Abstract: A method includes obtaining a spatial configuration of a plurality of imaging devices relative to one another and to a movable object. The imaging devices are coupled to the movable object and comprise a first imaging device configured to operate in a multi-ocular mode and a second imaging device configured to operate in a monocular mode. The method further includes determining at least one of a distance of the movable object to an object or surface lying within a field-of-view of at least one of the imaging devices, a disparity between matched points in stereoscopic images acquired by the first imaging device, or an environment in which the plurality of imaging devices are operated. The distance is determined based in part on the spatial configuration. The method also includes selecting either the first imaging device or the second imaging device to acquire image data based on the determination.

Abstract: A computer-implemented method for controlling an unmanned aerial vehicle (UAV) includes detecting a target marker based on a plurality of images captured by an imaging device carried by the UAV, determining a spatial relationship between the UAV and the target marker based at least in part on the plurality of images, and controlling the UAV to approach the target marker based at least in part on the spatial relationship while controlling the imaging device to track the target marker such that the target marker remains within a field of view of the imaging device.

Abstract: A method for controlling an aircraft includes determining photographing information related to a photographing object, the photographing information indicating an occupying scope of the photographing object in an image to be captured. The method also includes controlling the aircraft to fly to a photographing location based on the photographing information.

Abstract: A surface defect measuring apparatus and method by microscopic scattering polarization imaging is provided. The apparatus mainly comprises a laser, a first converging lens, a rotary diffuser, a second converging lens, a diaphragm, a third converging lens, a pinhole, a fourth converging lens, a polarizer, a half-wave plate, a polarizing beam splitter, an X-Y translation stage, a sample, a microscope lens, a quarter-wave plate, a micro-polarizer array, a camera and a computer. The micro-polarizer array is adopted to realize real-time microscopic scattering polarization imaging of the surface defects; a polarization-degree image is calculated to improve the sensitivity for detecting the surface defects of the ultra-smooth element, and the effective detection of the surface defects of a high-reflective coating element is also realized, and the requirement for rapid detection of the surface defects of a meter-scale large-aperture ultra-smooth element can be met.

Abstract: A method includes generating one or more calibration instructions for calibrating one or more sensors coupled to a movable object and providing at least some of the one or more calibration instructions to a user interface. The at least some of the one or more calibration instructions includes human-readable user instructions for moving the movable object along a predetermined pattern. The method further includes calibrating one or more sensor parameters for the one or more sensors based at least in part on sensor data collected while the movable object moves along the predetermined pattern.

Abstract: Approaches to selection of motion vector (“MV”) precision during video encoding are presented. These approaches can facilitate compression that is effective in terms of rate-distortion performance and/or computational efficiency. For example, a video encoder determines an MV precision for a unit of video from among multiple MV precisions, which include one or more fractional-sample MV precisions and integer-sample MV precision. The video encoder can identify a set of MV values having a fractional-sample MV precision, then select the MV precision for the unit based at least in part on prevalence of MV values (within the set) having a fractional part of zero. Or, the video encoder can perform rate-distortion analysis, where the rate-distortion analysis is biased towards the integer-sample MV precision. Or, the video encoder can collect information about the video and select the MV precision for the unit based at least in part on the collected information.

Abstract: An image processing device acquires at least two first images and down-samples the at least two first images to obtain at least two second images, where a first resolution of the at least two first images is higher than a second resolution of the at least two second images. By using the at least two first images and the at least two second images, the image processing device respectively determines a first depth map corresponding to the at least two first images under a limit of a first disparity threshold, and a second depth map corresponding to the at least two second images under a limit of a second disparity threshold, where the second disparity threshold is greater than the first disparity threshold. The image processing device then combines the determined first depth map with the second depth map to generate a combined depth map.

Abstract: A vehicle detection method includes obtaining a target image and depth information of each pixel in the target image, obtaining a distance value of a vehicle candidate area in the target image according to the target image and the depth information, and determining a detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area.

Abstract: Provided are a seven-speed double clutch transmission and a vehicle. The seven-speed double clutch transmission includes: an outer input shaft and an inner input shaft, a 4/6-speed driving gear and a 2-speed driving gear are sequentially fixed on the outer input shaft, and a 1-speed driving gear, a 3-speed driving gear and a 5/7-speed driving gear are sequentially fixed on the inner input shaft; and a first output shaft and a second output shaft, a 4-speed driven gear, a 2-speed driven gear, a 1-speed driven gear and a 5-speed driven gear, are sequentially fixed on the first output shaft, and a 6-speed driven gear, a reverse gear, a reverse gear synchronizer, a 3-speed driven gear and a 7-speed driven gear are sequentially fixed on the second output shaft.

Abstract: A vehicle detection method includes obtaining a target image and depth information of each pixel in the target image, obtaining a distance value of a vehicle candidate area in the target image according to the target image and the depth information, and determining a detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area.

