Tencent Technology (Shenzhen) Company Limited

Shenzhen Yinwang Intelligent Technologies Co., Ltd.

Tencent Technology Company Limited

Shijie Zhao

Feng Li

Xiaoxiang Zuo

Jun Cheng

Yang Yi

Kun Jin

Yuanzhi Lu

A hand key-point recognition model training method is provided for a model training device. The method includes: converting a sample virtual image into an emulation image through a Cycle-GAN model, the sample virtual image being an image generated through three-dimensional modeling, and the sample virtual image including key-point coordinates corresponding to hand key-points, and the emulation image being used for emulating an image acquired in a real scenario; extracting a hand image in the emulation image; and training a hand key-point recognition model according to the hand image in the emulation image and the key-point coordinates, the hand key-point recognition model being used for outputting hand key-point coordinates of a hand in a real image according to the inputted real image.

Hand key point recognition model training method, hand key point recognition method and device

This application discloses a method, an apparatus, and a storage medium for gesture movement recognition. The method includes: acquiring a first gesture image and a second gesture image; recognizing the first gesture image to obtain a first vector used for representing angles of finger segments in the first gesture image, and recognizing the second gesture image to obtain a second vector used for representing angles of finger segments in the second gesture image; selecting a first specified finger from a plurality of predetermined types of fingers; selecting first specified segments of a plurality of types of finger segments as needing to change segment angles in the first specified finger from the first gesture image to the second gesture image according to a specific gesture movement; calculating, by the server, a first total angular change amount of the first specified segments of a first specified finger according to the first vector and the second vector; and obtaining, a recognition result associated with the gesture movement according to the first total angular change amount in relation to a first preset angular change threshold.

Gesture movement recognition method, apparatus, and device

An embodiment of this application provides an image object detection method. The method may include obtaining a detection image, an n-level deep feature map framework, and an m-level non-deep feature map framework. The method may further include extracting deep feature from an (i&#x2212;1)-level feature of the detection image using an i-level deep feature map framework, to obtain an i-level feature of the detection image. The method may further include extracting non-deep feature from a (j&#x2212;1+n)-level feature of the detection image using a j-level non-deep feature map framework, to obtain a (j+n)-level feature of the detection image. The method may further include performing information regression operation on an a-level feature to an (m+n)-level feature of the detection image, to obtain an object type information and an object position information of an object in the detection image. The a is an integer less than n and greater than or equal to 2.

Method and apparatus for detecting object in image, and storage medium thereof

Growing community of inventors

Shenzhen, China

Shijie Zhao