Abstract: An image processing method includes correcting a target image based on an initial distortion coefficient to obtain a first corrected target image, performing straight-line fitting on a first border line in the first corrected target image to calculate a first distortion metric value and a correction distortion coefficient, correcting the target image based on the correction distortion coefficient to obtain a second corrected target image, performing straight-line fitting on a second border line in the second corrected target image to calculate a second distortion metric value, detecting whether a preset correction condition is satisfied based on at least one of the first distortion metric value or the second distortion metric value, and configuring the correction distortion coefficient as the initial distortion coefficient if the preset correction condition is not satisfied.

Abstract: A method of controlling an unmanned aerial vehicle (UAV) includes receiving an image from one or more vision sensors of the UAV. The image is captured while the UAV is in flight and includes a marker within an environment. The marker has a visual pattern. The method further includes identifying the visual pattern to determine a plurality of instructions encoded in the visual pattern, and controlling, in response to the plurality of instructions, the UAV to perform an action including at least one of adjusting position of a payload, swapping a payload, or capturing an image of a selected subject.

Abstract: A method for generating a first person view (FPV) of an environment includes, with aid of one or more processors individually or collectively, analyzing stereoscopic video data of the environment to determine environmental information and generating augmented stereoscopic video data of the environment by fusing the stereoscopic video data and the environmental information.

Abstract: A method for controlling a movable object includes detecting a live object within a proximity of the movable object, determining an operation mode to operate the movable object with the live object detected within the proximity of the movable object, and applying a control scheme associated with the operation mode to control an operation of the movable object.

Abstract: Methods and associated systems and apparatus for controlling a moveable device are disclosed herein. The moveable device includes an image-collection component and a distance-measurement component. A representative method includes generating an image corresponding to the operator and generating a first set of distance information corresponding to the operator. The method identifies a portion of the image in the generated image and then retrieves a second set of distance information from the first set of distance information based on the identified image portion corresponding to the operator. The method then identifies a gesture associated with the operator based on the second set of distance information. The method then further generates an instruction for controlling the moveable device based on the gesture.

Abstract: A method of using an unmanned aerial vehicle (UAV) to guide a target includes receiving, via the UAV, a signal indicative of a target area for guiding the target, determining an indicator based on a location of the UAV and/or a location of the target area while the target is in motion, and performing, via the UAV, an operation in response to the indicator.

Abstract: Systems and methods are provided for positing an unmanned aerial vehicle (UAV) in an environment. The UAV may be able to identify visual markers and patterns in the environment. The UAV can distinguish between visual markers and other features in the environment. The visual markers can be analyzed with visual sensors to determine the position of the UAV in the environment. The visual markers can encode instructions to the UAV.

Abstract: A method for supporting target tracking includes obtaining a feature model for a target that represents imagery characteristics of the target, extracting one or more features from one or more images captured by an imaging device carried by a movable object, and applying the feature model on the one or more features to determine similarity between the one or more features and the feature model.

Abstract: A method for processing video data of an environment includes, with aid of one or more processors individually or collectively, obtaining in or near real-time a reference position of an imaging device located on a movable object based on one or more previously traversed positions of the imaging device, and modifying an image frame in the video data to obtain a modified image frame based on the reference position of the imaging device and an actual position of the imaging device at which the image frame is taken. The one or more previously traversed positions are obtained using at least one sensor on the movable object.

Abstract: A system for controlling an unmanned aerial vehicle (UAV) includes one or more processors configured to receive sensor data from one or more sensors carried by the UAV. The sensor data is indicative of at least a state of the UAV. The one or more processors are further configured to select a flight mode from a plurality of different flight modes based at least in part on the sensor data and effect operation of the UAV in accordance with a set of operating rules associated with the selected flight mode.

Abstract: A hover control method includes obtaining a flight velocity of an unmanned aerial vehicle (UAV), obtaining an image frame as a keyframe in response to that the flight velocity satisfies a preset condition, and controlling hovering of the UAV using the keyframe as a reference object.

