A media resource playing system and method

Abstract

The present invention discloses a media resource playback system and method, which includes a launcher, an identification module, a matching module, and a control system; the launcher is used to launch media materials, the matching module is used to perform data analysis on the human body posture of the audience, and transmit the analyzed data to the control system, the identification module is used to perform feature analysis on the audience, and transmit the analyzed data to the control system, the control system selects a launcher for playing media materials according to the analysis data transmitted by the matching module, the control system selects the type of media materials to be played according to the data transmitted by the identification module, and the control system controls the launcher to play the media materials. The matching module analyzes the head orientation of the audience, and through the analysis of the head orientation, the control system selects a launcher for playing media resources, so that the media resources appear in the audience's sight, thereby improving the effect of launching the media resources.

Description

Technical Field

[0001] The present invention relates to the technical field of media resource playback, and in particular to a media resource playback system and method. Background Art

[0002] In the information age, advertising is everywhere. Expanding economic benefits is the main purpose of advertising, and advertising plays a very important role in the market.

[0003] Elevator advertising is a new type of advertising media. When riding in an elevator, it is a monotonous and boring thing for most people in the elevator. When waiting for the elevator and when the elevator is running up and down, it is the most boring time for people. At this time, people have a strong and subconscious visual demand. The appearance of advertising pictures will naturally attract people's attention and become the center of vision. However, how to effectively promote advertising to relevant people and let more people see advertisements that suit them is the long-term goal of the advertising industry and the direction in which elevator advertising needs to be improved.

[0004] Elevators are usually used by many people only during rush hour. There are almost no people in the elevator during working hours. However, elevator advertisements will continue to play regardless of whether there are people in the elevator or not. This not only fails to achieve a good promotion effect, but also reduces the life of the display screen, wastes electricity resources, and increases maintenance costs. Summary of the invention

[0005] The purpose of the present invention is to provide a media resource playing system and method to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a media resource playback system, the media resource playback system includes a launcher, a matching module, an identification module, and a control system;

[0007] The launcher is used to launch media materials, the matching module is used to perform data analysis on the audience's body posture and transmit the analyzed data to the control system, the identification module is used to perform feature analysis on the audience and transmit the analyzed data to the control system, the control system selects a launcher for playing media materials according to the analysis data transmitted by the matching module, the control system selects the type of media materials to be played according to the data transmitted by the identification module, and the control system controls the launcher to play the media materials; the matching module analyzes the audience's head orientation, and through the analysis of the head orientation, the control system selects a launcher for playing media resources, so that the media resources appear in the audience's line of sight, thereby improving the effect of launching the media resources.

[0008] The matching module includes a posture acquisition module and a posture analysis module. The posture acquisition module acquires images of the posture of a human body when standing and marks them as posture images. The posture analysis module analyzes the head orientation of the human body in the posture image. The posture acquisition module acquires images of the audience from above the audience, and marks the positions of the audience's left and right acromion points, nose tip, and dispenser in the image, so that it is convenient for the posture analysis module to mark the left and right acromion points, nose tip, and dispenser in the coordinate system after establishing the coordinate system. Through the position marking of the posture acquisition module and the establishment of the coordinate system by the posture analysis module, the content in the posture image is converted into data that can be quickly processed by the control system. The posture acquisition module and the posture analysis module divide the work of processing the posture image, thereby subtracting the processing steps of the control system, so that the control system can quickly calculate the relationship between the audience's line of sight and the dispenser, thereby quickly selecting the dispenser for playing media resources.

[0009] The recognition module includes an image acquisition subsystem, a sorting module, and a screening module. The image acquisition subsystem acquires images of the audience and marks them as recognition images. The sorting module analyzes the body features of the audience in the recognition images, and the screening module analyzes the clothing features of the audience in the recognition images. The image acquisition subsystem takes two images from the side and front of the audience, and forms a three-dimensional image of the audience's body shape and clothing analysis through the two images, so that the sorting module and the screening module extract the completed analysis data from the image.

