Zepp Labs, Inc.

Melo Inc.

Other

Beijing Shunyuan Kaihua Technology Limited

Zheng Han

Xiaowei Dai

Guobin Shen

Ke Zhao

Jie Xu

Fan Liu

Jiangyu Liu

Fan Yang

Zeyu Liu

Yusheng Ye

Xianjun Huang

Seong Jae Hwang

Jason Fass

Mi Chen

Systems and methods are provided for processing information of a meeting. An exemplary system may include a communication interface configured to receive meeting information obtained by a plurality of client devices. The meeting information may include multiple audio streams. The system may also include a memory and a processor. The processor may execute instructions stored on the memory to perform operations. The operations may include determining signal-to-noise-ratio (SNR) indicators associated with the audio streams. The operations may also include selecting, from the audio streams, a candidate audio stream based on the SNR indicators. The SNR indicator associated with the candidate audio stream may indicate that the candidate audio stream has a higher average SNR than that of a predetermined number of other audio streams. In addition, the operations may include generating an output data stream including at least a portion of the candidate audio stream.

Systems and methods for processing meeting information obtained from multiple sources

Embodiments disclosed provide a solution to detect a rally in a sports game. One or more stroke actions or non-stroke actions are detected based on motion data detected by a sensor attached to a sports instrument of a user. Using a trained stroke classification model, each detected stroke action is classified into a plurality of classes. Additionally, a determination is made whether each detected non-stroke action is an intentional special user action. The determination whether a non-stroke action is an intentional special user action is made based on a customized set of definitions defining one or more special user actions. One or more rallies are then detected based on the classified stroke actions and intentional special user actions.

Automatic rally detection and scoring

Embodiments of the disclosure provide systems and methods for logging a meeting. The system may include a memory storing computer-executable instructions and a processor. The processor may be configured to execute the instructions to perform operations. The operations may include receiving audio of the meeting captured by at least one microphone device and determining an arriving angle of speech from at least one attendee of the meeting based on the captured audio. The operations may also include generating a data stream based at least in part on the arriving angle of speech, determining an identification of the at least one attendee, and matching the identification to the data stream.

Systems and methods for logging and reviewing a meeting

A solution is provided for detecting in real time video highlights in a sports video at a mobile computing device. A highlight detection module of the mobile computing device extracts visual features from each video frame of the sports video using a trained feature model and detects a highlight in the video frame based on the extracted visual features of the video frame using a trained detection model. The feature model and detection model are trained with a convolutional neural network on a large corpus of videos to generate category level and pair-wise frame feature vectors. Based on the detection, the highlight detection module generates a highlight score for each video frame of the sports video and presents the highlight scores to users of the computing device. The feature model and detection model are dynamically updated based on the real time highlight detection data collected by the mobile computing device.

Detect sports video highlights for mobile computing devices

Embodiments of the disclosure provide a system and methods for logging and reviewing a meeting. The system may include a communication interface configured to receive video of the meeting captured by at least one camera device and audio of the meeting captured by at least one microphone device, a memory having computer-executable instructions stored thereon, and a processor. The processor may be configured to execute the instructions to generate a plurality of data streams based on captured video and captured audio, and to determine identifications of attendees of the meeting based on at least one of the captured video and the captured audio. The processor may also be configured to execute the instructions to transcribe speeches of the attendees based on at least one of the captured audio. The processor may be further configured to execute the instructions to match the identifications to the plurality of data streams, and to cause a data stream of the plurality of data streams to be shown on the display based on a user-selected identification of an attendee of the meeting.

A solution is provided for detecting video highlights of a sports video. A video highlight of a sports video is a portion of the sports video and represents a semantically important event captured in the sports video. An audio stream associated with the sports video is evaluated, e.g., the loudness and length of the loudness of the portions of the audio stream. Video segments of the sports video are selected based on the evaluation of the audio stream. Each selected video segment represents a video highlight candidate of the sports video. A trained audio classification model is used to recognize the voice patterns in the audio stream associated with each selected video segment. Based on the comparison of the recognized video patterns with a set of desired voice patterns, one or more video segments are selected as the video highlights of the sports video.

