WO2023061356A1

WO2023061356A1 - Advertisement serving method and apparatus, device, storage medium and computer program product

Info

Publication number: WO2023061356A1
Application number: PCT/CN2022/124578
Authority: WO
Inventors: 姜德志; 李怀德
Original assignee: 咪咕视讯科技有限公司; 咪咕文化科技有限公司; 中国移动通信集团有限公司
Priority date: 2021-10-13
Filing date: 2022-10-11
Publication date: 2023-04-20
Also published as: CN113988906A

Abstract

Embodiments of the present disclosure relate to the field of video processing, and disclose an advertisement serving method and apparatus, a device, a storage medium and a computer program product. The method comprises: determining a motion inclination angle of a moving target relative to the ground in a current video frame; according to the motion inclination angle, determining whether the moving target is turning at a steep inclination angle; when the moving target is turning at a steep inclination angle, placing an advertisement on a track on the ground in the current video frame. By means of the described method, embodiments of the present disclosure achieve the effect of accurate positioning of an advertisement serving location.

Description

Advertising method, device, equipment, storage medium and computer program product

Cross References to Related Applications

The embodiment of the present disclosure is based on the Chinese patent application with the application number 202111191382.7, the application date is October 13, 2021, and the application name is "advertising delivery method, device and computing equipment", and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated by reference into this disclosure.

technical field

Embodiments of the present disclosure relate to, but are not limited to, the technical field of image processing, and in particular, relate to an advertisement placement method, device, equipment, storage medium, and computer program product.

Background technique

Digital Billboard Replacement (DBR) technology is aimed at specific camera positions and specific football scenes, and the system reusability and device flexibility are poor. Virtual signage technology lacks specific solutions in ice and snow events, especially in bobsleigh and sled tracks, and in high-speed sports scenes, the ability to analyze the main body and irregular tracks is insufficient, making it difficult for accurate positioning of advertisements.

Contents of the invention

In view of the above problems, the embodiments of the present disclosure provide an advertisement placement method, device, device, storage medium and computer program product, which are used to solve the problem that advertisement placement cannot be accurately positioned in the prior art.

According to an aspect of an embodiment of the present disclosure, an advertisement delivery method is provided, the method comprising:

Determine the motion inclination of the moving target relative to the ground in the current video frame;

determining whether the moving target is turning at a steep angle according to the movement inclination;

When the moving target is turning at a steep angle, the advertisement is placed on the track on the ground in the current video frame.

According to another aspect of the embodiments of the present disclosure, an advertisement delivery device is provided, including:

The first determination module is configured to determine the inclination angle of motion of the moving target relative to the ground in the current video frame;

The second determination module is configured to determine whether the moving target is turning with a large inclination according to the movement inclination;

The placement module is configured to place the advertisement on the track on the ground in the current video frame when the moving target is turning at a steep angle.

According to another aspect of the embodiments of the present disclosure, there is provided a computing device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete the communication through the communication bus. communication between

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operation of the above advertisement delivery method.

According to yet another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium, and when the executable instruction is run on a computing device, the computing device executes the above-mentioned The action of the ad serving method.

According to still another aspect of the embodiments of the present disclosure, a computer program product is provided, the computer program product includes computer instructions, and when the computer instructions are run on a computer device, the computer device is made to perform the above advertisement placement The operation of the method.

In the embodiment of the present disclosure, by determining the inclination angle of the moving object relative to the ground in the current video frame, it is determined according to the inclination angle whether the moving object is turning at a steep angle, and when the moving object is turning at a steep angle, the advertisement is placed In the track on the ground in the current video frame, the advertisement placement can be accurately positioned, and the user experience is improved.

In one implementation, by extracting the 3D information of the moving target and the 3D information of the ground in the current video frame in real time, the inclination angle of the moving target relative to the ground is determined according to the 3D information of the moving target and the 3D information of the ground. Determine the inclination angle When the moving target is turning at a large inclination angle, identify the area ratio of the track in the current video frame, and place the advertisement on the track on the ground in the current video frame according to the motion inclination angle and area ratio, which can make the sled and In the bobsleigh race, based on the real-time inclination of the sled or bobsleigh and the proportion of the track, the location of the advertisement is determined, as well as the timing of when the advertisement starts to be projected and disappears, so as to achieve the effect of precisely positioning the advertisement placement.