[0010] The sorting module includes a body shape analysis subsystem and a facial recognition subsystem. The body shape analysis subsystem performs contour analysis on the human body shape of the audience in the recognition image, and the facial recognition subsystem analyzes the facial features of the audience in the recognition image; the facial recognition subsystem extracts and performs data analysis on the facial features of the audience, thereby analyzing the gender and age of the audience. The body shape analysis subsystem analyzes the body shape of the audience, including the thickness from front to back and the width from left to right, thereby analyzing the fatness and gender of the audience. Through the cooperation between the body shape analysis subsystem and the facial recognition subsystem, the gender of the audience can be analyzed more accurately. Through the analysis of the gender of the audience, the control system can select the media resources that meet the gender of the audience from the database. Through the analysis of the age and fatness of the audience, the control system can play media resources more targetedly.

[0011] The screening module includes a clothing recognition subsystem and a color analysis subsystem. The clothing recognition subsystem performs contour analysis on clothing in the recognition image, and the color analysis subsystem analyzes the color of clothing in the recognition image. The clothing recognition subsystem collects and analyzes the type of collar, sleeve height, and line contour of clothing, and analyzes the audience's clothing type, including suits or casual wear, men's wear or women's wear. The color analysis subsystem analyzes the color of clothing to determine the audience's personality and preference for clothing. The control system plays media resources that meet the audience's preferences based on the analyzed clothing type, personality, and preference for clothing, further improving the accuracy of media resource playback and the pertinence of media resource playback to the audience, thereby improving the efficiency and effect of media resource delivery.

[0012] The recognition image includes two images on vertical planes perpendicular to each other; the content of the posture image includes the audience's head orientation and the position distribution of the dispenser; the control system includes a database, which is used to store various media resources.

[0013] The input end of the posture analysis module is connected to the output end of the posture acquisition module, the output end of the posture analysis module is connected to the input end of the control system, the output end of the image acquisition subsystem is connected to the input end of the body shape analysis subsystem, the input end of the facial analysis subsystem, the input end of the clothing recognition subsystem and the input end of the color analysis subsystem, the output end of the body shape analysis subsystem, the output end of the facial analysis subsystem, the output end of the clothing recognition subsystem and the output end of the color analysis subsystem are all connected to the input end of the control system, and the output end of the control system is connected to the input end of the dispenser.

[0014] A media resource playing method, the media resource playing method comprising the following steps:

[0015] S1. Collect images of the audience's human posture and mark them as posture images; collect images of the audience's clothing features and human body features and mark them as recognition images;

[0016] S2, analyzing the head orientation of the audience in the posture image; analyzing the clothing outline, clothing color, body shape and facial features of the audience;

[0017] S3, selecting media resources to be played;

[0018] S4. Analyze the audience's head orientation and the location of the delivery device;

[0019] S5. Play media resources.

[0020] The step S1 comprises the following specific steps:

[0021] S101, the posture acquisition module acquires an image of the audience's posture from above the audience, marks the positions of the left and right shoulder peaks, the nose tip, and the dispenser, and marks the image as a posture image;

[0022] S102: The image acquisition subsystem acquires images of the audience and marks the acquired images as recognition images.

[0023] The step S2 comprises the following specific steps:

[0024] S201, processing the posture image in step S101, the posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the position of the dispenser as L in the coordinate system, L is represented as a straight line formed with the width of the dispenser as a reference, marks the positions of the left and right acromion points and the nose tip in the coordinate system, wherein the coordinates of the left acromion point are Z (XZ, YZ), the coordinates of the right acromion point are Y (XY, YY), and the coordinates of the nose tip are B (XB, YB);

[0025] The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as Lshoulder, where Lshoulder is the width of the audience's shoulders. A vertical line is drawn at the midpoint of the shoulder width line Lshoulder, which is marked as Lcenter. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line Lcenter is marked as a, where the angle a is the orientation of the audience's head, 0°≤a≤90°.