Detect sports video highlights based on voice recognition

A solution is disclosed for conveniently capturing video highlights in a sports event by tracking head rotation movement of a user and synchronizing rotations of a video capturing device (e.g., the user's mobile phone) on a rotary station with the head rotation movement of the user. The user wears a rotation tracking device, which tracks the head rotation movement of the user in connection with watching an event. The head rotation data from the user's head rotation movement is filtered to generate filtered head rotation data, which excludes noise motions in the head rotation data. Corresponding rotary control data is generated based on the filtered head rotation data. The rotary control data is used to instruct a rotary system to rotate synchronously with head rotations of the user when a video capturing device mounted on the rotary system captures videos of the sports event.

Head rotation tracking device for video highlights identification

Motion sensor charger

A solution is provided to enhance motion detection and recognition of moving objects associated with various sports by embedding motion sensors into sports instruments such as tennis rackets, badminton rackets, baseball bats and golf clubs, that are swung in a three-dimensional (3D) space. A motion sensor device inserted and locked inside a sports instrument is configured to detect motions associated with movements associated with the sports instrument. The device is shaped to be inserted into a sensor housing attached to a selected location inside the sports instrument. The device includes a motion sensor for detecting motion associated with the movement of the sports instrument, a cover for protecting the motion sensor, and a locking mechanism attached to the sensor housing for locking the motion sensor inside the sensor housing.

Motion sensor in a sports instrument

Motion sensor

A system is provided for real-time single-view action recognition for sports videos based on key pose analysis of the sports videos. A training module of the system trains feature models for a sports action distinctively associated with each sports type using a large corpus of training videos. The trained feature models include a player detector for detecting locations of a player in video frames of a training video, a set of key pose identifiers for identifying distinctive poses of a sports action associated with a type of sports, and a meta classifier for determining a likelihood that the sports action has happened in a sports video based on the key poses analysis. Responsive to an input sports video being received for real-time action recognition, a set of trained feature models associated with the sports type of the input video are selected and applied to the input video.

Real-time single-view action recognition based on key pose analysis for sports videos

A solution is provided to enhance motion detection and recognition of moving objects associated with various sports by intelligently embedding motion sensors into sport instruments such as tennis rackets, badminton rackets, baseball bats and golf clubs, that are swung in a three-dimensional (3D) space. The motion sensors embedded inside the sport instruments are securely locked and are detachable for replacement. A motion sensor inserted and locked inside a sport instrument is configured to detect motions associated with movements associated with the sport instrument. The motion parameters associated with the detected motion are collected through the embedded motion sensor and analyzed by a motion detection and recognition system. Based on the analysis of the motion parameters, various types of sports performance reports and performance improvement recommendations are generated for users of the sport instruments.

Removable motion sensor embedded in a sport instrument

A solution for composing a multi-angle video from videos captured from different angles is disclosed. A request to compose a multi-angle video is received from a target user, requesting composing a multi-angle video using a video captured by the target user and videos captured by other users nearby the target user. A plurality of videos captured by nearby users are identified based on metadata associated with the captured videos, e.g., geolocation and timestamps of the videos, and presented to the target user. A video sequence including two or more videos from the plurality of videos captured by nearby users is received and the multi-angle video is composed based on the received video sequence.

Multi-angle video editing based on cloud video sharing

A solution is provided for object tracking in a sports video is disclosed. A determination whether a position of the object was identified in a previous video frame is made. If the position of the object was identified in the previous video frame, a new position of the object is identified in a current video frame based on the identified position of the object in the previous video frame. An expected position of the object is identified based on the identified position of the object in the previous video frame and a trained object classification model. A determination is made whether the new position is consistent with the expected position; if the new position is consistent with the expected position, the new position is stored as the position of the object in the current frame.

Fast object tracking framework for sports video recognition

A solution is provided for recommending sports video content samples to users of a recommendation service with enhanced user experience. The recommendation service generates voting scores for sports video content samples according to a voting method, and selects from among the sports content samples according to the voting scores for the sports video content samples. The voting method is based on in part on motion data for a user's sports motion and the motion data is captured by a motion data device. The sports video content samples, e.g., golf videos, can be classified into multiple classes, e.g., golf swing power related videos, and each class is related to a different aspect of the sports motion.

Growing community of inventors

Beijing, China

Zheng Han