The above description is an overview of the technical solutions of the embodiments of the present disclosure. In order to better understand the technical means of the embodiments of the present disclosure, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the embodiments of the present disclosure To make it more obvious and understandable, specific embodiments of the present disclosure are given below.

Description of drawings

The drawings are only for illustrating the embodiments and are not to be considered as limiting the present disclosure. Also throughout the drawings, the same reference numerals are used to designate the same parts. In the attached picture:

FIG. 1 is a schematic flowchart of an advertisement placement method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of determining three-dimensional information in an advertisement placement method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of stereo matching results in an advertisement delivery method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of mapping from a two-dimensional frame to a three-dimensional frame in an advertisement placement method provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of viewing angle information of a two-dimensional frame provided by an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of an advertisement delivery device provided by an embodiment of the present disclosure;

FIG. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein.

At present, for the two competitions of sled and snowmobile in the Winter Olympics, the fastest speed can reach 160km/h, which is called "F1 on ice". The competition tracks of the two competitions are the same, only the starting point of the competition is different. The race track can be divided into two parts, straight and curves. Compared with the straight road, there is no obvious ice wall on both sides of the curve, and the ice surface of the curve section is wider than that of the straight section, and the angle between the curve track plane and the ground can reach up to 70-80 degrees. The high-speed cornering of sleds and sleds is one of the most entertaining parts of these two competitions, which is a test of the contestants' ability to control the vehicles and sleds.

However, in the existing technology, there are two solutions for the automatic advertisement placement of video stream AI, which are customized rebroadcasting technology and virtual signage (Virtual Signage) technology. Among them, the customized broadcast technology may also be called digital billboard replacement (DBR) technology. DBR technology is mainly used in the virtual advertisement of the billboard beside the football field. It can add different advertising content on the billboard in the broadcast signal in different regions. Camera data; virtual identification technology is currently mainly used in football and basketball. It uses visual processing algorithms to locate player positions and specific areas of the court such as penalty areas and three-point lines, and analyze player positions and shooting camera position information. Regional placement of advertisements. In the above-mentioned existing technologies, DBR technology is aimed at specific camera positions and specific football scenes, and the system reusability and equipment flexibility are poor; virtual sign technology lacks specific solutions in ice and snow projects, especially in bobsleigh and sled tracks In the high-speed sports scene, the ability to analyze the main body and the irregular field is insufficient.

Fig. 1 is a flowchart of an advertisement placement method provided by an embodiment of the present disclosure, the method is executed by a computing device. The computing device may be a computer device, a terminal device, a server or other devices with data processing capabilities. As shown in Figure 1, the method includes the following steps:

Step 110: Determine the inclination angle of the moving object relative to the ground in the current video frame.

Wherein, determining the motion inclination angle of the moving target in the current video frame relative to the ground, for example, may include the following steps:

Step 1101: extracting the 3D information of the moving target and the 3D information of the ground in the current video frame in real time.

In the embodiment of the present disclosure, a real-time video stream is acquired first, and a current video frame in the real-time video stream is extracted. Among them, the real-time video stream can be obtained through the binocular camera. Therefore, the current video frame includes a left-eye video frame and a right-eye video frame.