[0026] The posture analysis module performs vector analysis on the left peak point Z and the right peak point Y Calculate and calculate the vector The model is the size of the shoulder width line L shoulder, L shoulder = = The posture analysis module calculates the shoulder width, so that the control system can further determine the age of the audience and improve the accuracy and pertinence of the control system's playback of media resources.

[0027] The step S2 also includes the following specific steps:

[0028] S202, processing the recognition image in step S102, the facial recognition subsystem collects facial features in the recognition image, including the forehead, eyebrows, and brows. When no facial features are collected, the process returns to step S102. When facial features are collected, the facial recognition subsystem performs data analysis on the facial features.

[0029] S203, processing the recognition image in step S102, the body shape analysis subsystem collects the body shape contour of the audience in the recognition image, including the thickness of the front and back, the width of the left and right, the chest, the abdomen and the buttocks, and performs data analysis on the body shape contour; by analyzing the thickness of the front and back and the width of the left and right, the fatness of the audience can be analyzed, and by analyzing the size of the chest, the size of the abdomen and the size of the buttocks, the gender of the audience can be accurately determined to be male or female.

[0030] S204, processing the recognition image in step S102, the clothing recognition subsystem collects the clothing contours of the audience in the recognition image, including the collar, sleeves, and clothing line contours, and performs data analysis on the clothing contours;

[0031] S205, processing the recognition image in step S102, the color analysis subsystem collects the clothing color of the audience in the recognition image, and performs data analysis on the clothing color.

[0032] The step S3 comprises the following specific steps:

[0033] S301, the control system sorts the media resources in the database according to the results analyzed in steps S202 and S203 and the size of the L shoulder in step S201, including sorting by age, gender, and body type;

[0034] S302, the control system screens the sorted media resources again according to the results analyzed in steps S204 and S205, including screening clothing types, clothing colors, and clothing combinations;

[0035] S303: The control system selects media resources to be played according to steps S301 and S302.

[0036] The step S4 comprises the following specific steps:

[0037] S401. According to the content described in step S201, the control system processes the visual line S in step S201. The control system takes the midpoint of the shoulder width line Lshoulder as the starting point and draws a ray based on the visual line S. When the ray does not intersect with the straight line Lcast, steps S101 and S201 are repeated. When the ray intersects with the straight line Lcast, the launcher that forms the straight line Lcast is selected as the launcher for playing the media resource.

[0038] Step S5 includes the following steps:

[0039] The control system selects a delivery device for playing the media resource according to step S401, and the control system plays the media resource selected in step S303 in the delivery device.

[0040] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0041] 1. Through the cooperation between the body shape analysis subsystem and the facial recognition subsystem, the gender of the audience can be analyzed more accurately. By analyzing the gender of the audience, the control system can select the media resources that match the gender of the audience from the database. By analyzing the age and fatness of the audience, the control system can play media resources more targetedly.

[0042] 2. The clothing recognition subsystem collects and analyzes the collar, sleeve, and line outlines of clothing to determine the audience's clothing type, including whether it is a suit or casual wear, men's clothing or women's clothing. The color analysis subsystem analyzes the color of clothing to determine the audience's personality and clothing preferences. The control system plays media resources that meet the audience's preferences based on the analyzed clothing type, personality, and clothing preferences, further improving the accuracy of media resource playback and the targeted nature of media resource playback to the audience, thereby improving the efficiency and effectiveness of media resource delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 It is a schematic diagram of the composition framework structure of a media resource playback system of the present invention;

[0045] Figure 2 It is a schematic diagram of module connection of a media resource playback system of the present invention;

[0046] Figure 3 It is a schematic diagram of the steps of a media resource playback method of the present invention;

[0047] Figure 4 It is a schematic diagram of a facial feature collection process of a media resource playback method of the present invention;

[0048] Figure 5 It is a schematic diagram of a flow chart of a delivery device selection process of a media resource playing method of the present invention;

[0049] Figure 6 It is a simulation schematic diagram of the dispenser selected by the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1-Figure 2 The present invention provides a technical solution: a media resource playback system, which includes a launcher, a matching module, an identification module, and a control system. The identification module and the control system are arranged inside the launcher, and the matching module is arranged outside the launcher.

