58results about How to "Cannot restrict public content" patented technology

Disclosed are a wearable device and control method thereof, a gesture recognition method, a control system of a movable platform and a storage medium. The method comprises the following steps of acquiring key point information of the gesture action of a target user (S110); identifying input instructions according to key point information (S120); generating control instructions according to the input instructions to perform task operations according to the control instructions (S130) .

The present invention relates to a lane line fusion method and device, a vehicle and a storage medium. The lane line fusion method comprises acquiring an environment image around a movable platform, and obtaining an initial lane line set of the movable platform according to the environment image (S110); performing fitting optimization on the initial lane line data in the initial lane line set to obtain a target lane line set, wherein the fitting optimization comprises performing fitting optimization according to the initial lane line data and historical lane line data in a historical lane lineset to obtain a target lane line set (S120), wherein the target lane line set comprises lane lines which are not parallel to each other.

The invention provides a real-time luggage three-dimensional modeling method, electronic equipment and a storage medium, and the method comprises the steps of obtaining local depth maps of target luggage collected in real time from different visual angles through all cameras calibrated in advance; converting the local depth maps acquired at different visual angles into respective corresponding local point cloud data, splicing all the local point cloud data, and determining a three-dimensional model of the target luggage based on the spliced three-dimensional point cloud data. The state of the target luggage is determined according to the three-dimensional model of the target luggage. Due to the fact that the three-dimensional model of the target luggage is constructed through the local depth maps collected at the different field angles, the state and the appearance of the target luggage can be restored from all directions and angles, damage of the luggage in the transportation process can be effectively detected and recorded, and the experience effect of a user is improved.

The invention provides an image processing method, electronic equipment and a storage medium. The method comprises the steps of carrying out the analysis of to-be-processed images of different preset sizes according to a pre-trained first image processing model, and obtaining a ternary image set of the to-be-processed images, inputting the ternary image set and the target training data set into a pre-trained second image processing model for training to obtain a third image processing model, analyzing the to-be-processed image based on the third image processing model to obtain a foreground mask of the to-be-processed image, and performing target background filling on the foreground mask to obtain a target image. The acquisition efficiency of the ternary image and the use flexibility of the image processing model can be improved.

The invention provides a performance evaluation method of a power information system, electronic equipment and a storage medium. The method comprises the following steps: acquiring network topology information of the power information system; acquiring node description information of a communication node, wherein the size of a communication parameter in the node description information is determined based on a distribution model of the communication parameter; integrating the node description information of the communication node and the network topology information to obtain a system model of the power information system; in the system model, searching for a path from a source node in the plurality of communication nodes to a sink node in the plurality of communication nodes, and determining a communication parameter of the path according to the communication parameters of the communication nodes on the path; and generating a performance evaluation result from the source node to the sink node according to the path from the source node to the sink node and the communication parameters of the path. The performance of the power information system can be determined more accurately and efficiently.

The invention provides a luggage three-dimensional identification method, electronic equipment and a storage medium. The method comprises the following steps: acquiring first point cloud data of a target luggage case; calculating a three-dimensional data model of the target luggage case according to the first point cloud data of the target luggage case; and identifying the target luggage case according to comparison between the three-dimensional data model of the target luggage case and the three-dimensional point cloud data of the luggage cases of the preset categories. The defect that a two-dimensional image recognition technology cannot accurately recognize the luggage case under some conditions is overcome, so that the recognition effect on the target luggage case is improved, the luggage case is effectively prevented from being lost in the transmission process, and the user experience effect is improved.

A control method for a movable platform comprises: acquiring a control program file (S110); determining a trigger key for controlling the program file according to the user operation (S120); sending the control program file to the mobile platform configuration (S130); displaying a first key identifier corresponding to a trigger key of the control program file (S140); and controlling the movable platform to execute the task according to an operation of the user on the trigger key or the first key identifier (S150). The control program can be configured on the movable platform, and the invention further provides terminal equipment and a storage medium.

The invention provides a target detection method, an electronic device and a storage medium, a target image is identified through a pre-trained fine-grained target detection model, and the training process of the pre-trained fine-grained target detection model is obtained by retraining a preset target detection model based on an interval loss function. the interval loss function is determined based on the learning interval between the preset fine-grained categories and the loss function of the preset target detection model, and the learning interval between the preset fine-grained categories enables the loss function of the preset target detection model not to pursue learning of the difference characteristics of each instance in the training sample in the model retraining process; therefore, the model complexity of the preset target detection model in the retraining process is not higher than that of an actual model. Therefore, an over-fitting phenomenon in a fine-grained recognition scene can be effectively avoided, and the accuracy of target detection can be improved.

The invention relates to the technical field of machine learning, and particularly discloses a model training method, electronic equipment and a storage medium, and the method comprises the steps: obtaining a pre-trained super network model; determining a plurality of target sub-network models from a preset number of sub-network models of the super-network model; obtaining a plurality of mainstream network models based on open source data training; splicing each target sub-network model as a first backbone network with a first branch network to obtain a plurality of first spliced networks, and splicing each mainstream network model as a second backbone network with a second branch network to obtain a plurality of second spliced networks; performing fine tuning and testing on the plurality of first spliced networks and the plurality of second spliced networks to determine a target network model; and carrying out transfer learning on the target network model to obtain a required model, thereby realizing convenience and intelligence of model training, and improving user experience.

An image processing method, comprising the steps: acquiring a sensor image sensed by an infrared image sensor (S110); and stretching the sensor image in the first and second directions according to the first and second compression ratios to obtain a target image, the stretching ratio in the first direction being greater than the stretching ratio in the second direction (S120), the capabilities of the lens and the infrared image sensor being fully utilized to realize infrared imaging or temperature measurement in a wider range. The invention further provides a shooting device, a movable platform and a storage medium.

