Abstract: The human body 3D key point detection method includes: acquiring a to-be-detected image, the to-be-detected image including first human body image data; inputting the to-be-detected image into a key point extraction model to acquire N first 3D heatmaps of N human body 3D key points in the first human body image data, each first 3D heatmap representing a Gaussian distribution of one human body 3D key point in first human body image data in a predetermined space, where N is a positive integer; and determining coordinate information about the N human body 3D key points in the first human body image data based on the N first 3D heatmaps.

Abstract: A method and apparatus for promoting a motion, an electronic device and a storage medium, relating to the field of image recognition technology are provided. An embodiment of the method may include: acquiring a user motion image, and acquiring three-dimensional recognition coordinates of body key points recognized in the user motion image; determining, based on the three-dimensional recognition coordinates, a user motion matching the user motion image; screening, according to a mapping relationship between user motion and body key points, a target body key point among all of the recognized body key points; acquiring three-dimensional standard coordinates of the target body key point corresponding to the user motion; and prompting a motion based on values of differences between the three-dimensional standard coordinates of the target body key point and the three-dimensional recognition coordinates of the target body key point.

Abstract: The present application discloses a virtual object driving method, an apparatus, an electronic device and a readable storage medium, which relate to technical fields of artificial intelligence and deep learning. A specific implementing solution is as follows: obtaining a target image of a real object acquired by a camera when the real object makes a limb movement; inputting the target image into a coordinate acquisition model to obtain coordinates of a plurality of key points on a limb of the real object; determining a posture of the limb of the real object according to coordinates of each key point; driving, according to the posture of the real object, a virtual object displayed on a screen to present the limb movement of the real object. The method greatly reduces operation complexity and cost consumption when driving a virtual image.

Abstract: A method and apparatus for generating a 3D joint point regression model are provided. An embodiment of the method includes: acquiring a sample image with a 2D label and a sample image with a 3D label; training part of channels of an output layer of a basic 3D joint point regression model, with the sample image with the 2D label as a first input, and with a joint point heat map set corresponding to the 2D label as a first expected output; and training all of the channels of the output layer, with the sample image with the 3D label as a second input, with a joint point heat map set corresponding to the 3D label as a first part output of a second expected output and with a joint point depth information map set corresponding to the 3D label as a second part output of the second expected output.

Abstract: The present application discloses an image processing method, an apparatus, a device and a storage medium, and relate to computer vision, augmented reality and deep learning technology in the field of computer technology. A specific implementation includes: determining, by a detection model, a 3D thermal distribution map and a 3D position offset of body key points of a target character in an image to be detected, determining predicted 3D coordinates of the body key points based on the 3D thermal distribution map of the body key points, correcting the predicted 3D coordinates according to the 3D position offset of the body key points, so that accurate 3D coordinates of the body key points can be obtained, and performing corresponding processing according to the gesture or motion of the target character.

Abstract: The present application discloses a virtual object driving method, an apparatus, an electronic device and a readable storage medium, which relate to technical fields of artificial intelligence and deep learning. A specific implementing solution is as follows: obtaining a target image of a real object acquired by a camera when the real object makes a limb movement; inputting the target image into a coordinate acquisition model to obtain coordinates of a plurality of key points on a limb of the real object; determining a posture of the limb of the real object according to coordinates of each key point; driving, according to the posture of the real object, a virtual object displayed on a screen to present the limb movement of the real object. The method greatly reduces operation complexity and cost consumption when driving a virtual image.

Abstract: A method and apparatus for promoting a motion, an electronic device and a storage medium, relating to the field of image recognition technology are provided. An embodiment of the method may include: acquiring a user motion image, and acquiring three-dimensional recognition coordinates of body key points recognized in the user motion image; determining, based on the three-dimensional recognition coordinates, a user motion matching the user motion image; screening, according to a mapping relationship between user motion and body key points, a target body key point among all of the recognized body key points; acquiring three-dimensional standard coordinates of the target body key point corresponding to the user motion; and prompting a motion based on values of differences between the three-dimensional standard coordinates of the target body key point and the three-dimensional recognition coordinates of the target body key point.

Abstract: The human body 3D key point detection method includes: acquiring a to-be-detected image, the to-be-detected image including first human body image data; inputting the to-be-detected image into a key point extraction model to acquire N first 3D heatmaps of N human body 3D key points in the first human body image data, each first 3D heatmap representing a Gaussian distribution of one human body 3D key point in first human body image data in a predetermined space, where N is a positive integer; and determining coordinate information about the N human body 3D key points in the first human body image data based on the N first 3D heatmaps.

Abstract: Embodiments of the present invention provide a method for controlling compressor braking, a frequency converter and a variable speed compressor. The method includes steps of: determining to brake a compressor, wherein a brake circuit includes three switching units and the three switching units are respectively electrically connected to three phases of windings of a motor of the compressor; actuating two of the three switching units to short-circuit two phases of windings of the motor. The two phases of windings of the motor are short-circuited by controlling the three switching units to generate braking torque, such that the compressor is braked without introducing a DC voltage, and thus the braking energy consumption is reduced. Besides, by turning on only two switches at a time, the switching abrasion is reduced, and the overall service life of the three switching units is effectively improved.

Abstract: A method and apparatus for generating a 3D joint point regression model are provided. An embodiment of the method includes: acquiring a sample image with a 2D label and a sample image with a 3D label; training part of channels of an output layer of a basic 3D joint point regression model, with the sample image with the 2D label as a first input, and with a joint point heat map set corresponding to the 2D label as a first expected output; and training all of the channels of the output layer, with the sample image with the 3D label as a second input, with a joint point heat map set corresponding to the 3D label as a first part output of a second expected output and with a joint point depth information map set corresponding to the 3D label as a second part output of the second expected output.

Abstract: A method, an apparatus, an electronic device, and a computer readable storage medium for constructing a key-point learning model are provided. The method includes: acquiring labeled data labeling a human-body key-point and unlabeled data that does not label the human-body key-point; training, using the labeled data, an initial prediction model and an initial discriminator in a supervised training way to obtain a first prediction model and a first discriminator; training, using the unlabeled data, the first prediction model and the first discriminator in an unsupervised training way to obtain a second prediction model and a second discriminator; and constructing a key-point learning model according to the second prediction model and the second discriminator.

Abstract: The present disclosure provides a parameter control system for a motor, comprising: a current acquisition circuit connected to the motor, so as to acquire a current output by the motor; an arithmetic processor configured to determine whether to adjust a parameter of the motor according to the current acquired, and generate a new parameter when it is determined to adjust the parameter of the motor; and an output circuit configured to output the new parameter generated by the arithmetic processor to a control device of the motor. The present disclosure also provides a motor including the parameter control system.

Abstract: Embodiments of the present invention provide a method for controlling compressor braking, a frequency converter and a variable speed compressor. The method includes steps of: determining to brake a compressor, wherein a brake circuit includes three switching units and the three switching units are respectively electrically connected to three phases of windings of a motor of the compressor; actuating two of the three switching units to short-circuit two phases of windings of the motor. The two phases of windings of the motor are short-circuited by controlling the three switching units to generate braking torque, such that the compressor is braked without introducing a DC voltage, and thus the braking energy consumption is reduced. Besides, by turning on only two switches at a time, the switching abrasion is reduced, and the overall service life of the three switching units is effectively improved.