[0052] The launcher is used to launch media materials, the matching module is used to perform data analysis on the human posture of the audience and transmit the analyzed data to the control system, the identification module is used to perform feature analysis on the audience and transmit the analyzed data to the control system, the control system selects the launcher for playing the media materials according to the analyzed data transmitted by the matching module, the control system selects the type of media materials to be played according to the data transmitted by the identification module, and the control system controls the launcher to play the media materials;

[0053] The matching module includes a posture acquisition module and a posture analysis module. The posture acquisition module acquires images of the audience's posture from above the audience and marks the images as posture images. The content of the posture image includes the audience's head orientation and the position distribution of the dispenser. The posture acquisition module marks the positions of the left and right acromion points, the tip of the nose and the dispenser in the posture image.

[0054] The posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the position of the dispenser as L in the coordinate system, and L represents a straight line formed with the width of the dispenser as the reference. The positions of the left and right acromion points and the tip of the nose are marked in the coordinate system, where the coordinates of the left acromion point are Z (XZ, YZ), the coordinates of the right acromion point are Y (XY, YY), and the coordinates of the tip of the nose are B (XB, YB);

[0055] The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as Lshoulder, where Lshoulder is the width of the audience's shoulders. A vertical line is drawn at the midpoint of the shoulder width line Lshoulder, which is marked as Lcenter. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line Lcenter is marked as a, where the angle a is the orientation of the audience's head, 0°≤a≤90°.

[0056] The posture analysis module performs vector analysis on the left peak point Z and the right peak point Y Calculate and calculate the vector The model is the size of the shoulder width line L shoulder, L shoulder = = .

[0057] The recognition module includes an image acquisition subsystem, a sorting module, and a screening module. The image acquisition subsystem acquires images of the audience and marks them as recognition images. The recognition images include two images on vertical planes perpendicular to each other. The two images are divided into images on the left or right side and images in front. The sorting module analyzes the human body features of the audience in the recognition images, and the screening module analyzes the clothing features of the audience in the recognition images.

[0058] The sorting module includes a body shape analysis subsystem and a facial recognition subsystem;

[0059] The body shape analysis subsystem performs contour analysis on the human body shape of the audience in the recognition image. The body shape analysis subsystem collects the contour of the audience in the recognition image, including the thickness of the front and back of the body, the width of the left and right, the height, the chest, the abdomen and the buttocks, and performs data analysis on the body shape contour. Through the analysis of the body shape, the gender, body shape, fatness and height of the audience can be analyzed;

[0060] The facial recognition subsystem analyzes the facial features of the audience in the recognition image. The facial recognition subsystem collects facial features in the recognition image, including forehead, eyebrows, brows, eyes, nose, mandibular angle, lower cheeks, etc. The facial recognition subsystem performs data analysis on the facial features, and analyzes the gender and age of the audience by analyzing these facial data;

[0061] The control system can accurately determine the gender and age of the person in the hand by combining the gender, body shape, fatness and height analyzed by the body shape analysis subsystem with the gender, age, etc. analyzed by the facial recognition subsystem. Through the analysis of fatness and thinness, media resources can be played to the audience in a targeted manner.

[0062] The screening module includes clothing recognition subsystem and color analysis subsystem;

[0063] The clothing recognition subsystem performs contour analysis on the clothing in the recognition image. The clothing recognition subsystem collects the clothing contours of the audience in the recognition image, including the collar, sleeves, and clothing line contours, and performs data analysis on the clothing contours to analyze the audience's clothing type, including whether it is a suit or casual wear, men's wear or women's wear;

[0064] The color analysis subsystem analyzes the color of clothing in the recognition image. The color analysis subsystem analyzes the color of clothing to determine the audience's personality and clothing preferences. The control system plays media resources that meet the audience's preferences based on the analyzed clothing type, personality, and clothing preferences.

