CN115641354A - Information generation method and device - Google Patents
Information generation method and device Download PDFInfo
- Publication number
- CN115641354A CN115641354A CN202110818185.7A CN202110818185A CN115641354A CN 115641354 A CN115641354 A CN 115641354A CN 202110818185 A CN202110818185 A CN 202110818185A CN 115641354 A CN115641354 A CN 115641354A
- Authority
- CN
- China
- Prior art keywords
- human body
- body image
- key points
- target
- preset key
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The disclosure discloses an information generation method and device, relates to the technical field of computers, and particularly relates to the technical field of image processing. The specific implementation scheme is as follows: firstly, every two adjacent frames of human body images in a target video are obtained, the previous frame of human body image in every two frames of human body images is used as a target human body image, then three-dimensional coordinates of preset key points in every two frames of human body images are determined, and finally speed information of the preset key points in the target human body image is generated according to the three-dimensional coordinates.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an information generating method and apparatus.
Background
In sports, the stance of a player is important for the performance of the game, such as a shooting action in basketball, a swing action of a golf ball, and a churning action in diving. The existing training mode usually adopts a mode of correcting a coach hand grip to train, and the action of an athlete cannot be recorded and guided in a digital mode.
Along with the development of camera collection technique and artificial intelligence technique, make sportsman's gesture data can be got down by accurate record through detection and the recovery to sportsman's action 3D skeleton. In the prior art, wearing sensors are mostly used for recording the state of an athlete, for example, an acceleration sensor or an electromyographic signal sensor is bound on an arm or a leg of the athlete, but for some special sports such as diving, gymnastics and the like, wearing equipment can interfere with the training of the athlete.
Disclosure of Invention
The disclosure provides an information generation method, an information generation device, an electronic device, a storage medium and a computer program product.
According to an aspect of the present disclosure, there is provided an information generating method including: acquiring every two adjacent frames of human body images in a target video, and taking the previous frame of human body image in every two frames of human body images as a target human body image; determining three-dimensional coordinates of preset key points in every two frames of human body images; and generating speed information of preset key points in the target human body image according to the three-dimensional coordinates.
According to another aspect of the present disclosure, there is provided an information generating apparatus including: the acquisition module is configured to acquire every two adjacent frames of human body images in the target video and take the previous frame of human body image in every two frames of human body images as a target human body image; the determining module is configured to determine three-dimensional coordinates of preset key points in every two frames of human body images; and the generating module is configured to generate speed information of preset key points in the target human body image according to the three-dimensional coordinates.
According to another aspect of the present disclosure, there is provided an electronic device comprising at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the information generating method.
According to another aspect of the present disclosure, a computer-readable medium is provided, on which computer instructions are stored, the computer instructions being used for enabling a computer to execute the above information generating method.
According to another aspect of the present disclosure, the present application provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-mentioned information generating method.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow diagram of one embodiment of an information generation method according to the present disclosure;
FIG. 2 is a schematic diagram of one application scenario of an information generation method according to the present disclosure;
FIG. 3 is a flow diagram for one embodiment of acquiring adjacent two frames of human images in a target video, according to the present disclosure;
FIG. 4 is a flow diagram for one embodiment of generating velocity information for a preset keypoint in a target human image, according to the present disclosure;
FIG. 5 is a flow diagram of another embodiment of an information generation method according to the present disclosure;
FIG. 6 is a schematic block diagram of one embodiment of an information generating apparatus according to the present disclosure;
fig. 7 is a block diagram of an electronic device for implementing the information generation method of the embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Referring to fig. 1, fig. 1 shows a flow diagram 100 of an embodiment of an information generation method that may be applied to the present disclosure. The information generation method comprises the following steps:
and step 110, acquiring every two adjacent frames of human body images in the target video, and taking the previous frame of human body image in every two frames of human body images as the target human body image.
In this embodiment, an executing subject (for example, a server) of the information generating method may locally read or obtain a target video from another server or a terminal device through a wired connection manner or a wireless connection manner, where the target video may be a video recorded on a target human body in a moving state, and the target video may be a monocular video recorded by a monocular camera. The execution main body can intercept part of frame images or all frame images of the target video to obtain multiple frames of human body images included by the target video, the multiple frames of human body images can be arranged according to a preset sequence, and each frame of human body image includes a target human body in motion at a certain moment. The execution main body can sequentially extract every two adjacent human body images from the obtained multiple frames of human body images, and then the previous human body image in the two frames of human body images is used as the target human body image.
