Abstract: The disclosure proposes a method for remote upgrade and rollback of Unmanned Aerial Vehicle (UAV) software. The UAV includes a storage area and a UAV software upgrade module; and the storage area is divided into a main storage area, a backup storage area and a data area.

Abstract: An image processing method for sparse image reconstruction, image denoising, compressed sensing image reconstruction or image restoration, comprising: establishing a general linear optimization inverse problem under the 1-norm constraint of a sparse signal; establishing a differentiable deep network model based on convex combination to solve the problem on the basis of standard or learned iterative soft shrinkage thresholding algorithm; and introducing a deep neural network of arbitrary structure into the solving step to accelerate the solving step and reducing a number of iterations needed to reach a convergence. The present disclosure combines the traditional iterative optimization algorithm with the deep neural network of arbitrary structure to improve the image reconstruction performance and ensure fast convergence to meet the current needs of sparse image reconstruction.

Abstract: In a 3D point cloud compression system based on multi-scale structured dictionary learning, a point cloud data partition module outputs a voxel set and a set of blocks of voxels of different scales. A geometric information encoding module outputs an encoded geometric information bit stream. A geometric information decoding module outputs decoded geometric information. An attribute signal encoding module outputs a sparse coding coefficient matrix and a learned multi-scale structured dictionary. An attribute signal compression module outputs a compressed attribute signal bit stream. An attribute signal decoding module outputs decoded attribute signals. A 3D point cloud reconstruction module completes reconstruction. The system is applicable to lossless geometric and lossy attribute compression of point cloud signals.

Abstract: The present disclosure provides a saliency prediction method and system for a 360-degree image based on a graph convolutional neural network. The method includes: firstly, constructing a spherical graph signal of an image of an equidistant rectangular projection format by using a geodesic icosahedron composition method; then inputting the spherical graph signal into the proposed graph convolutional neural network for feature extraction and generation of a spherical saliency graph signal; and then reconstructing the spherical saliency graph signal into a saliency map of an equidistant rectangular projection format by using a proposed spherical crown based interpolation algorithm. The present disclosure further proposes a KL divergence loss function with sparse consistency. The method can achieve excellent saliency prediction performance subjectively and objectively, and is superior to an existing method in computational complexity.

Abstract: A smart home device control method, a medium, a terminal, and an apparatus. By approaching a target home device and obtaining device information thereof, and executing a device control program of a corresponding target home device according to the device information, the user operation is simplified, and the user experience of the home device is improved. The use of hardware multiplexing of a mobile terminal can enrich the function of the home device without significantly increasing the hardware cost of the home device, and reduce the design difficulty and complexity of the home device. The method includes: obtaining a distance between a target home device and a mobile terminal, and obtaining device information of the target home device when the distance is less than or equal to a preset distance.

Abstract: The present disclosure provides a saliency prediction method and system for a 360-degree image based on a graph convolutional neural network. The method includes: firstly, constructing a spherical graph signal of an image of an equidistant rectangular projection format by using a geodesic icosahedron composition method; then inputting the spherical graph signal into the proposed graph convolutional neural network for feature extraction and generation of a spherical saliency graph signal; and then reconstructing the spherical saliency graph signal into a saliency map of an equidistant rectangular projection format by using a proposed spherical crown based interpolation algorithm. The present disclosure further proposes a KL divergence loss function with sparse consistency. The method can achieve excellent saliency prediction performance subjectively and objectively, and is superior to an existing method in computational complexity.

Abstract: In a 3D point cloud compression system based on multi-scale structured dictionary learning, a point cloud data partition module outputs a voxel set and a set of blocks of voxels of different scales. A geometric information encoding module outputs an encoded geometric information bit stream. A geometric information decoding module outputs decoded geometric information. An attribute signal encoding module outputs a sparse coding coefficient matrix and a learned multi-scale structured dictionary. An attribute signal compression module outputs a compressed attribute signal bit stream. An attribute signal decoding module outputs decoded attribute signals. A 3D point cloud reconstruction module completes reconstruction. The system is applicable to lossless geometric and lossy attribute compression of point cloud signals.

Abstract: Techniques involve: acquiring a first source snapshot for a source storage object stored in a source storage device; determining first difference data between the first source snapshot and the source storage object or a second source snapshot for the source storage object, creation time of the first source snapshot being associated with creation time of the second source snapshot; and sending the first difference data to a destination storage device to enable the destination storage device to create a first destination snapshot for a destination storage object stored in the destination storage device based on the first difference data. Such techniques can migrate snapshots more efficiently to improve storage management efficiency.

