Abstract: A control method for a mobile platform includes obtaining a captured image, determining a target first characteristic part of a target object from the captured image, determining a second characteristic part of the target object in the captured image, and switching from tracking the second characteristic part to tracking the target first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition.

Abstract: Disclosed herein are high Tm RNA nanostructures that can be composed of one or more modules or motifs to build RNA nanostructures with or without layers. The RNA nanostructures can have a core domain and three or more double-stranded arms and formulations thereof to conjugate high copy numbers of therapeutics, pH responsive or enzyme cleavable drug cargo. Also described herein is a design strategy for generation of synthetic RNA oligonucleotides that can self assemble into highly thermostable RNA structures. Also described herein are uses of the RNA nanostructures described herein.

Abstract: A wearable device and its control method, a gesture recognition method, a movable platform control system and a storage medium are provided. The control method may include acquiring key point information of a gesture action of a target user, recognizing an input instruction based upon the key point information, and generating a control instruction based upon the input instruction and executing a task operation according to the control instruction.

Abstract: A method is provided for controlling flight of an aircraft carrying an imaging device. The imaging device is mounted at a gimbal. The method includes in response to receiving a triggering operation that triggers the aircraft to operate in an image control mode, obtaining an environment image captured by the imaging device, recognizing a gesture of a target user in the environment image, and in response to recognizing that the gesture of the target user is a start-flight gesture, generating a takeoff control command to control the aircraft to take off. Obtaining the environment image includes after obtaining the triggering operation, controlling the gimbal to rotate to control the imaging device to scan and photograph in a predetermined photographing range, and obtaining the environment image including a characteristic part of the target user that is captured by the imaging device through scanning and photographing in the predetermined photographing range.

Abstract: Provided is a CZT semiconductor activity meter and an activity measuring device, which relate to the field of medical apparatus and instruments. The CZT semiconductor activity meter includes a shell, a CZT probe, a package substrate and a processing module, wherein the CZT probe is arranged on an end of the shell, the package substrate is arranged at the middle part of the shell and abuts against an inner wall of the shell, the CZT probe is connected to one side of the package substrate, the other side of the package substrate and the inner wall of the shell together form a package inner cavity, and the processing module is accommodated in the package inner cavity and connected to the package substrate. The CZT semiconductor activity meter has a small volume, is convenient to operate, does not require manual control during detection, and can be used at room temperature.

Abstract: A machine vision-based tree recognition method and device are provided. The machine vision-based tree recognition method may include obtaining a top view image containing a tree and processing the top view image to obtain pixel position information of a tree center of the tree and tree radius information corresponding to the tree center in the top view image.

Abstract: A control method for a mobile platform includes obtaining a captured image, determining a target first characteristic part of a target object from the captured image, determining a second characteristic part of the target object in the captured image, and switching from tracking the second characteristic part to tracking the target first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition.

Abstract: Provided is a CZT semiconductor activity meter and an activity measuring device, which relate to the field of medical apparatus and instruments. The CZT semiconductor activity meter includes a shell, a CZT probe, a package substrate and a processing module, wherein the CZT probe is arranged on an end of the shell, the package substrate is arranged at the middle part of the shell and abuts against an inner wall of the shell, the CZT probe is connected to one side of the package substrate, the other side of the package substrate and the inner wall of the shell together form a package inner cavity, and the processing module is accommodated in the package inner cavity and connected to the package substrate. The CZT semiconductor activity meter has a small volume, is convenient to operate, does not require manual control during detection, and can be used at room temperature.

Abstract: A control method for a mobile platform includes obtaining a captured image, identifying one or more candidate first characteristic parts from the captured image, determining a second characteristic part of a target object in the captured image, determining one or more matching parameters each corresponding to one of the one or more candidate first characteristic parts based on the one or more candidate first characteristic parts and the second characteristic part, determining a target first characteristic part of the target object from the one or more candidate first characteristic parts based on the one or more matching parameters, and switching from tracking the second characteristic part to tracking the target first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition.

Abstract: A wearable device and its control method, a gesture recognition method, a movable platform control system and a storage medium are provided. The control method may include acquiring key point information of a gesture action of a target user, recognizing an input instruction based upon the key point information, and generating a control instruction based upon the input instruction and executing a task operation according to the control instruction.

Abstract: An image processing method includes: obtaining target image data, the target image data including a target image and depth data corresponding to various pixels in the target image; processing the target image data to obtain a confidence level feature map of semantics of the target image data; and based on the confidence level feature map, determining a position of a target region in the target image data.

Abstract: An imagery method includes obtaining a plurality of images of an object and selecting one or more images related to a moment from the plurality of images based on a selection rule. The plurality of images are captured by one or more imaging devices within a period of time while the object is being tracked. A plurality of triggers each are configured to trigger at least one of a starting time or a stopping time of the period of time for capturing the plurality of images. The plurality of triggers include a detection based on motion/state estimation of the object.

Abstract: A neural network acceleration device includes a processor and a storage medium. The storage medium stores instructions that, when executed by the processor, cause the processor to obtain an input feature value, perform computation processing on the input feature value to obtain an output feature value, and in response to a fixed-point format of the output feature value being different from a predetermined fixed-point format, perform at least one of a low bit shifting operation or a high bit truncation operation on the output feature value according to the predetermined fixed-point format to obtain a target output feature value. A fixed-point format of the target output feature value is the predetermined fixed-point format.

Abstract: An imagery method includes obtaining a plurality of images of an object captured using one or more imaging devices within a period of time while the object is being tracked, performing motion and/or state estimation of the object for the period of time, and selecting one or more images related to a moment from the plurality of images based on the motion and/or state estimation of the object.