It is noted that the wireless connection may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a UWB (ultra wideband) connection, and other wireless connection now known or developed in the future.
As an example, the execution subject obtains multiple frames of human body images by cutting out all frame images of the target video, and the multiple frames of human body images are arranged in the order of the first frame of human body image, the second frame of human body image, the third frame of human body image and the fourth frame of human body image. The executing main body can sequentially acquire every two adjacent frames of human body images in a plurality of frames of human body images and takes the previous frame of human body image as a target human body image, namely the executing main body can acquire a first frame of human body image and a second frame of human body image and takes the first frame of human body image as the target human body image; a second frame of human body image and a third frame of human body image can also be obtained, and the second frame of human body image is taken as a target human body image; and a third frame of human body image and a fourth frame of human body image can be obtained, the third frame of human body image is taken as a target human body image, and the like.
And step 120, determining the three-dimensional coordinates of preset key points in every two frames of human body images.
In this embodiment, after the execution main body obtains two adjacent frames of human body images in the target video, the two frames of human body images may be subjected to image preprocessing through the deep learning network, so as to solve image problems such as distortion, blurring, unclear light, complex background and the like of the human body images, enhance target human body information in the human body images, and obtain the preprocessed two frames of human body images. The execution main body can determine the three-dimensional coordinates of preset key points of the target human body based on the preprocessed human body image, the preset key points are human body key points of the target human body, the human body key points can be 24 skeleton key points included in the target human body, and the preset key points can be any one or all of the 24 skeleton key points.
The execution main body can respectively identify the human body information of the two frames of the preprocessed human body images, and respectively determine the position information of the preset key points in each frame of the human body image by using a human body key point detection algorithm. Then, the execution main body can respectively determine the three-dimensional coordinates of the preset key points in each frame of the human body image by using a plurality of three-dimensional coordinate generation means according to the position information of the preset key points in each frame of the human body image, wherein the three-dimensional coordinates can be the position coordinates of the preset key points in a rectangular space coordinate system. Therefore, the execution main body can respectively determine the three-dimensional coordinates of the preset key points in each frame of human body image and store the three-dimensional coordinates of the preset key points in each frame of human body image.
Or, the executing body may input the preprocessed human body image into the three-dimensional coordinate generating model, and the three-dimensional coordinate generating model may process the preprocessed human body image and output the three-dimensional coordinates of the preset key points in the human body image. Therefore, the execution main body can respectively determine the three-dimensional coordinates of the preset key points in each frame of human body image and store the three-dimensional coordinates of the preset key points in each frame of human body image.
The three-dimensional coordinate generation model can be obtained based on the following steps:
the method comprises the following steps of firstly, obtaining a training sample set, wherein training samples in the training sample set comprise sample human body images and sample three-dimensional coordinates corresponding to the sample human body images.
And secondly, training to obtain a three-dimensional coordinate generation model by using the machine learning algorithm and taking the sample human body image as input data and the sample three-dimensional coordinate corresponding to the input sample human body image as expected output data.
And step 130, generating speed information of preset key points in the target human body image according to the three-dimensional coordinates.
In this embodiment, the execution subject determines three-dimensional coordinates of preset key points in each two frames of human body images, and since the three-dimensional coordinates in the two frames of human body images are corresponding to the same key point of the target human body, the three-dimensional coordinates of the preset key points in each two frames of human body images may be different three-dimensional coordinates of the same key point. The execution main body can utilize an instantaneous speed calculation formula to calculate the speed information of the preset key point in the target human body image according to different three-dimensional coordinates of the same key point in two adjacent frames of human body images, and the speed information can represent the instantaneous speed of the preset key point of the target human body in the target human body image at the current moment.
The execution main body can calculate and generate the instantaneous speed of the key points of the 24 human bodies of the target human body in the target human body image according to the three-dimensional coordinates of the preset key points in the two adjacent frames of human body images, so that the instantaneous speed of the key points of the 24 human bodies of the target human body in each frame of human body image in the target video is determined.
