inventors

Beijing, China

Qin Han