Among them, as shown in Figure 2, the process of real-time detection of the 3D information of the moving target in the current video frame and the 3D information of the ground is as follows:

First, input the left-eye video frame and right-eye video frame into the object detection model to obtain the feature and position information of the moving object. Among them, the target detection model is obtained by pre-training the convolutional neural network based on the training samples of the moving target. In the embodiments of the present disclosure, for scenes with small moving objects and complex backgrounds, a feature pyramid network can be added to the object detection model to obtain shallow edge information and deep semantic information, so that when the object detection model detects moving objects , the features of the extracted moving target are combined with shallow edge information and deep semantic information. For example, for sleds and snowmobiles, the targets are small and the background is complex. By adding a feature pyramid network, the detection of moving targets is more accurate. Stereo matching is performed on the left-eye video frame and the right-eye video frame according to the characteristics and position information of the moving object, and a depth map after stereo matching is obtained, as shown in FIG. 3 . The process of stereo matching is to establish the corresponding relationship of the same pixel between the images acquired by the left and right cameras, and obtain the depth map.

Then, after the depth map is obtained, the two-dimensional frame of the moving object is determined according to the feature and position information of the moving object. For example, in some implementations, grid regression is performed on the left-eye video frame and the right-eye video frame, so as to obtain the two-dimensional frame of the moving object in the left-eye video frame and the right-eye video frame.

Finally, the three-dimensional position information of the moving object is obtained according to the two-dimensional frame of the moving object and preset constraint conditions. The three-dimensional position information of the moving object includes the position coordinates of the center point of the moving object and the angle between the moving direction of the moving object and the optical axis of the camera. Among them, the three-dimensional position information of the moving object is obtained by combining the shooting angle information of the binocular camera orientation and the key coordinate information in the two-dimensional frame of the moving object through preset constraint conditions. The three-dimensional position information of the moving object can be represented by a three-dimensional frame of the moving object, and the three-dimensional frame is represented as: S=[x, y, z, λ]. As shown in FIG. 4 , it shows a mapping process from a two-dimensional frame to a three-dimensional frame, including an example of a mapping process from key coordinate information in a two-dimensional frame of a moving object to a three-dimensional frame. For example, in some implementations, seven key point coordinate information z=u _l , v _t , u _r , v _b , u' _l , u are extracted from the two-dimensional frame of the moving object in the left-eye video frame and the right-eye video frame respectively ' _r , _up . Among them, u _l represents the left coordinates of the two-dimensional frame of the moving object in the left-eye video frame, v _t represents the top edge coordinates of the two-dimensional frame of the moving object in the left-eye video frame, and v _b represents the two-dimensional frame of the moving object in the left-eye video frame v _b represents the bottom coordinates of the two-dimensional frame of the moving target in the left-eye video frame, u' _l represents the left coordinate of the two-dimensional frame of the moving target in the right-eye video frame, and u' _r represents the moving target in the right-eye video frame The right coordinates of the two-dimensional frame of , u _p represents the coordinates of one of the four vertices in the bottom surface of xz in the three-dimensional frame. Among them, the preset constraints are expressed by the constraint equation from the two-dimensional frame of the moving target to the three-dimensional frame of the moving target, which can be expressed as:

Among them, b is an example between the two eye axes of the binocular camera; (x, y, z) is the coordinates of the middle point of the cube of the three-dimensional frame of the moving target, that is, the coordinates of the center point of the moving target; (l, w, h) is the length, width and height of the three-dimensional frame of the moving target; λ represents the angle between the direction of motion of the moving target and the optical axis of the camera (the optical axis of the binocular camera); β represents the midpoint of the three-dimensional frame of the moving target and the center of the camera The azimuth angle between the connection line and the optical axis of the camera; the key coordinate point information of the two-dimensional frame of the left and right eye images after feature extraction and feature detection is substituted into the above constraints to solve the three-dimensional position information of the moving target. As shown in Figure 5, the viewing angle information of the two-dimensional frame, in which the azimuth angle between the moving direction of the moving object and the optical axis of the camera is λ, and the azimuth angle between the midpoint of the three-dimensional frame of the moving object and the center of the camera and the optical axis of the camera is beta.

Wherein, the analysis and calculation process of the three-dimensional information of the ground is consistent with the above-mentioned three-dimensional information of the moving target, and will not be repeated here.

Step 1102: According to the three-dimensional information of the moving object and the three-dimensional information of the ground, determine the inclination angle of the moving object relative to the ground.