With continuing reference to fig. 2, fig. 2 is a schematic diagram of an application scenario of the information generation method according to the present embodiment. In the application scenario of fig. 2, the terminal 201 records a target video for the athlete and sends the target video to the server 202. After the server 202 acquires the target video from the terminal 201, preprocessing the target video to acquire every two adjacent frames of human body images in the target video, and taking the previous frame of human body image in every two frames of human body images as the target human body image. Then, the server 202 determines three-dimensional coordinates of preset key points in each two frames of human body images according to the human body information of the athlete in each two frames of human body images, for example, three-dimensional coordinates of ankles of the athlete in each two frames of human body images can be respectively determined. Finally, the server 202 generates speed information of the ankles of the athletes in the target human body images according to the determined three-dimensional coordinates of the ankles of the athletes in the two frames of human body images.
According to the information generation method provided by the embodiment of the disclosure, every two adjacent frames of human body images in the target video are obtained, the previous frame of human body image in every two frames of human body images is used as the target human body image, then the three-dimensional coordinates of the preset key points in every two frames of human body images are determined, and finally the speed information of the preset key points in the target human body image is generated according to the three-dimensional coordinates.
Referring to fig. 3, fig. 3 shows a flowchart 300 of an embodiment of acquiring every two adjacent frames of human body images in the target video, that is, the step 110 described above, acquiring every two adjacent frames of human body images in the target video may include the following steps:
In this embodiment, the execution main body may locally read or acquire a target video from another server or terminal device in a wired connection manner or a wireless connection manner, where the target video may be a video recorded on a target human body in a moving state, and the target video may be a monocular video recorded by a monocular camera.
And 320, sampling the human body image of the target human body in the target video based on a preset sampling time interval to obtain a human body image sequence.
In this embodiment, after the execution main body acquires the target video, the execution main body may analyze the target video to determine each frame of human body image included in the target video. Then, the execution main body can determine the shooting time corresponding to each frame of human body image in the target video according to the shooting time of the target video.
The execution main body can acquire a preset sampling time interval, and the preset sampling time interval can be used for sampling multiple frames of human body images based on the shooting time of the human body images, so that the time interval between two adjacent frames of human body images after being collected is the same as the sampling time interval. The execution main body can sample the human body images in the target video according to the preset sampling time interval and the shooting time corresponding to each frame of human body image in the target video to obtain the sampled multiframe human body images, the sampled multiframe human body images form a human body image sequence according to the sequence of the shooting time, and then the human body image sequence can comprise the human body images arranged based on the time sequence.
And step 330, acquiring every two adjacent frames of human body images from the human body image sequence.
In this embodiment, after the execution main body acquires the human body image sequence, every two adjacent human body images may be acquired from multiple frames of human body images in the human body image sequence according to the arrangement order of the human body images.
As an example, if the execution subject obtains the human body image sequence as a first frame human body image, a second frame human body image, a third frame human body image, and a fourth frame human body image, the first frame human body image and the second frame human body image, or the second frame human body image and the third frame human body image, or the third frame human body image and the fourth frame human body image may be obtained.
In the implementation mode, the human body image sequence is obtained by sampling the human body image of the target human body in the target video based on the sampling time interval, and every two adjacent frames of human body images are obtained in the human body image sequence, so that the number of the human body images in the human body image sequence is reduced, and the efficiency of calculating speed information based on the human body images is improved.
Referring to fig. 4, fig. 4 shows a flowchart 400 of an embodiment of generating velocity information of a preset key point in a target human body image, namely, the step 130, generating the velocity information of the preset key point in the target human body image according to three-dimensional coordinates, which may include the following steps:
and step 410, determining the angle information of the preset key points according to the three-dimensional coordinates of the preset key points in every two frames of human body images.