[0065] The control system includes a database, which is used to store various media resources.

[0066] The input end of the posture analysis module is connected to the output end of the posture acquisition module, the output end of the posture analysis module is connected to the input end of the control system, the output end of the image acquisition subsystem is connected to the input end of the body shape analysis subsystem, the input end of the facial analysis subsystem, the input end of the clothing recognition subsystem and the input end of the color analysis subsystem, the output end of the body shape analysis subsystem, the output end of the facial analysis subsystem, the output end of the clothing recognition subsystem and the output end of the color analysis subsystem are all connected to the input end of the control system, and the output end of the control system is connected to the input end of the dispenser.

[0067] See also Figure 3-Figure 6 , a media resource playing method, the media resource playing method comprising the following steps:

[0068] S1. Collect images of the audience's human posture and mark them as posture images; collect images of the audience's clothing features and human body features and mark them as recognition images;

[0069] S2, analyzing the head orientation of the audience in the posture image; analyzing the clothing outline, clothing color, body shape and facial features of the audience;

[0070] S3, selecting media resources to be played;

[0071] S4. Analyze the audience's head orientation and the location of the delivery device;

[0072] S5. Play media resources.

[0073] Step S1 includes the following specific steps:

[0074] S101, the posture acquisition module acquires an image of the audience's posture from above the audience, marks the positions of the left and right shoulder peaks, the nose tip, and the dispenser, and marks the image as a posture image;

[0075] S102: The image acquisition subsystem acquires images of the audience and marks the two acquired images as recognition images.

[0076] Step S2 includes the following specific steps:

[0077] S201, processing the posture image in step S101, the posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the position of the dispenser as L in the coordinate system, L is represented as a straight line formed with the width of the dispenser as a reference, marks the positions of the left and right acromion points and the tip of the nose in the coordinate system, wherein the coordinates of the left acromion point are Z (XZ, YZ), the coordinates of the right acromion point are Y (XY, YY), and the coordinates of the tip of the nose are B (XB, YB);

[0078] The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as Lshoulder, where Lshoulder is the width of the audience's shoulders. A vertical line is drawn at the midpoint of the shoulder width line Lshoulder, which is marked as Lcenter. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line Lcenter is marked as a, where the angle a is the orientation of the audience's head, 0°≤a≤90°.

[0079] The posture analysis module performs vector analysis on the left peak point Z and the right peak point Y Calculate and calculate the vector The model is the size of the shoulder width line L shoulder, L shoulder = = .

[0080] Step S2 also includes the following specific steps:

[0081] S202, processing the recognition image in step S102, the facial recognition subsystem collects facial features in the recognition image, including the forehead, eyebrows, and brows. When no facial features are collected, the process returns to step S102. When facial features are collected, the facial recognition subsystem performs data analysis on the facial features.

[0082] S203, processing the recognition image in step S102, the body shape analysis subsystem collects the body shape of the audience in the recognition image, including the thickness of the front and back, the width of the left and right, the chest, abdomen and buttocks, and performs data analysis on the body shape contour;

[0083] S204, processing the recognition image in step S102, the clothing recognition subsystem collects the clothing contours of the audience in the recognition image, including the collar, sleeves, and clothing line contours, and performs data analysis on the clothing contours;

[0084] S205, processing the recognition image in step S102, the color analysis subsystem collects the clothing color of the audience in the recognition image, and performs data analysis on the clothing color.

[0085] Step S3 includes the following specific steps:

[0086] S301, the control system sorts the media resources in the database according to the results analyzed in steps S202 and S203 and the size of the L shoulder in step S201, including sorting by age, gender, and body type;

[0087] S302, the control system screens the sorted media resources again according to the results analyzed in steps S204 and S205, including screening clothing types, clothing colors, and clothing combinations;

[0088] S303: The control system selects media resources to be played according to steps S301 and S302.