Wherein, according to the three-dimensional information of the moving object, the reference frame is formed as the first normal vector of the moving object; according to the three-dimensional information of the ground, a second normal vector perpendicular to the ground in the current video frame is formed; according to the first normal vector and the The second normal vector is used to calculate the inclination angle of the moving target relative to the ground. In some implementations, the calculation process of the first normal vector of the moving target is:

Based on the coordinate information of the xz bottom surface of the three-dimensional frame of the moving object, a first normal vector based on the xz surface is generated as the first normal vector of the moving object as a reference system.

Among them, coordinates A(x ₁ ,y ₁ ,z ₁ ), B(x ₂ ,y ₂ ,z ₂ ), C(x ₃ ,y ₃ ,z ₃ ), p ₁ p ₂ , p ₁ p ₃ are two vectors based on the arbitrary three points, i, j, k are unit vectors,

is the first normal vector of the xz base.

In the embodiment of the present disclosure, the binocular camera is combined with a real scene to generate a second normal vector perpendicular to the ground in the current video frame. In the establishment process of the second normal vector perpendicular to the ground in the current video frame, three points are selected as the ground to generate the second normal vector perpendicular to the ground in the current video frame. The establishment process is similar to the calculation process of the first normal vector , which will not be repeated here. The direction of the second normal vector is based on the ground in the current video frame, and is not affected by the track plane and the movement of the snowmobile.

Wherein, after the first normal vector and the second normal vector are obtained, the angle between the first normal vector and the second normal vector is calculated to generate a motion inclination angle of the moving target relative to the ground.

Step 120: Determine whether the moving target is turning with a steep angle according to the moving inclination.

Wherein, it is determined whether the motion inclination is greater than or equal to the inclination threshold, and when the inclination threshold is greater than or equal to the inclination threshold, it is determined that the moving target is in a high-inclination turning state; when the motion inclination is smaller than the inclination threshold, it is determined that the moving target is not in a high-inclination state. Wherein, the embodiment of the present disclosure does not limit the specific value of the inclination threshold, and those skilled in the art can set it according to specific scenarios.

Step 130: When the moving target is turning at a steep angle, place the advertisement on the track on the ground in the current video frame.

Wherein, when the moving target is turning at a steep angle, placing the advertisement on the track on the ground in the current video frame may include, for example, the following steps:

Step 1301: Identify the area ratio of the track in the current video frame when it is determined according to the motion inclination that the moving object is turning at a large inclination. When the moving object turns at a large inclination angle, identify the position information of the track in the current video frame, and determine the area ratio of the area of the track in the current video frame according to the position information. In some implementations, the location information of the track in the current video frame can be identified through an image segmentation algorithm. Among them, when identifying the position information of the track in the current video frame, determine whether the position information of the track is detected in the current video frame, and when the track is detected, calculate the area ratio of the area of the track in the current video frame . When the race track is not detected, the operation of putting the advertisement is stopped. When the track is detected, the area ratio of the track area in the current video frame is determined according to the position information of the track. Wherein, the area ratio of the area of the track in the current video frame can be determined by the ratio of the area of the track to the overall area of the picture, and the calculation process of the ratio is determined based on the number of pixels.

Step 1302: According to the motion inclination and the area ratio, place the advertisement on the track on the ground in the current video frame.

Wherein, when it is determined according to the motion inclination angle that the moving target is turning at a large inclination angle, and the area ratio is greater than or equal to a preset ratio threshold, determine the size and position of the track in the current video frame; Size and position to insert into said track on the ground in the current video frame. Wherein, the embodiment of the present disclosure does not limit the specific value of the preset ratio threshold, and those skilled in the art can set correspondingly according to specific scenarios, for example, for skiing competition, the preset ratio threshold can be 0.4.

Wherein, when advertising is placed, the advertisement can be placed on the track area of the track except the moving target according to the three-dimensional frame of the moving target.

In the embodiment of the present disclosure, when it is determined according to the motion inclination that the moving target is not turning at a steep angle, or when a track is not detected in the current video frame, or when the area ratio is smaller than a ratio threshold, Stop serving of said ad.

