Abstract: A method includes receiving a plurality of images from an imaging device carried by a movable object. The method further includes determining whether an environment type of the movable object is a first type or a second type according to sensing data received from one or more sensors of the movable object, identifying a target based on the plurality of images using a first method in response to determining that the environment type is the first type and using a second method different from the first method in response to determining that the environment type is the second type, and determining state information of the movable object or the target based on the plurality of images.

Abstract: A method for determining a target direction for a movable object includes providing an image on a computer-implemented display, obtaining a position of a selected point on the image in response to a user selecting the point on the image, and determining the target direction based on the position of the selected point on the image.

Abstract: A method for controlling a mobile device includes obtaining a measurement image of a calibration device including a plurality of calibration objects, obtaining position-attitude information of the mobile device according to the measurement image, predicting a movement status of the mobile device according to the position-attitude information and a control instruction to be executed, and, in response to the predicted movement status not meeting a movement condition, constraining movement of the mobile device so that the movement status after constraining meets the movement condition.

Abstract: A method for positioning a movable platform, and related device and system are provided. The method includes obtaining an image obtained by photographing a positioning auxiliary device. The positioning auxiliary device is configured with a plurality of calibration objects of at least two different size types. The method also includes detecting image objects of each calibration object of each size type in the image, and selecting image objects of calibration objects of one or more size types from the detected image objects. Further, the method includes according to the selected image objects, determining attitude information and/or position information of the movable platform with respect to the positioning auxiliary device.

Abstract: A baseline adjustment method includes acquiring a first image of an object by a first imaging device of an imaging apparatus, acquiring a second image of the object by a second imaging device of the imaging apparatus, determining a binocular disparity between the first and second image and determining an object distance based at least on the binocular disparity by the controller, and automatically adjusting a baseline according to the object distance by a baseline adjustment mechanism. The object distance represents a distance between the imaging apparatus and the object. The baseline represents a relative distance between the first and second imaging device. The baseline is being adjusted to fall within a range approximately between a minimum and a maximum baseline. The maximum baseline is defined by the object distance and an angle-of-view of at least one of the first or the second imaging device.

Abstract: A method for processing image information in an image to determine a movement for a movable object. The method includes detecting whether the image includes a water surface or a sky based on the image information in the image, And, in response to detecting that the image includes the water surface or the sky, determining a technique from a plurality of techniques for calculating a depth map, generating the depth map using the technique, and determining a movement parameter for the movable object using the depth map.

Abstract: A method for supporting visual tracking includes receiving a plurality of image signals indicative of a plurality of image frames captured by an imaging device over a period of time while the imaging device is in motion. Each image frame includes a plurality of pixels. The method further includes obtaining motion characteristics of the imaging device based on a plurality of motion signals, and analyzing the plurality of image signals based on the motion characteristics of the imaging device, so as to compute movement characteristics associated with the plurality of pixels.

Abstract: A system for automatically adjusting a baseline of an imaging system for stereoscopic imaging and methods for making and using same. The imaging system includes a plurality of imaging devices that cooperate via a baseline adjustment mechanism. The imaging devices can acquire images of an object of interest and ascertain an object distance between the stereoscopic imaging system and the object of interest using triangulation. Based on the object distance, the baseline adjustment mechanism automatically adjusts a baseline between any pair of imaging devices. The baseline can be reduced when the object of interest is proximate to the imaging system and can be increased when the object of interest is distal. Once the baseline has been adjusted, one or more extrinsic parameters of the imaging devices are calibrated using a two-step optimization method. The imaging system is suitable for use aboard a mobile platform such as an unmanned aerial vehicle.

Abstract: A method for supporting visual tracking includes receiving a plurality of image frames captured at different times using an imaging device. Each of the plurality of image frames includes a plurality of pixels associated with a plurality of feature points. The method further includes analyzing the plurality of image frames to compute movement characteristics of the plurality of feature points and identifying a tracking feature relative to a background feature based on the movement characteristics of the plurality of feature points.

Abstract: A method for controlling palm landing of an unmanned aerial vehicle (“UAV”) includes detecting a flight status of the UAV under a predetermined condition. The method also includes controlling the UAV to land on a palm of a user when the flight status is a hover state and when the palm is located under the UAV.

Abstract: A method for recognizing a posture includes acquiring a depth image of a scene, and obtaining point clouds of an operator based on the depth image of the scene. The method also includes separating point clouds of an arm from the point clouds of the operator and obtaining a characteristic point from the point clouds of the arm. The method further includes determining a location relationship between the characteristic point and the operator and determining a posture of the operator based on the location relationship.

Abstract: A terminal device includes one or more processors. The one or more processors are configured to obtain a marker in an image captured by a photographing device, determine position-attitude information of the photographing device relative to the marker, and control the mobile object according to the position-attitude information of the photographing device relative to the marker.

Abstract: An imaging apparatus includes first and second imaging devices configured to capture first and second images of a scene, respectively. The first and second images include multiple first image blocks relative to a first coordinate system and multiple second image blocks relative to a second coordinate system, respectively. The apparatus further includes a processor configured to calibrate one or more first image blocks and one or more corresponding second image blocks using the first and second coordinate systems, convert each calibrated first image block to an intensity image and a first depth map, convert each calibrated second image block to a grayscale image, and generate a second depth map associated with the second image by enhancing a resolution of the first depth map for each calibrated first image block based on calculating a relationship between the intensity image and the grayscale image for each calibrated first and second image blocks.

Abstract: A method includes receiving a plurality of images from an imaging device carried by a movable object. The method further includes determining whether an environment type of the movable object is a first type or a second type according to sensing data received from one or more sensors of the movable object, identifying a target based on the plurality of images using a first method in response to determining that the environment type is the first type and using a second method different from the first method in response to determining that the environment type is the second type, and determining state information of the movable object or the target based on the plurality of images.

Abstract: A method of processing an image having a first set of pixels includes generating a depth map of the image that includes a second set of pixel values representative of distances of objects in the image, identifying a plurality of different depths at which the objects are located in the image based on the depth map, using the depth map to determine a relative distance between one identified depth in the plurality of different depths and each of the other identified depths in the plurality of different depths, and blurring pixels in the first set of pixels based on each determined relative distance.

Abstract: A method for calibrating an imaging device includes calculating attitude information of the imaging device relative to a screen based at least in part on an image captured by the imaging device, generating a calibration signal based at least in part on the attitude information, displaying the calibration signal on the screen, and displaying a guiding signal on the screen.

Abstract: The present disclosure provides a gesture recognition method. The method includes the following steps: acquiring a depth image of a user; determining a point set of a two-dimensional image indicating a palm based on a depth information of the depth image; and, determining a gesture based on the point set.

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, removing outlier points on a second border line in the second corrected target image, performing straight-line fitting on the second border line with the outlier points removed 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, if the preset correction condition is satisfied, applying the correction distortion coefficient to subsequent image correction to obtain better corrected images.

Abstract: A method for enhancing image resolution includes obtaining one or more images of a scene. The one or more images are associated with a first depth map. The method further includes determining a second depth map of the scene based upon the one or more images. The second depth map has a higher resolution than the first depth map.

Abstract: Systems and methods for obstacle detection and state information determination are provided. In some embodiments, a movable object may carry one or more imaging devices. The imaging devices may be arranged on the movable object so as to have a field of view oriented vertically relative to the movable object. The arrangement of the imaging device may complement or supplant existing arrangement schemes and provide efficient, multi-functional and cost-effective means of arranging imaging devices on movable objects.