[0089] Step S4 includes the following specific steps:

[0090] S401. According to the content described in step S201, the control system processes the visual line S in step S201. The control system takes the midpoint of the shoulder width line Lshoulder as the starting point and draws a ray based on the visual line S. When the ray does not intersect with the straight line Lcast, steps S101 and S201 are repeated. When the ray intersects with the straight line Lcast, the launcher that forms the straight line Lcast is selected as the launcher for playing the media resource.

[0091] Step S5 includes the following steps:

[0092] The control system selects a delivery device for playing the media resource according to step S401, and the control system plays the media resource selected in step S303 in the delivery device.

[0093] When the ray does not intersect the straight line L, the launcher does not play the media resource; when the facial recognition system cannot collect facial features, the launcher does not play the media resource.

[0094] Embodiment 1:

[0095] Taking the media resource playback in an elevator as an example, this embodiment includes two dispensers.

[0096] The matching module is arranged above the interior of the elevator. The posture acquisition module acquires images of the audience entering the elevator from top to bottom and marks them as posture images. The positions of the left and right shoulder points, the tip of the nose and the dispenser are marked in the posture images.

[0097] The posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the location of the dispenser as Lthrow 1 and Lthrow 2 in the coordinate system, and marks the location of the left and right acromion points and the tip of the nose in the coordinate system, where the coordinates of the left acromion point are Z (20, 50), the coordinates of the right acromion point are Y (5, 35), and the coordinates of the tip of the nose are B (17, 36);

[0098] The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as Lshoulder, where Lshoulder is the width of the audience's shoulders. A vertical line is drawn at the midpoint of the shoulder width line Lshoulder, and the vertical line is marked as Lzhong. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line Lzhong is marked as a. The angle a is the orientation of the audience's head, 0°≤a≤90°. The posture analysis module calculates the angle a and obtains a=30°. The control system processes the visual line S, and the control system uses the midpoint of the shoulder width line Lshoulder as the starting point and draws a ray based on the visual line S. When the ray intersects the straight line Lcast1, the launcher that forms the straight line Lcast1 is selected as the launcher for playing the media resource.

[0099] The posture analysis module performs vector analysis on the left peak point Z and the right peak point Y Calculate and calculate the vector The model is the size of the shoulder width line L shoulder, L shoulder = = ≈21.21, the posture analysis module calculates the shoulder width, so that the control system can further determine the age of the audience and improve the accuracy and pertinence of the control system's playback of media resources.

[0100] While the posture acquisition module is acquiring images of the audience, the image acquisition subsystem is also acquiring images of the audience;

[0101] The facial recognition subsystem collects facial features in the recognition image, and when the facial features are collected, the facial recognition subsystem performs data analysis on the facial features;

[0102] While the facial recognition subsystem is analyzing the data of facial features, the body shape analysis subsystem, clothing recognition subsystem, and color analysis subsystem are all processing the data in the recognition image;

[0103] The body shape analysis subsystem collects the body shape of the audience in the recognition image, including the thickness of the front and back, the width of the left and right, the chest, abdomen and buttocks, and performs data analysis on the body shape contour;

[0104] The clothing recognition subsystem collects the clothing contours of the audience in the recognition image, including the collar, sleeves, and clothing line contours, and performs data analysis on the clothing contours;

[0105] The color analysis subsystem collects the clothing colors of the audience in the recognition image and performs data analysis on the clothing colors.

[0106] The facial recognition subsystem extracts and analyzes the facial features of the audience, thereby analyzing the gender and age of the audience. The body shape analysis subsystem analyzes the body shape of the audience, including the thickness from front to back and the width from left to right, thereby analyzing the fatness and gender of the audience. Through the cooperation between the body shape analysis subsystem and the facial recognition subsystem, the gender of the audience can be analyzed more accurately. By analyzing the gender of the audience, the control system can select the media resources that match the gender of the audience from the database. By analyzing the age and fatness of the audience, the control system can play media resources in a more targeted manner.