In one implementation, by extracting the 3D information of the moving target and the 3D information of the ground in the current video frame in real time, the inclination angle of the moving target relative to the ground is determined according to the 3D information of the moving target and the 3D information of the ground. Determine the inclination angle When the moving target turns at a large inclination angle, identify the area ratio of the track in the current video frame, and place the advertisement on the track on the ground in the current video frame according to the motion inclination angle and area ratio, which can make it possible to track the sled With the bobsleigh race, based on the real-time inclination of the sledge or bobsleigh and the proportion of the track, the location of the advertisement is determined, as well as the timing when the advertisement starts to be projected and disappears, thus achieving the effect of precisely positioning the placement of the advertisement.

FIG. 6 is a schematic structural diagram of an advertisement delivery device provided by an embodiment of the present disclosure. As shown in Figure 6, the device 300 includes:

In some embodiments, the determining the inclination angle of the moving object in the current video frame relative to the ground includes: extracting the 3D information of the moving object in the current video frame and the 3D information of the ground in real time; according to the 3D information of the moving object and the three-dimensional information of the ground, and determine the motion inclination angle of the moving target relative to the ground.

In some implementations, when the moving object is turning at a steep angle, placing the advertisement on the track on the ground in the current video frame includes: when the moving object is turning at a steep angle, Identifying the area ratio of the track in the current video frame; placing advertisements on the track on the ground in the current video frame according to the motion inclination and the area ratio.

In some implementations, the current video frame includes a left-eye video frame and a right-eye video frame; the real-time extraction of the three-dimensional information of the moving object and the three-dimensional information of the ground in the current video frame includes: combining the left-eye video frame and the Input the right-eye video frame into the target detection model to obtain the characteristics and position information of the moving target; determine the two-dimensional frame of the moving target according to the characteristics and position information of the moving target; according to the two-dimensional frame and preset constraints The condition is to obtain the three-dimensional position information of the moving object; the three-dimensional position information includes the position coordinates of the center point of the moving object and the angle between the moving direction of the moving object and the optical axis of the camera.

In some embodiments, the determining the inclination of the moving object relative to the ground according to the three-dimensional position information of the moving object and the three-dimensional position information of the ground includes: according to the three-dimensional information of the moving object Forming the first normal vector whose reference frame is a moving target; forming a second normal vector perpendicular to the ground in the current video frame according to the three-dimensional information of the ground; calculating the first normal vector and the second normal vector according to the first normal vector The inclination angle of the moving target relative to the ground.

In some implementations, when it is determined that the moving object is turning at a steep angle, identifying the area ratio of the track in the current video frame includes: when the moving object is turning at a steep angle, Identify the position information of the track in the current video frame; determine the area ratio of the track in the current video frame according to the position information.

In some implementations, the placing advertisements on the track on the ground in the current video frame according to the motion inclination and the area ratio includes: determining the motion according to the motion inclination When the target is turning at a large inclination angle, and the area ratio is greater than or equal to a preset ratio threshold, determine the size and position of the track in the current video frame; place the advertisement according to the size and position of the track, Insert into the track on the ground in the current video frame.

In some implementations, after the determination of the motion inclination of the moving object relative to the ground in the current video frame, the method further includes: when it is determined according to the motion inclination that the moving object is not turning at a steep angle, or when not When a race track is detected in the current video frame, or when the area ratio is smaller than a ratio threshold, the advertisement delivery is stopped.

In some implementations, placing the advertisement on the track on the ground in the current video frame according to the motion inclination and the area ratio includes: placing the advertisement on the track Areas of the track other than the stated sporting objectives.

The working process of the advertisement delivery device in the embodiment of the present disclosure is substantially the same as the implementation steps of the above-mentioned advertisement delivery method embodiment, and will not be repeated here.