Abstract: In some embodiments, a control system, a control method and a storage medium are provided. In the method, first motion information of a machine acquired by a first sensor is received; the first motion information is inputted into a deep learning model to obtain a model output, the deep learning model comprising a convolutional neural network (CNN) and a long short-term memory (LSTM); the deep learning model is trained using the first motion information and second motion information acquired by a second sensor; the first sensor and the second sensor having different ways of detecting information and processing the detected information. The model output is used to control the machine.

Abstract: Provided are a tire with new sidewall pattern and a tire mold, which belongs to the technical field of tire, the tire includes a tire body, a sidewall of the tire body has a labeling region, in which multiple pattern units are provided; the pattern units are provided to protrude from the tire body, the pattern unit includes a curved portion having a curved segment and extension ends provided at both ends of the curved segment. The tire mold is used for manufacturing the tire. The tire has better visual performance and mechanical performance.

Abstract: A smart home device control method, a medium, a terminal, and an apparatus. By approaching a target home device and obtaining device information thereof, and executing a device control program of a corresponding target home device according to the device information, the user operation is simplified, and the user experience of the home device is improved. The use of hardware multiplexing of a mobile terminal can enrich the function of the home device without significantly increasing the hardware cost of the home device, and reduce the design difficulty and complexity of the home device. The method includes: obtaining a distance between a target home device and a mobile terminal, and obtaining device information of the target home device when the distance is less than or equal to a preset distance.

Abstract: The present disclosure relates to a demodulation method, apparatus, and device. Some embodiments of the present disclosure are beneficial to improving demodulation performance.

Abstract: Techniques for disk failure control involve determining the number of failed disks in a Redundant Array of Independent Disks (RAID). The techniques further involve comparing the number of failed disks with a predetermined threshold; and in accordance with a determination that the number of failed disks exceeds the predetermined threshold, setting at least one non-failing disk in the RAID into a protection mode to prevent the at least one non-failing disk from being disconnected. Such techniques facilitate prevention of the user data loss in the RAID.

Abstract: The present disclosure relates to a demodulation method, apparatus, and device. Some embodiments of the present disclosure are beneficial to improving demodulation performance.

Abstract: The present disclosure relates to an encoded signal demodulation method, apparatus, and device. Some embodiments of the present disclosure are beneficial to improving demodulation performance.

Abstract: Techniques involve: acquiring a first source snapshot for a source storage object stored in a source storage device; determining first difference data between the first source snapshot and the source storage object or a second source snapshot for the source storage object, creation time of the first source snapshot being associated with creation time of the second source snapshot; and sending the first difference data to a destination storage device to enable the destination storage device to create a first destination snapshot for a destination storage object stored in the destination storage device based on the first difference data. Such techniques can migrate snapshots more efficiently to improve storage management efficiency.

Abstract: Techniques for disk failure control involve determining the number of failed disks in a Redundant Array of Independent Disks (RAID). The techniques further involve comparing the number of failed disks with a predetermined threshold; and in accordance with a determination that the number of failed disks exceeds the predetermined threshold, setting at least one non-failing disk in the RAID into a protection mode to prevent the at least one non-failing disk from being disconnected. Such techniques facilitate prevention of the user data loss in the RAID.

Abstract: Provided are a tire with new sidewall pattern and a tire mold, which belongs to the technical field of tire, the tire includes a tire body, a sidewall of the tire body has a labeling region, in which multiple pattern units are provided; the pattern units are provided to protrude from the tire body, the pattern unit includes a curved portion having a curved segment and extension ends provided at both ends of the curved segment. The tire mold is used for manufacturing the tire. The tire has better visual performance and mechanical performance.

Abstract: In some embodiments, a control system, a control method and a storage medium are provided. In the method, first motion information of a machine acquired by a first sensor is received; the first motion information is inputted into a deep learning model to obtain a model output, the deep learning model comprising a convolutional neural network (CNN) and a long short-term memory (LSTM); the deep learning model is trained using the first motion information and second motion information acquired by a second sensor; the first sensor and the second sensor having different ways of detecting information and processing the detected information. The model output is used to control the machine.