[0107] The clothing recognition subsystem collects and analyzes the collar, sleeve, and line outlines of clothing to determine the audience's clothing type, including whether it is a suit or casual wear, men's or women's clothing. The color analysis subsystem analyzes the color of clothing to determine the audience's personality and clothing preferences. The control system plays media resources that meet the audience's preferences based on the analyzed clothing type, personality, and clothing preferences, further improving the accuracy of media resource playback and the targeted nature of media resource playback to the audience, thereby improving the efficiency and effectiveness of media resource delivery.

[0108] The control system selects media resources that meet the playback conditions from the database and plays them on the launcher.

[0109] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0110] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A media resource playback system, characterized in that: The media resource playback system includes a launcher, a matching module, an identification module, and a control system; The dispenser is used to dispense media materials, the matching module is used to perform data analysis on the human posture of the audience and transmit the analyzed data to the control system, the identification module is used to perform feature analysis on the audience and transmit the analyzed data to the control system, the control system selects a dispenser for playing media materials according to the analyzed data transmitted by the matching module, the control system selects the type of media materials to be played according to the data transmitted by the identification module, and the control system controls the dispenser to play the media materials; The matching module includes a posture acquisition module and a posture analysis module, wherein the posture acquisition module acquires images of the posture of a human body when standing and marks them as posture images, and the posture analysis module analyzes the head orientation of the human body in the posture image; The recognition module includes an image acquisition subsystem, a sorting module, and a screening module. The image acquisition subsystem acquires images of the audience and marks them as recognition images. The sorting module analyzes the human body features of the audience in the recognition images. The screening module analyzes the clothing features of the audience in the recognition images. The sorting module includes a body shape analysis subsystem and a facial recognition subsystem. The body shape analysis subsystem performs a contour analysis on the body shape of the audience in the recognition image, and the facial recognition subsystem performs an analysis on the facial features of the audience in the recognition image. The screening module includes a clothing recognition subsystem and a color analysis subsystem. The clothing recognition subsystem performs contour analysis on clothing in the recognition image, and the color analysis subsystem analyzes the color of clothing in the recognition image. The recognition image includes two images on vertical planes perpendicular to each other; the control system includes a database, and the database is used to store various media resources; The input end of the posture analysis module is connected to the output end of the posture acquisition module, the output end of the posture analysis module is connected to the input end of the control system, the output end of the image acquisition subsystem is connected to the input end of the body shape analysis subsystem, the input end of the facial analysis subsystem, the input end of the clothing recognition subsystem and the input end of the color analysis subsystem, the output end of the body shape analysis subsystem, the output end of the facial analysis subsystem, the output end of the clothing recognition subsystem and the output end of the color analysis subsystem are all connected to the input end of the control system, and the output end of the control system is connected to the input end of the dispenser; The posture acquisition module acquires images of the audience's posture from above the audience and marks the images as posture images. The content of the posture images includes the audience's head orientation and the position distribution of the dispenser. The posture acquisition module marks the positions of the left and right shoulder peaks, the nose tip, and the dispenser in the posture images. The posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the position of the dispenser as L in the coordinate system, and L represents a straight line formed with the width of the dispenser as the reference. The positions of the left and right acromion points and the tip of the nose are marked in the coordinate system, where the coordinates of the left acromion point are Z (XZ, YZ), the coordinates of the right acromion point are Y (XY, YY), and the coordinates of the tip of the nose are B (XB, YB); The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as L shoulder. L shoulder is the width of the audience's shoulder. A vertical line is drawn at the midpoint of the shoulder width line L shoulder, which is marked as L center. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line L center is marked as , angle is the orientation of the audience’s head, 0°≤ ≤90°; The control system uses the midpoint of the shoulder width line Lshoulder as the starting point and the visual line S as the reference to draw a ray. When the ray intersects the straight line Lcast, the dispenser forming the straight line Lcast is selected as the dispenser for playing the media resource. When the ray does not intersect the straight line L, the launcher does not play the media resource; when the facial recognition system cannot collect facial features, the launcher does not play the media resource.