In this embodiment, after the execution main body obtains the three-dimensional coordinates of the preset key points in each two frames of human body images, since the three-dimensional coordinates in the two frames of human body images are directed at the same key point of the target human body, the three-dimensional coordinates of the preset key points in each two frames of human body images may be different three-dimensional coordinates of the same key point, the execution main body may calculate the angle information of the preset key points in the target human body image by using an angle calculation formula according to the different three-dimensional coordinates of the same key point in the two adjacent frames of human body images, and the angle information may represent the three-dimensional angle information of the preset key point of the target human body in the target human body image in a rectangular spatial coordinate system. The angle calculation formula may be:
wherein, the first and the second end of the pipe are connected with each other,
angle information indicating the nth keypoint in the image of the ith frame,
three-dimensional coordinates representing the nth keypoint in the image of the ith frame,
and representing the three-dimensional coordinates of the nth key point in the image of the (l + 1) th frame.
As an example, the two adjacent frames of human body images obtained by the execution main body from the human body image sequence are a first frame of human body image and a second frame of human body image, and the execution main body determines three-dimensional coordinates of a head key point in the first frame of human body image and three-dimensional coordinates of a head key point in the second frame of human body image respectively. And then the executing body calculates the angle information of the head key point in the first frame of human body image by utilizing the angle calculation formula according to the three-dimensional coordinates of the head key point in the first frame of human body image and the three-dimensional coordinates of the head key point in the second frame of human body image.
And step 420, determining the corresponding time interval of every two frames of human body images.
In this embodiment, the execution subject acquires every two adjacent frames of human body images, and determines the shooting time of the two frames of human body images respectively. The execution main body can calculate and determine the time interval corresponding to the two frames of human body images according to the shooting time of the two frames of human body images, so that the time interval corresponding to each two frames of human body images can be determined.
Or, the execution main body may determine every two frames of human body images from the human body image sequence, and determine a preset sampling time interval corresponding to the human body image sequence as a time interval corresponding to every two frames of human body images.
And 430, generating speed information of the preset key points in the target human body image according to the angle information and the time interval of the preset key points.
In this embodiment, after obtaining the angle information and the time interval of the preset key points in every two frames of human body images, the execution subject calculates and generates the speed information of the preset key points in the target human body image by using an instantaneous speed calculation formula, where the speed information may represent the movement speed of the preset key points of the target human body in the target human body image in the spatial direct coordinate system. The instantaneous velocity calculation formula may be:
wherein the content of the first and second substances,
velocity information indicating the nth key point in the ith frame image,
angle information of an nth key point in an ith frame image is represented, and Δ t represents a time interval between the ith frame image and an (l + 1) th frame image.
As an example, the two adjacent frames of human body images obtained by the execution main body from the human body image sequence are a first frame of human body image and a second frame of human body image, and the execution main body determines three-dimensional coordinates of a head key point in the first frame of human body image and three-dimensional coordinates of a head key point in the second frame of human body image respectively. And then the execution main body calculates the angle information of the head key point in the first frame of human body image by utilizing the angle calculation formula according to the three-dimensional coordinates of the head key point in the first frame of human body image and the three-dimensional coordinates of the head key point in the second frame of human body image. And the execution main body determines the time interval between the first frame of human body image and the second frame of human body image according to the shooting time of the first frame of human body image and the shooting time of the second frame of human body image. And finally, the execution main body calculates the speed information of the head key point in the first frame of human body image by utilizing the instantaneous speed calculation formula according to the angle information of the head key point in the first frame of human body image and the time interval between the first frame of human body image and the second frame of human body image.
In the implementation mode, the speed information of the preset key points in the target human body image is generated through the angle information and the time interval of the preset key points, the speed information of the preset key points can be quickly determined, and the efficiency and the accuracy of speed information determination are improved.
Referring to fig. 5, fig. 5 shows a flow diagram 500 of another embodiment of an information generation method, which may include the steps of:
and step 510, acquiring every two adjacent frames of human body images in the target video, and taking the previous frame of human body image in every two frames of human body images as the target human body image.
Step 510 of this embodiment may be performed in a manner similar to step 110 in the embodiment shown in fig. 1, and is not described herein again.
And step 520, determining the three-dimensional coordinates of preset key points in every two frames of human body images.
Step 520 of this embodiment may be performed in a manner similar to step 120 of the embodiment shown in fig. 1, and is not described herein again.
And 530, generating speed information of a preset key point in the target human body image according to the three-dimensional coordinates.
