Sz Dji Technology Co., Ltd.

Sz Dji Osmo Technology Co., Ltd.

Tencent Technology (shenzhen) Company Limited

Bgi Tech Solutions Co., Ltd

Shenzhen Horizon Robotics Technology Co., Ltd.

Bgi Shenzhen

Bgi-shenzhen Co., Limited

Ye Tao

Weifeng Liu

Zhiyuan Zhang

Shunnian Li

Liutao Zhang

Yayun Zheng

Zhuo Guo

Guanhua Su

Bingzhen Yang

Heli Zhong

Yukun He

Zisheng Cao

Jianyu Song

Renli Shi

Taiwen Liang

Xiaojun Li

Xiaohang Zhong

Jun Wu

Zihan Chen

Chaobin Chen

Ran Liao

Tao Deng

Dongjun Zhang

Xueli Yan

Mingyu Wang

Cong Zhao

Linchao Bao

Xuyang Feng

Xun Xu

Zhongqian You

Yong Hou

Hongbo Jin

Huan Jin

Xiaohu Yang

Ruochen Tang

Guanliang Su

Kui Wu

Guodong Zhu

Weiming He

Luting Song

Di Shao

Zequn Zheng

Zhijun Zheng

Shuheng Liang

Hongzhi Zhang

Li Bao

The present disclosure includes a method for training a sequence mining model. In the method, a first sequence sample in a target service scenario is obtained. A tag status of the first sequence sample is obtained, the tag status of the first sequence sample indicating a proportion of the first sequence sample that has corresponding tag information. A sub-model from a sequence mining frame is selected according to the tag status to construct the sequence mining model. Also, the sequence mining model is trained by using the first sequence sample. The sequence mining frame includes a first sub-model configured to obtain a latent representation, a second sub-model configured to determine the target tag information when the tag status meets a first condition, and a third sub-model being configured to determine the target tag information when the tag status meets a second condition.

Method for training sequence mining model, method for processing sequence data, and device

Disclosed are an extrinsic camera parameter calibration method, apparatus and system. The method includes: obtaining a calibration image photographed for a target location in a calibration cabin by a first camera provided therein; determining calibration feature information of the target location from the calibration image; obtaining reference feature information pre-determined from a reference image photographed for a target location in a reference cabin by a second camera provided therein; determining position-posture change data of the first relative to the second camera based on a calibration location of the calibration feature information in the calibration image and a reference location of the reference feature information in the reference image; and determining an extrinsic parameter of the first camera based on the position-posture change data. The extrinsic parameter of the first camera can be calibrated in real time and is closer to a currently actual state of the first camera when used.

Extrinsic camera parameter calibration method, extrinsic camera parameter calibration apparatus, and extrinsic camera parameter calibration system

The present invention discloses a heading generation method of an unmanned aerial vehicle including the following steps of: making a preliminary flight for selecting a point of view to record flight waypoints, the waypoints including positioning data and flight altitude information of the unmanned aerial vehicle; receiving and recording flight waypoints of the unmanned aerial vehicle; generating a flight trajectory according to waypoints of the preliminary flight; editing the flight trajectory to obtain a new flight trajectory; and transmitting the edited new flight trajectory to the unmanned aerial vehicle to cause the unmanned aerial vehicle to fly according to the new flight trajectory. The present invention further relates to a heading generation system of an unmanned aerial vehicle.

Heading generation method and system of unmanned aerial vehicle

An image processing method includes, when an edit triggering event for a target image is detected, acquiring description information associated with the target image. The description information includes interference information that affects image quality occurred in a shooting process of the target image. The description information includes at least one of motion data of a carrying member that carries a shooting module configured to acquire the target image or motion data of a moving object on which the carrying member is mounted. The method further includes editing image clips in the target image which are associated with respective interference information of the description information to obtain a processed target image.

Video processing method, device and image system

A method for adjusting image exposure includes, while continuously tracking one or more targets using an imaging device mounted on a movable object, receiving a user indication of a target for imaging, determining a first representation of the target, capturing a first image that includes the first representation of the target, determining an exposure parameter for the imaging device using data in the first image that corresponds to the first representation of the target, determining a second representation of the target, capturing a second image including the second representation of the target, and adjusting the exposure parameter for the imaging device using data in the second image that corresponds to the second representation of the target.