2. A method dedicated to a media resource playback system as claimed in claim 1, characterized in that: The steps include: S1. Collect images of the audience's human posture and mark them as posture images; collect images of the audience's clothing features and human body features and mark them as recognition images; S2, analyzing the head orientation of the audience in the posture image; analyzing the clothing outline, clothing color, body shape and facial features of the audience; S3, selecting media resources to be played; S4. Analyze the audience's head orientation and the location of the delivery device; S5. Play media resources.

3. The method according to claim 2, characterized in that: The step S1 comprises the following specific steps: S101, the posture acquisition module acquires an image of the audience's posture from above the audience, marks the positions of the left and right shoulder peaks, the nose tip, and the dispenser, and marks the image as a posture image; S102: The image acquisition subsystem acquires images of the audience and marks the acquired images as recognition images.

4. The method according to claim 3, characterized in that: The step S2 comprises the following specific steps: S201, processing the posture image in step S101, the posture analysis module establishes a plane coordinate system with one corner of the posture image as the origin of the coordinate system, marks the position of the dispenser as L in the coordinate system, L is represented as a straight line formed with the width of the dispenser as a reference, marks the positions of the left and right acromion points and the nose tip in the coordinate system, wherein the coordinates of the left acromion point are Z (XZ, YZ), the coordinates of the right acromion point are Y (XY, YY), and the coordinates of the nose tip are B (XB, YB); The posture analysis module connects the left peak point Z with the right peak point Y to form a shoulder width line, which is marked as L shoulder. L shoulder is the width of the audience's shoulder. A vertical line is drawn at the midpoint of the shoulder width line L shoulder, which is marked as L center. The posture analysis module connects the midpoint with the nose tip B to form a visual line S, and the angle between the visual line S and the vertical line L center is marked as , angle is the orientation of the audience’s head, 0°≤ ≤90°; The posture analysis module performs vector analysis on the left peak point Z and the right peak point Y Calculate and calculate the vector The model is the size of the shoulder width line L shoulder, L shoulder = = .

5. The method according to claim 4, characterized in that: The step S2 also includes the following specific steps: S202, processing the recognition image in step S102, the facial recognition subsystem collects facial features in the recognition image, including the forehead, eyebrows, and brows. When no facial features are collected, the process returns to step S102. When facial features are collected, the facial recognition subsystem performs data analysis on the facial features. S203, processing the recognition image in step S102, the body shape analysis subsystem collects the body shape of the audience in the recognition image, including the thickness of the front and back, the width of the left and right, the chest, abdomen and buttocks, and performs data analysis on the body shape contour; S204, processing the recognition image in step S102, the clothing recognition subsystem collects the clothing contours of the audience in the recognition image, including the collar, sleeves, and clothing line contours, and performs data analysis on the clothing contours; S205, processing the recognition image in step S102, the color analysis subsystem collects the clothing color of the audience in the recognition image, and performs data analysis on the clothing color.

6. The method according to claim 5, characterized in that: The step S3 comprises the following specific steps: S301, the control system sorts the media resources in the database according to the results analyzed in steps S202 and S203 and the size of the L shoulder in step S201, including sorting by age, gender, and body type; S302, the control system screens the sorted media resources again according to the results analyzed in steps S204 and S205, including screening clothing types, clothing colors, and clothing combinations; S303: The control system selects media resources to be played according to steps S301 and S302.

7. The method according to claim 6, characterized in that: The step S4 comprises the following specific steps: S401, according to the content described in step S201, the control system processes the visual line S in step S201, the control system takes the midpoint of the shoulder width line Lshoulder as the starting point, and takes the visual line S as the reference to make a ray, when the ray does not intersect with the straight line Lcast, repeat steps S101 and S201, when the ray intersects with the straight line Lcast, select the dispenser forming the straight line Lcast as the dispenser for playing the media resource; Step S5 includes the following steps: The control system selects a delivery device for playing the media resource according to step S401, and the control system plays the media resource selected in step S303 in the delivery device.

Images