Abstract: Use of a combination of a histone deacetylase inhibitor and a protein kinase inhibitor in the preparation of a medicament for the treatment or prevention of tumors, a pharmaceutical composition comprising a histone deacetylase inhibitor and a protein kinase inhibitor as active ingredients, and a method for treating or preventing cancers by combining a histone deacetylase inhibitor and a protein kinase inhibitor.

Abstract: The present disclosure relates to systems, methods, and computer-readable storage devices for the coordination of actions between movable objects. For example, a method may coordinate actions between at least a first and a second movable object. The method may detect, by the first movable object, the position of a target. The method may control the position of a first movable object based on the position of the target. A command may be received for the first movable object to perform an action in coordination with the second movable object. In some embodiments, the command may be to take images of the target to create a bullet time effect.

Abstract: Automatic terrain evaluation of landing surfaces, and associated systems and methods are disclosed herein. A representative method includes receiving a request to land a movable object and, in response to the request, identifying a target landing area on a landing surface based on at least one image of the landing surface obtained by the movable object. The method can further include directing the movable object to land at the target landing area.

Abstract: Methods, systems, and articles of manufacture configured to operate an aerial vehicle are provided. Various embodiments may be implemented with an aerial vehicle. In one exemplary implementation, a method of operating an aerial vehicle may include identifying, from image data, a set of predetermined features based on one or more invariant properties associated with the predetermined features. The predetermined features may be associated with predetermined physical locations. Based on the image locations of the predetermined features within the image data and the predetermined physical locations of the predetermined features, a system may be configured to determine at least one of a location and an orientation of the aerial vehicle. The disclosed embodiments may provide enhanced accuracy, usability, and robustness in tracking the location and orientation of an aerial vehicle under various operation conditions.

Abstract: A method for controlling a movable object is provided. A user input that includes a first parameter corresponding to a first coordinate system is received and an operation mode is determined. In response to determining the operation mode being a first operation mode, a second parameter corresponding to a second coordinate system is generated and the movable object is controlled to move based on the second parameter. In response to determining the operation mode being a second operation mode, the first parameter is translated to a third parameter corresponding to the second coordinate system and the movable object is controlled to move based on the third parameter.

Abstract: Identifying interfering features in the detection of an environment adjacent to a mobile platform, and associated systems and methods are disclosed herein. A representative method can include identifying candidate regions from a color image obtained by a color vision sensor carried by a mobile platform, filtering out a first region subset of regions based, at least in part, on non-image data obtained by a second sensor carried by the mobile platform, determining a second subset of regions as corresponding to an interfering feature based, at least in part, on color information, and performing environment detection based, at least in part, on the second subset of regions. Furthermore, the method can comprise transforming data corresponding to the subset of regions to integrate with non-color environment data obtained from another sensor carried by the mobile platform.

Abstract: Embodiments of the present disclosure provide an image processing method applied in an unmanned aerial vehicle (UAV), the UAV including an imaging device in two or more directions. The method includes obtaining an image to be processed in each of the two or more directions; determining a first direction in the two or more directions and obtaining a first direction reference value based on the image to be processed in each of the two or more directions, the first direction reference value being used to determine whether to update key reference frames corresponding to the two or more directions respectively; and updating the key reference frames corresponding to the two or more directions respectively if the first direction reference value meets a preset condition.

Abstract: Approaches to selection of motion vector (“MV”) precision during video encoding are presented. These approaches can facilitate compression that is effective in terms of rate-distortion performance and/or computational efficiency. For example, a video encoder determines an MV precision for a unit of video from among multiple MV precisions, which include one or more fractional-sample MV precisions and integer-sample MV precision. The video encoder can identify a set of MV values having a fractional-sample MV precision, then select the MV precision for the unit based at least in part on prevalence of MV values (within the set) having a fractional part of zero. Or, the video encoder can perform rate-distortion analysis, where the rate-distortion analysis is biased towards the integer-sample MV precision. Or, the video encoder can collect information about the video and select the MV precision for the unit based at least in part on the collected information.

Abstract: A method for controlling target tracking includes determining whether a tracking mode of a movable object is a manual tracking mode or an automatic tracking mode; when it is determined that the tracking mode is the manual tracking mode, determining a target for the movable object from one or more images based on a user input; when it is determined that the tracking mode is the automatic tracking mode, having the movable object determine the target automatically; and directing the movable object to track a target object using the target.

Abstract: The present disclosure is directed to systems and methods for providing dynamic communication threads in response to a detected interaction with a sponsored digital content item. For example, systems and method described herein detect a user interaction with a sponsored digital content item and generate a screened communication thread between the user and the sponsor that is not available to the sponsor. The screened communication thread serves as a reminder to the user of the sponsored digital content item. Systems and methods described herein convert the screened communication thread to an open communication thread based on user interaction with the screened communication thread (e.g., after the user submits a reply in the screened communication thread). Thus, systems and methods described herein protect the user's online privacy unless and until the user indicates a desire to interact with the sponsor.