Target-based image exposure adjustment

A video processing method includes determining a shooting template that includes background music, one or more gimbal movement trajectories, and one or more shooting elements, sending one or more parameters corresponding to the one or more gimbal movement trajectories to a gimbal to control the gimbal to drive a shooting device to shoot according to the one or more gimbal movement trajectories, obtaining information of at least one video segment, and generating a video file based on the at least one video segment.

Video processing method and device, shooting system, and computer-readable storage medium

A method includes receiving state information of a virtual movable object in a simulated movement from a movement simulator associated with a movable object and determining movement information for the simulated movement by associating the state information with context information. The state information includes information identifying a location of the virtual movable object in a virtual space. The context information includes information identifying a location of the user terminal, which is at a different location than the movable object in a real space. The method further includes displaying the simulated movement on a display associated with the user terminal based on the movement information, and receiving control data to control the simulated movement in the virtual space using the user terminal when the movable object is in simulation and to control movement of the movable object in the real space when the movable object is in real operation.

System and method for supporting simulated movement

A method for presenting operational information of a mobile platform includes collecting diagnostic data and travel route data associated with an operation of the mobile platform, and integrating the travel route data with the diagnostic data for presentation. The diagnostic data includes at least one of platform diagnostic data or remote control data. The remote control data is generated by a remote controller associated with the mobile platform or generated by a computer device.

Method, device and system for presenting operation information of a mobile platform

A propulsion system includes a driving device and a propeller coupled with the driving device. The driving device includes a body portion and a lock portion disposed on the body portion. The lock portion includes a first snap-fitting portion. The propeller includes a hub having a receiving hole, a plurality of blades connected to the hub, and a second snap-fitting portion arranged on an inner wall of the receiving hole and configured to snap with the first snap-fitting portion.

Driving device, propeller and propulsion system

A method of operating a mobile platform includes determining a threshold angle relative to the mobile platform of an imaging device mounted to the mobile platform that avoids obstruction of a field-of-view of the imaging device by one or more components of the mobile platform, and controlling the mobile platform according to the threshold angle.

Systems and methods for improved mobile platform imaging

A gimbal photographing method includes obtaining an external signal, processing the external signal to generate one or more gimbal action control instructions and one or more photographing control instructions, controlling a gimbal to perform a corresponding action according to at least one of the one or more gimbal action control instructions, and controlling a camera device to perform photographing according to at least one of the one or more photographing control instructions. The at least one of the one or more photographing control instructions cause the camera device to photograph along with the action performed by the gimbal during at least part of a whole photographing process.

Gimbal photographing method, gimbal camera system, and storage medium

A display device includes a display area configured to display one or more images of a virtual reality (VR) environment or an augmented reality (AR) environment, one or more sensors configured to obtain region-of-interest (ROI) data of a user in response to the user wearing the display device and looking at the one or more images of the VR environment or the AR environment displayed on the display area, and one or more processors. The one or more processors are individually or collectively configured to select one or more ROI zones from a plurality of zones based on the ROI data and effect display of the one or more ROI zones on the display area to the user. The plurality of zones are used to divide the one or more images of the VR environment or the AR environment on the display area.

Systems and methods for processing image data based on region-of-interest (ROI) of a user

An image processing method includes, when an edit triggering event for a target image is detected, acquiring description information associated with the target image. The description information includes interference information that affects image quality occurred in a shooting process of the target image. The method further includes editing image clips in the target image which are associated with respective interference information of the description information to obtain a processed target image.

Systems, devices and methods are provided for training a user to control a gimbal in an environment. The systems and methods provide a simulation environment to control a gimbal in a virtual environment. The virtual environment closely resembles a real control environment. A controller may be used to transmit simulation commands and receive simulated data for visual display.

Systems and methods for gimbal simulation

Growing community of inventors

Shenzhen, China

Ye Tao