Step 530 of this embodiment may be performed in a manner similar to step 130 of the embodiment shown in fig. 1, and is not described herein again.
And 540, in response to the speed information of the preset key points in the target human body image, acquiring a human body image set adjacent to the target human body image.
In this embodiment, after the execution subject obtains the speed information of the preset key point in the target human body image, the execution subject may determine the position of the target human body image in the human body images included in the target video, and obtain a preset number of frames of human body images adjacent to the target human body image in the human body images of the target video, as a human body image set adjacent to the target human body image, that is, obtain a preset number of frames of human body images adjacent to the target human body image and sequenced before and after the target human body image.
Alternatively, the executing body may determine the position of the target human body image from the obtained human body image sequence, and obtain a preset number of frames of human body images adjacent to the target human body image in the human body image sequence as a human body image set adjacent to the target human body image, that is, obtain a preset number of frames of human body images adjacent to the target human body image and sorted before and after the target human body image.
The preset number may be a preset number of images adjacent to the target human body image, for example, 2 frames, 4 frames, 6 frames, and the like, which is not specifically limited in this disclosure.
And 550, updating the speed information of the preset key points in the target human body image based on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set.
In this embodiment, after the execution subject acquires a human body image set adjacent to the target human body image, speed information of a preset key point of each frame of human body image in the human body image set is respectively determined. The execution main body can perform Gaussian filtering weighting on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set, update the speed information of the preset key points in the target human body image, and obtain updated speed information corresponding to the preset key points in the target human body image, so that the execution main body can update the speed information of the preset key points in each frame of human body image based on the method.
As an example, the target human body image is a 3 rd frame human body image, and after the executing body generates speed information of a head key point in the 3 rd frame human body image, four human body images adjacent to the 3 rd frame human body image are acquired, that is, a 1 st frame human body image, a 2 nd frame human body image, a 4 th frame human body image, and a 5 th frame human body image are acquired. The execution main body performs Gaussian filtering weighting on the speed information of the head key point in the 3 rd frame human body image and the speed information of the head key point in the 1 st frame human body image, the 2 nd frame human body image, the 4 th frame human body image and the 5 th frame human body image, updates the speed information of the head key point in the 3 rd frame human body image to obtain updated speed information of the head key point in the 3 rd frame human body image, and takes the updated speed information as the speed information of the head key point in the 3 rd frame human body image.
In the implementation mode, the speed information of the preset key points in the target human body image is updated based on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set, so that the condition that a calculation result does not conform to the real motion condition due to the fact that a single frame of independent calculation is prone to large deviation is avoided, the speed information of each frame of human body image is smoother and more in line with the actual condition, and the accuracy of the speed information is improved.
As an alternative implementation, with continued reference to fig. 5, the information generating method may further include the steps of:
and step 560, in response to the updated speed information of the preset key points in the acquired target human body image, acquiring standard speed information corresponding to the preset key points.
In this embodiment, the execution main body may locally pre-store a correspondence table between a preset key point and standard speed information, and after the execution main body obtains the updated speed information of the preset key point in the target human body image, the execution main body may obtain the standard speed information corresponding to the preset key point in the correspondence table, where the standard speed information may be an optimal speed state at the current time in a certain motion corresponding to the preset key point, which is not specifically limited by this disclosure.
In this step, after obtaining the standard speed information corresponding to the preset key point, the execution main body compares the updated speed information corresponding to the preset key point with the standard speed information, and generates a prompt message based on the comparison result, where the prompt message is used to represent the comparison result between the preset key point and the standard speed information.
The execution main body compares the updated speed information corresponding to the preset key point with the standard speed information, and if the updated speed information is determined to be smaller than the standard speed information, prompt information for prompting the target human body to accelerate can be generated; if the updated speed information is determined to be greater than the standard speed information, prompt information for prompting the target human body to reduce the speed can be generated; if the updated speed information is determined to be equal to the standard speed information, prompt information for prompting the target human body to keep the current speed can be generated.
In the implementation mode, the updated speed information is compared with the standard speed information to generate the prompt information, so that the speed information of the preset key points can be visually reflected, the speed information of each human body key point can be more visually observed, a target human body can know the current speed information of the preset key points, and improvement is performed.