In one implementation, by extracting the 3D information of the moving target and the 3D information of the ground in the current video frame in real time, the inclination angle of the moving target relative to the ground is determined according to the 3D information of the moving target and the 3D information of the ground. Determine the inclination angle When the moving target turns at a large inclination angle, identify the area ratio of the track in the current video frame, and place the advertisement on the track on the ground in the current video frame according to the motion inclination angle and area ratio, which can make it possible to track the sled With the bobsleigh race, based on the real-time inclination of the sledge or bobsleigh and the proportion of the track to determine where to add the ad, and when the ad starts to project and disappear, the user experience is improved.

FIG. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present disclosure, and specific embodiments of the present disclosure do not limit the specific implementation of the computing device.

As shown in FIG. 7 , the computing device may include: a processor (processor) 402, a communication interface (Communications Interface) 404, a memory (memory) 406, and a communication bus 408.

Wherein: the processor 402 , the communication interface 404 , and the memory 406 communicate with each other through the communication bus 408 . The communication interface 404 is used to communicate with network elements of other devices such as clients or other servers. The processor 402 is configured to execute the program 410, and specifically, may execute the relevant steps in the above-mentioned embodiment of the advertisement delivery method.

Specifically, the program 410 may include program codes including computer-executable instructions.

The processor 402 may be a central processing unit CPU, or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present disclosure. The one or more processors included in the computing device may be of the same type, such as one or more CPUs, or may be different types of processors, such as one or more CPUs and one or more ASICs.

The memory 406 is used to store the program 410 . The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

Specifically, the program 410 may be invoked by the processor 402 to cause the computing device to perform the following operations:

The specific working process of the computing device in the embodiment of the present disclosure is substantially the same as the specific implementation steps in the above embodiment of the advertisement delivery method, and will not be repeated here.

In one implementation, by extracting the 3D information of the moving target and the 3D information of the ground in the current video frame in real time, the inclination angle of the moving target relative to the ground is determined according to the 3D information of the moving target and the 3D information of the ground. Determine the inclination angle When the moving target turns at a large inclination angle, identify the area ratio of the track in the current video frame, and place the advertisement on the track on the ground in the current video frame according to the motion inclination angle and area ratio, which can make it possible to control the sled For a race with a bobsled, determine where to add the ad based on the real-time inclination and track ratio information of the sled or bobsleigh, as well as when the ad starts to project and disappears.

An embodiment of the present disclosure provides a computer-readable storage medium, the storage medium stores at least one executable instruction, and when the executable instruction is run on a computing device, the computing device executes the method described in any of the above method embodiments. Ad delivery method.

Specifically, the executable instructions can be used to cause the computing device to perform the following operations:

In some embodiments, the determining the inclination angle of the moving object relative to the ground according to the three-dimensional position information of the moving object and the three-dimensional position information of the ground includes: according to the three-dimensional information of the moving object Forming the first normal vector whose reference frame is the moving target; forming the second normal vector perpendicular to the ground in the current video frame according to the three-dimensional information of the ground; calculating the first normal vector according to the first normal vector and the second normal vector The inclination angle of the moving target relative to the ground.

When the executable instructions of the computer-readable storage medium in the embodiment of the present disclosure are run on the computing device, the specific working process is roughly the same as the specific implementation steps of the above-mentioned advertisement delivery method embodiment, and will not be repeated here.

An embodiment of the present disclosure provides an advertisement placement device, configured to implement the above advertisement placement method.

An embodiment of the present disclosure provides a computer program, and the computer program can be called by a processor to cause a computing device to execute the advertisement delivery method in any of the above method embodiments.

An embodiment of the present disclosure provides a computer program product. The computer program product includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. The advertisement delivery method in the method embodiment.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present disclosure are not directed to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present disclosure described herein, and the above description of specific languages is for disclosing the best mode of the present disclosure.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the above description of exemplary embodiments of the disclosure, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of embodiments of the disclosure are sometimes grouped together into a single implementation examples, figures, or descriptions thereof. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed disclosure requires more features than are expressly recited in each claim.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. The modules or units or components in the embodiments can be combined into one module or unit or component, and they can be divided into a plurality of sub-modules or sub-units or sub-components. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

