Yutou Technology (hangzhou) Co., Ltd.

Yotou Technology (hangzhou) Co., Ltd.

Yutou Technology Co., Ltd.

Mingxiu Chen

Ningqing Liang

Hongxin Zhang

An expression feedback method and a smart robot, belonging to smart devices. The method comprises: step S, a smart robot using an image collection apparatus to collect image information; step S, the smart robot detecting whether human face information representing a human face exists in the image information; if so, acquiring position information and size information associated with the human face information, and then turning to step S; and if not, returning to step S; step S, according to the position information and the size information, obtaining, by prediction, a plurality of pieces of feature point information in the human face information and outputting same; and step S, using a first identification model formed through pre-training, determining whether the human face information represents a smiling face according to the feature point information, and then exiting from this step; if so, the smart robot outputting preset expression feedback information; and if not, exiting from this step. The beneficial effect of the method is: enriching an information interaction content between a smart robot and a user, so as to improve usage experience of the user.

Expression feedback method and smart robot

The present invention falls within the technical field of robots, and particularly relates to a robot monitoring system. The robot monitoring system based on human body information comprises an image collection unit for collecting an image; a human body detection unit for determining whether human body information matching a training sample exists in the image; a target acquisition unit for acquiring position information and size information about the human body information in the image; a target tracking unit for acquiring a current motion region according to a frame difference between the image and a predetermined image frame and acquiring a moving target from the motion region; and an adjustment unit for adjusting the orientation of the image collection unit such that the moving target is located in the centre of the image. By means of the technical solution, human body information is detected to track a moving target, so that a monitoring centre always tracks the position of a human body, thereby effectively realizing human body positioning and tracking, so as to monitor content information of interest.

Robot monitoring system based on human body information

A human face detection method, falling within the technical field of image detection. The method comprises: respectively determining a plurality of pieces of human face characteristic information in a plurality of pre-input human face training samples, and training and forming a characteristic prediction model according to all the pieces of human face characteristic information in each of the human face training samples. The method further comprises: step S, using an image acquisition apparatus to acquire an image; step S, using a human face detector trained and formed in advance to determine whether the image comprises a human face, and if not, returning back to step S; step S, using a characteristic prediction model to obtain a plurality of pieces of human face characteristic information through prediction from the human face in the image; and step S, constituting a facial structure associated with the human face according to the plurality of pieces of human face characteristic information obtained through prediction, and subsequently quitting. The beneficial effects of the technical solution are: being able to detect information about a human face comprising parts, such as the five sense organs and an outer profile, and improving the accuracy of human face detection.

Human face detection method

The present invention relates to the technical field of electronic devices, and in particular to a target tracking device and a target tracking method. A moving target tracking device which comprises a target tracking module, a motion module and a comprehensive analysis module is constructed; images of moving targets are acquired from a camera to determine the moving targets and finally determine an effective moving target; parameter information about the current motion of the effective moving target is then calculated, and whether the camera needs to be rotated is judged according to the parameter information; and after the rotation of the camera is completed, the parameter information stored in a memory is updated. By means of the technical solution, a moving target can be accurately and effectively tracked in real time, moreover, the moving target can continue to be tracked after the rotation of the camera is completed, and motion detection and tracking information accumulation do not need to be executed once again as in a traditional method. Furthermore, the technical solution can rapidly track any moving object without depending on any object model.

Target tracking device and target tracking method

The invention discloses an image recognition system, comprising: a robot having an image collection module configured to drive an image collection module to collect an image in a view of the robot by the image collection drive module; a light source configured to supplement light when the image collection module collecting an image; a face detection module configured to locate a face image in an image according to the image collected by the image collection module; a face recognition module configured to implement a preprocessing for the located face image, then the preprocessed face image being compared with an image feature information of a known identity in a database, to determine an identity information and a confidence probability of the present face image. The invention can identify a face based on a fixed face pose, and it can identify a face based on a local or web server database.

Growing community of inventors

Hangzhou, China

Mingxiu Chen