With further reference to fig. 6, as an implementation of the methods shown in the above-mentioned figures, the present disclosure provides an embodiment of an information generating apparatus, which corresponds to the method embodiment shown in fig. 1, and which is specifically applicable to various electronic devices.
As shown in fig. 6, the information generating apparatus 600 of the present embodiment includes: an acquisition module 610, a determination module 620 and a generation module 630.
The obtaining module 610 is configured to obtain every two adjacent frames of human body images in the target video, and use a previous frame of human body image in every two frames of human body images as the target human body image;
a determining module 620 configured to determine three-dimensional coordinates of preset key points in every two frames of human body images;
and the generating module 630 is configured to generate speed information of preset key points in the target human body image according to the three-dimensional coordinates.
In some optional aspects of this embodiment, the obtaining module 610 is further configured to: acquiring a target video including a target human body; sampling human body images of a target human body in a target video based on a preset sampling time interval to obtain a human body image sequence, wherein the human body image sequence comprises human body images arranged based on a time sequence; and acquiring every two adjacent human body images from the human body image sequence.
In some optional aspects of this embodiment, the generating module 630 is further configured to: determining angle information of preset key points according to three-dimensional coordinates of the preset key points in every two frames of human body images; determining the corresponding time interval of every two frames of human body images; and generating speed information of the preset key points in the target human body image according to the angle information and the time interval of the preset key points.
In some optional manners of this embodiment, the apparatus further includes: an update module; an obtaining module 610, further configured to: responding to the speed information of preset key points in the obtained target human body image, and obtaining a human body image set adjacent to the target human body image, wherein the human body image set comprises a preset number of frames of human body images adjacent to the target human body image; and the updating module is configured to update the speed information of the preset key points in the target human body image based on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set.
In some optional aspects of this embodiment, the obtaining module 610 is further configured to: in response to the updated speed information of the preset key points in the target human body image, acquiring standard speed information corresponding to the preset key points; the generating module 630 is further configured to: and generating prompt information based on the updated speed information and the standard speed information.
According to the information generation device provided by the embodiment of the disclosure, every two adjacent frames of human body images in the target video are obtained, the previous frame of human body image in every two frames of human body images is used as the target human body image, then the three-dimensional coordinates of the preset key points in every two frames of human body images are determined, and finally the speed information of the preset key points in the target human body image is generated according to the three-dimensional coordinates.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the electronic device 700 comprises a computing unit 701, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
A plurality of components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (13)
1. An information generating method, comprising:
acquiring every two adjacent frames of human body images in a target video, and taking the previous frame of human body image in every two frames of human body images as a target human body image;
determining three-dimensional coordinates of preset key points in every two frames of human body images;
and generating speed information of a preset key point in the target human body image according to the three-dimensional coordinates.
2. The method of claim 1, wherein the acquiring every two adjacent frames of human body images in the target video comprises:
acquiring a target video including a target human body;
sampling human body images of a target human body in the target video based on a preset sampling time interval to obtain a human body image sequence, wherein the human body image sequence comprises human body images arranged based on a time sequence;
and acquiring every two adjacent human body images from the human body image sequence.
3. The method according to claim 1, wherein the generating speed information of preset key points in the target human body image according to the three-dimensional coordinates comprises:
determining angle information of preset key points according to the three-dimensional coordinates of the preset key points in every two frames of human body images;
determining the time interval corresponding to each two frames of human body images;
and generating speed information of the preset key points in the target human body image according to the angle information of the preset key points and the time interval.
4. The method of claim 1, wherein the method further comprises:
responding to the speed information of preset key points in the obtained target human body image, and obtaining a human body image set adjacent to the target human body image, wherein the human body image set comprises a preset number of frames of human body images adjacent to the target human body image;
and updating the speed information of the preset key points in the target human body image based on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set.
5. The method of claim 4, wherein the method further comprises:
in response to the updated speed information of the preset key points in the target human body image, acquiring standard speed information corresponding to the preset key points;
and generating prompt information based on the updated speed information and the standard speed information.