It should be noted that the above-mentioned embodiments illustrate rather than limit the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The disclosure can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims

A method for advertising, the method comprising:

Determine the motion inclination of the moving target relative to the ground in the current video frame;

determining whether the moving target is turning at a steep angle according to the movement inclination;

When the moving target is turning at a steep angle, the advertisement is placed on the track on the ground in the current video frame.
The method according to claim 1, wherein said determining the inclination angle of motion of the moving target in the current video frame relative to the ground comprises:

Real-time extraction of the 3D information of the moving target in the current video frame and the 3D information of the ground;

According to the three-dimensional information of the moving object and the three-dimensional information of the ground, the inclination angle of the moving object relative to the ground is determined.
The method according to claim 1, wherein when the moving target is turning at a steep angle, placing advertisements on the track on the ground in the current video frame includes:

When the moving target is turning at a steep angle, identify the area ratio of the track in the current video frame;

Advertisements are placed on the track on the ground in the current video frame according to the motion inclination and the area ratio.
The method according to claim 2, wherein the current video frame includes a left-eye video frame and a right-eye video frame; the real-time extraction of the three-dimensional information of the moving target and the three-dimensional information of the ground in the current video frame includes:

Inputting the left-eye video frame and the right-eye video frame into a target detection model to obtain the feature and position information of the moving target;

determining a two-dimensional frame of the moving object according to the characteristics and position information of the moving object;

According to the two-dimensional frame and preset constraint conditions, the three-dimensional position information of the moving object is obtained; the three-dimensional position information includes the position coordinates of the center point of the moving object and the distance between the moving direction of the moving object and the optical axis of the camera angle.
The method according to claim 2, wherein, according to the three-dimensional position information of the moving target and the three-dimensional position information of the ground, determining the inclination angle of the moving target relative to the ground includes:

forming a reference frame as the first normal vector of the moving object according to the three-dimensional information of the moving object;

forming a second normal vector perpendicular to the ground in the current video frame according to the three-dimensional information of the ground;

According to the first normal vector and the second normal vector, a motion inclination angle of the moving target relative to the ground is calculated.
The method according to claim 3, wherein when it is determined that the moving target is turning at a steep angle, identifying the area ratio of the track in the current video frame includes:

When the moving target is turning at a large inclination angle, identifying the position information of the track in the current video frame;

According to the position information, determine the area ratio of the track area in the current video frame.
The method according to claim 3, wherein the placing advertisements on the track on the ground in the current video frame according to the motion inclination angle and the area ratio includes:

When it is determined according to the motion inclination that the moving target is turning at a large inclination, and the area ratio is greater than or equal to a preset ratio threshold, determine the size and position of the track in the current video frame;

Inserting the advertisement into the race track on the ground in the current video frame according to the size and position of the race track.
The method according to any one of claims 3-7, wherein, after determining the motion inclination of the moving target in the current video frame relative to the ground, the method further comprises:

When it is determined according to the motion inclination that the moving target is not turning at a steep angle, or when a track is not detected in the current video frame, or when the area ratio is less than a ratio threshold, stop the advertisement delivery .
The method according to claim 3, wherein the placing advertisements on the track on the ground in the current video frame according to the motion inclination angle and the area ratio includes:

Putting the advertisement on the race track area in the race track except the sports target.
An advertising delivery device, the device comprising:

The first determination module is configured to determine the inclination angle of motion of the moving target relative to the ground in the current video frame;

The second determination module is configured to determine whether the moving target is turning with a large inclination according to the movement inclination;

The placement module is configured to place the advertisement on the track on the ground in the current video frame when the moving target is turning at a steep angle.
A computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface complete mutual communication through the communication bus;

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operation of the advertisement delivery method according to any one of claims 1-9.
A computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium, and when the executable instruction is run on a computing device, the computing device executes the advertisement according to any one of claims 1-9 The action of the delivery method.
A computer program product, the computer program product including computer instructions, when the computer instructions are run on a computer device, the computer device is made to execute the advertisement delivery method described in any one of claims 1-9 operate.