The invention provides a camera device calibration method and device and a storage medium, and the method comprises the steps: obtaining an image frame sequence of a target object based on each camera device, estimating a two-dimensional joint coordinate and a three-dimensional skeleton coordinate of the target object shot by each camera device, and obtaining a three-dimensional center coordinate of the three-dimensional skeleton coordinate; analyzing the two-dimensional joint coordinates and the three-dimensional skeleton coordinates shot by each pair of camera devices according to a PNP algorithm to obtain a first transformation matrix and a second transformation matrix, determining a relative transformation matrix between each pair of camera devices according to each first transformation matrix and each second transformation matrix, and repeating the above steps to obtain a relative transformation matrix between each pair of camera devices; three-dimensional center coordinates of the three-dimensional skeleton coordinates are obtained, and a relative transformation matrix between every two camera devices is obtained; and according to the relative change matrix between every two camera devices and a predefined reference coordinate, obtaining a three-dimensional attitude of each camera device relative to the three-dimensional center coordinate of the target object. The objective of the invention is to improve camera equipment calibration efficiency and calibration accuracy.

The invention provides a pilot protection method and device and a storage medium. The method comprises the following steps: acquiring time domain signal data of a target element at a preset sampling frequency; performing fusion processing on the time domain signal data of the plurality of first sampling periods to obtain first time domain signal combined data; based on a machine learning model, judging whether the target element has a fault according to the first time domain signal combination data; when it is judged that the target element breaks down according to the first time domain signal combination data, whether the target element breaks down in a second sampling period or not is judged according to the second time domain signal combination data based on a machine learning model, and the second sampling period is a sampling period after it is judged that the target element breaks down; and when it is judged that the target element has the same type of faults in multiple continuous second sampling periods, controlling the pilot protection system to execute a protection action on the target element. A machine learning model is utilized to realize fault identification of power system elements, so that the protection performance of a smart power grid is remarkably improved.

The photosensitive sensor comprises one or more avalanche diodes, each avalanche diode comprises an active photosensitive region, a first doped region and a second doped region, the active photosensitive region is provided with a first side and a second side opposite to the first side, and the second side is provided with a light incident surface; and the first reflective structure is close to the first side, is arranged opposite to the first doped region and the second doped region, and is used for reflecting light from the active photosensitive region back to the active photosensitive region. The photosensitive sensor provided by the invention has relatively high quantum absorption efficiency. The invention also provides a manufacturing method and a movable platform.

The invention discloses an endoscope camera host and a control method thereof, an endoscope imaging system and a storage medium, and the method comprises the steps: displaying a visual interface which comprises a camera handle key mode region; displaying a key function prompt corresponding to a camera handle key in the camera handle key mode region; and if a control operation of a user on a key on a camera handle carried by the endoscope camera host is detected, executing a preset function corresponding to the key according to the control operation. Therefore, a user can visually know the functions of the keys on the current handle, the control mode of the handle can be known without operating the handle for a trial, and the operation efficiency is improved.

A dual polarized antenna assembly (102), comprising a substrate (10), a first radiator (20) and a second radiator (30); the substrate (10) comprises a first surface (11) and a second surface (12) which are opposite to each other; the first radiator (20) is arranged on the first surface (11), the first radiator (20) is used for receiving or transmitting electromagnetic waves in a first polarization direction, and the first radiator (20) comprises a first high-frequency radiation branch knot (21) and a first low-frequency radiation branch knot (22); the second radiator (30) is arranged on the second surface (12), the second radiator (30) is used for receiving or transmitting electromagnetic waves in a second polarization direction, and the second radiator (30) comprises a second high-frequency radiation branch knot (31) and a second low-frequency radiation branch knot (32); the first polarization direction is different from the second polarization direction, and the projection of the second high-frequency radiation branch knot (31) on the first surface (11) is adjacent to the first low-frequency radiation branch knot (22). Therefore, the problem of polarization mismatch between the controlled terminal and the control terminal when the attitude change of the controlled terminal is large is solved. The invention also relates to a one-hand-held control terminal (1000).

A connecting assembly (102) and holder equipment (1000). The connecting assembly (102) comprises a first connecting piece (10), a second connecting piece (20) and a locking structure (30). The first connecting piece (10) is connected with the holder (101); the second connecting piece (20) is connected with the first connecting piece (10); when the locking structure (30) is in the locking state, the locking structure (30) can lock the first connecting piece (10) and the second connecting piece (20); when the locking structure (30) is in a loosened state, the first connecting piece (10) and the second connecting piece (20) can rotate relatively, so that the holder (101) can be switched between at least two use postures.

The invention discloses a control method of defibrillation equipment, the defibrillation equipment and a storage medium. The method comprises the following steps: acquiring a self-checking result obtained by executing a self-checking task by the defibrillation equipment; and when the defibrillation equipment is in a standby low-power-consumption mode, displaying the self-inspection result through the display component. The electric quantity of the battery can be saved so as to ensure the standby time of the machine, and a user can conveniently check self-checking results such as the equipment state and the detailed fault information of the equipment.

A data transmission method, comprising: receiving a TCP data packet sent by a sending device (S110); generating ACK acknowledgement data according to the TCP data packet, and storing the ACK acknowledgement data to a transmission buffer (S120); and transmitting the latest ACK acknowledgement data in the transmission buffer to the transmission device (S130). Therefore, the stability and the transmission efficiency of data transmission between the transmitting device and the receiving device can be improved. The invention further provides a device, a system, terminal equipment and a storage medium.