Abstract: An unmanned aerial vehicle (UAV) includes one or more propulsion units that effect flight of the UAV, an application processing circuit configured to verify a validity of a system image of the UAV in a secure environment, and a flight control circuit operably coupled to the application processing circuit. Generation and/or transmission of control signals from the flight control circuit to one or more electronic speed controllers (ESC controllers) is prevented prior to verification of the validity of the system image.

Abstract: A method for controlling flight includes displaying prompt information in a picture received from an aerial vehicle, dividing the picture into at least two portions based on the prompt information, obtaining a location of a click operation on the picture, and controlling a flight direction of the aerial vehicle based on the location and the prompt information.

Abstract: Systems and methods are provided for guiding a target object with an unmanned aerial vehicle (UAV) in an environment. The UAV may be able to recognize and locate the target object. The UAV can be configured to communicate the actions and behavior of the target object to a user through a user device in communication with the UAV. The UAV can provide positive and negative stimuli to the target object to encourage an action or behavior. The UAV can be configured to recognize and manage waste generated by the target object.

Abstract: A system for controlling an unmanned aerial vehicle (UAV) includes a first user interface configured to receive a first user input and a second user interface configured to receive a second user input. The first user input provides one or more instructions to effect an autonomous flight of the UAV. The second user input provides one or more instructions to modify the autonomous flight of the UAV, The autonomous flight includes a flight towards a target.

Abstract: Embodiments of the present disclosure disclose a method for modifying a segmentation model based on artificial intelligence, a device and a storage medium. The method may include: acquiring a model parameter of the segmentation model, and performing a training on a feature vector corresponding to a preset generalized feature of a first training corpus via a neural network so as to acquire a model parameter of the preset generalized feature; performing a word segmentation on the first training corpus according to the model parameter of the segmentation model and the model parameter of the preset generalized feature, so as to acquire a segmentation result; and comparing the segmentation result with the first training corpus according to a preset rule, and modifying the model parameter of the segmentation model and a parameter of the neural network according to a comparison result.

Abstract: Embodiments of the present disclosure disclose a method and an apparatus for customizing a word segmentation model based on artificial intelligence, a device and a medium. The method includes the followings. A customized segmentation training corpus is acquired. A first preset word segmentation model is rectified with an increment training method or a weight intervention method, based on the customized segmentation training corpus, to obtain a customized word segmentation model corresponding to the customized segmentation training corpus.

Abstract: Embodiments of the present disclosure disclose a word segmentation method based on artificial intelligence, a server and a storage medium. The word segmentation method may include: acquiring a corpus to be segmented and a segmentation model corresponding to a preset segmentation template; matching the corpus to be segmented with the segmentation model according to a preset matching algorithm, and acquiring a target phrase satisfying a first preset rule in the corpus to be segmented; modifying an emission matrix corresponding to the segmentation model and the corpus to be segmented according to the target phrase; and performing a word segmentation on the corpus to be segmented according to the emission matrix modified, to acquire a first segmentation result.

Abstract: An unmanned aerial vehicle (UAV) includes a vehicle body and a multi-ocular imaging assembly. The multi-ocular imaging assembly includes at least two imaging devices disposed in and fixed to the vehicle body.

Abstract: A system of virtual sightseeing using unmanned aerial vehicles (UAV) and methods of making and using same. The virtual sightseeing system can include a plurality of UAVs arranged over a geographical area of interest in one or more ground configurations. In response to a sightseeing request, one or more UAVs are activated and deployed to a sightseeing region of interest. The UAVs travel to the region of interest and, upon arriving, acquire data for presentation in real-time. The data can include both visual and non-visual data from the region of interest and can be presented in integrated fashion in a virtual reality terminal. The virtual sightseeing is supervised by an operational subsystem that is responsible for efficient allocation of UAVs in response to multiple sightseeing requests. Even if physically separate, the subsystems of the virtual sightseeing system can communicate via a data communication subsystem, such as a wireless network.