6. An information generating apparatus comprising:
the acquisition module is configured to acquire every two adjacent frames of human body images in a target video and take the previous frame of human body image in the every two frames of human body images as a target human body image;
the determining module is configured to determine three-dimensional coordinates of preset key points in each two frames of human body images;
and the generating module is configured to generate speed information of preset key points in the target human body image according to the three-dimensional coordinates.
7. The apparatus of claim 6, wherein the acquisition module is further configured to:
acquiring a target video including a target human body;
sampling human body images of a target human body in the target video based on a preset sampling time interval to obtain a human body image sequence, wherein the human body image sequence comprises human body images arranged based on a time sequence;
and acquiring every two adjacent human body images from the human body image sequence.
8. The apparatus of claim 6, wherein the generation module is further configured to:
determining angle information of preset key points according to the three-dimensional coordinates of the preset key points in every two frames of human body images;
determining the time interval corresponding to each two frames of human body images;
and generating speed information of the preset key points in the target human body image according to the angle information of the preset key points and the time interval.
9. The apparatus of claim 6, wherein the apparatus further comprises: an update module;
the acquisition module further configured to: in response to the speed information of preset key points in the obtained target human body image, obtaining a human body image set adjacent to the target human body image, wherein the human body image set comprises a preset number of frames of human body images adjacent to the target human body image;
the updating module is configured to update the speed information of the preset key points in the target human body image based on the speed information of the preset key points in the target human body image and the speed information of the preset key points of each frame of human body image in the human body image set.
10. The apparatus of claim 9, wherein the acquisition module is further configured to: in response to the updated speed information of the preset key points in the target human body image, acquiring standard speed information corresponding to the preset key points;
the generation module further configured to: and generating prompt information based on the updated speed information and the standard speed information.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818185.7A CN115641354A (en) | 2021-07-20 | 2021-07-20 | Information generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818185.7A CN115641354A (en) | 2021-07-20 | 2021-07-20 | Information generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115641354A true CN115641354A (en) | 2023-01-24 |
Family
ID=84940943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110818185.7A Pending CN115641354A (en) | 2021-07-20 | 2021-07-20 | Information generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115641354A (en) |
-
2021
- 2021-07-20 CN CN202110818185.7A patent/CN115641354A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114186632B (en) | Method, device, equipment and storage medium for training key point detection model | |
| CN113674421B (en) | 3D target detection method, model training method, related device and electronic equipment | |
| CN113378770B (en) | Gesture recognition method, device, equipment and storage medium | |
| US20220139061A1 (en) | Model training method and apparatus, keypoint positioning method and apparatus, device and medium | |
| CN113642431A (en) | Training method and device of target detection model, electronic equipment and storage medium | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| CN105068657B (en) | The recognition methods of gesture and device | |
| CN114972958B (en) | Key point detection method, neural network training method, device and equipment | |
| CN113362314B (en) | Medical image recognition method, recognition model training method and device | |
| CN111768005A (en) | Training method and device for lightweight detection model, electronic equipment and storage medium | |
| CN112580666A (en) | Image feature extraction method, training method, device, electronic equipment and medium | |
| CN115147831A (en) | Training method and device of three-dimensional target detection model | |
| CN114120454A (en) | Training method and device of living body detection model, electronic equipment and storage medium | |
| CN111027387B (en) | Method, device and storage medium for acquiring person number evaluation and evaluation model | |
| CN116403285A (en) | Action recognition method, device, electronic equipment and storage medium | |
| CN114694263B (en) | Action recognition method, device, equipment and storage medium | |
| CN115641354A (en) | Information generation method and device | |
| CN112200169B (en) | Method, apparatus, device and storage medium for training a model | |
| CN114220163B (en) | Human body posture estimation method and device, electronic equipment and storage medium | |
| US20210390334A1 (en) | Vehicle association method and device, roadside equipment and cloud control platform | |
| CN113325950B (en) | Function control method, device, equipment and storage medium | |
| CN114882587A (en) | Method, apparatus, electronic device, and medium for generating countermeasure sample | |
| CN115830640B (en) | Human body posture recognition and model training method, device, equipment and medium | |
| CN116189028B (en) | Image recognition method, device, electronic equipment and storage medium | |
| CN116912948B (en) | Training method, system and driving system for digital person |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |