International Business Machines Corporation

Peng Tang

Chi Xu

Jian Wang

Yan Wang

Hao Jia Li

Chang Wang

Yu Fen Yuan

Zhe Yan

Kai Guo

Rong Zhao

Li Bo Zhang

Li Li Guan

Chen Tian

Jiang Tao Wang

Xing Xing Di

A method, a computer program product, and a computer system guide a user through dimensional relationships. The method includes receiving a plurality of images of a unit of a perspective of a user. When a number of corresponding three-dimensional points between a current image and a previous image is less than a registration threshold to perform a three-dimensional registration operation, the method includes performing a three-dimensional data augmentation operation based on two-dimensional data from the current image and the previous image to generate extended corresponding three-dimensional points. The method includes determining a three-dimensional transform function between the current image and the previous image based on the extended corresponding three-dimensional points. The method includes generating annotations to be shown for the unit in the current image based on the three-dimensional transform function, the annotations being shown as a virtual rendering in a mixed reality environment viewed by the user.

Self guidance based on dimensional relationship

A method for generating training models includes generating a preliminary training model based on a group of first images, the first images including different types of objects; processing a group of second images with the preliminary model to generate a probability array for each of the second images, the probability array indicating likelihoods that an object is a particular type of object; generating correlations between the different types of objects based on the probability arrays; generating a plurality of object groups based on the correlations, where each object group includes a plurality of different types of objects that have a relatively low correlation with the other types of objects in the same object group; and for each object group, generating a final training model based on a group of third images, the third images each including an object having an object type corresponding to one of the object types.

Defect detection using multiple models

Embodiments of the present invention relate to water leakage detection. Data obtained by a smart electricity meter during a predefined time period is collected, where the smart electricity meter is associated with a water-consuming unit. Usages of certain electric appliances in the water-consuming unit during the predefined time period are determined based on the collected data. The electricity consumption of those appliances is correlated to water consumption. The legitimate water consumption of the water-consuming unit during the predefined time period is then determined based on the usages of the electric appliances.

Water leakage detection based on smart electricity meter

Growing community of inventors

Beijing, China

Peng Tang