Data processing method for vertical advertising machine and vertical advertising machine
By monitoring and identifying vibration and appearance features in real time on vertical advertising machines, the problem of not being able to identify vandals is solved, and more accurate vandal identification and tracking is achieved.
Patent Information
- Application Number
- CN202410101076.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-24
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-01-24
AI Technical Summary
When an existing vertical advertising machine is destroyed, it cannot start the camera, resulting in the inability to obtain photos of the vandal, and if the vandal blocks the facial features, it is difficult to identify the vandal.
Design a vertical advertising machine equipped with a camera, vibration sensor and processing module to monitor the environment in real time, determine the vibration value and whether there are active elbows in front of the camera, if detected, perform facial feature extraction or appearance feature recognition, and in history Surveillance video data searches for similar features and sends video clips and alert information to the background.
Even if the destroyer blocks the facial features, it can also provide backend reference by searching for people with similar features to the destroyer's appearance in historical video data, improving the accuracy and efficiency of the destroyer's identification, and solving the problem of the camera being unable to start and feature occlusion. question.
Smart Images

Figure CN118053240B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of advertising machines, and in particular to a data processing method for a vertical advertising machine and a vertical advertising machine. Background Art
[0002] Advertising machines are a new generation of intelligent devices. They form a complete advertising broadcast control system through terminal software control, network information transmission and multimedia terminal display, and use multimedia materials such as pictures, texts, videos, etc. for advertising. At present, most vertical advertising machines use LCD display screens, which are relatively expensive. If someone maliciously damages the LCD display screen of a vertical advertising machine, it will cause great losses to the merchant. At present, some advertising machines are already equipped with vibration sensors and cameras. When the vibration value of the vibration sensor is detected to be greater than the set threshold and a human body is detected, the camera is turned on to shoot the vandal, which makes it easier to find the vandal of the advertising machine later. However, if the camera cannot be started when the advertising machine is damaged, then it is impossible to obtain a photo of the vandal. In addition, if the vandal blocks the facial features, it is difficult to find the vandal even if the vandal's photo is obtained. Therefore, how to overcome this problem is an issue that needs to be solved urgently. Summary of the invention
[0003] The main purpose of the present invention is to provide a vertical advertising machine, aiming to solve the above-mentioned technical problems and to more accurately identify vandals.
[0004] A first aspect of the present invention provides a vertical advertising machine, the vertical advertising machine comprising: a camera, arranged on the front of the vertical advertising machine; a vibration sensor, used to detect the vibration of the vertical advertising machine; a memory, used to store data, including storing monitoring video data; a display screen, used to display, including text, images and videos, the camera is used to monitor the environment around the vertical advertising machine in real time; the processing module is used to:
[0005] Determining the range of the vibration value of the vibration sensor;
[0006] Detecting whether there is a person moving his elbow in front of the camera;
[0007] If it is detected at the same time that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, facial features of the person moving his elbow are extracted;
[0008] If the complete facial features cannot be extracted, the person moving the elbow is taken as the target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features;
[0009] Searching historical surveillance video data to see if there is a person with similar appearance features;
[0010] If so, extracting the video clip of the person with similar appearance features;
[0011] The video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0012] Furthermore, the key points of the human body include a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist and a right wrist, and the detection of whether there is a person moving his elbow in front of the camera includes
[0013] Obtaining the current video frame captured by the camera;
[0014] Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person;
[0015] Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person;
[0016] Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder;
[0017] If so, it is determined that the person in the posture sequence is moving his elbow;
[0018] If not present, it is determined that the person in the posture sequence is not moving his elbows.
[0019] Furthermore, the memory is also used to store a legal publicity video; wherein the legal publicity video is used to publicize the relevant consequences of damaging public facilities;
[0020] If the processing module simultaneously detects that the vibration value is within a preset second range and detects that there is a person moving his elbow in front of the camera, the processing module is further configured to:
[0021] Controlling the display screen of the vertical advertising machine to perform split-screen display, and dividing it into a first display area and a second display area;
[0022] The legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area; wherein the numerical value in the second range is smaller than the numerical value in the first range.
[0023] Furthermore, the vertical advertising machine also includes an alarm. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further used to control the alarm to sound an alarm.
[0024] Furthermore, the alarm is a sound alarm or an acousto-optic alarm.
[0025] Furthermore, the vertical advertising machine also includes a positioning module, which is connected to the processing module. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further used to:
[0026] Acquiring positioning data of the positioning module;
[0027] The positioning data and the alarm information are sent to the background of the vertical advertising machine.
[0028] Furthermore, the vertical advertising machine further includes a speaker, which is connected to the processing module. After the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the background of the vertical advertising machine, the processing module is also used to:
[0029] Receiving voice information sent by the monitoring background of the vertical advertising machine;
[0030] The voice information is played through the speaker.
[0031] Furthermore, the processing module is also used for:
[0032] The surveillance video stored in the memory is deleted regularly.
[0033] Furthermore, if it is detected that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, after extracting facial features of the person moving his elbow, the processing module is further used to:
[0034] If complete facial features are extracted, a facial image of the target person is collected;
[0035] Performing denoising and image enhancement processing on the face image in sequence to obtain a processed face image;
[0036] The processed face image, the video clip collected by the camera when the vibration value is within the first range, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0037] Furthermore, the alarm information also includes an image of the vertical advertising machine.
[0038] In a second aspect, an embodiment of the present application provides a data processing method for a vertical advertising machine, wherein the vertical advertising machine includes a camera, a vibration sensor, and a memory, wherein the camera is arranged on the front of the vertical advertising machine, the vibration sensor is used to detect the vibration of the vertical advertising machine, and the memory is used to store data, including storing monitoring video data. The camera is used to monitor the environment around the vertical advertising machine in real time, and the method includes:
[0039] Acquiring a vibration value detected by the vibration sensor;
[0040] Determining the range of the vibration value;
[0041] Detecting whether there is a person moving his elbow in front of the camera;
[0042] If it is detected at the same time that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, facial features of the person moving his elbow are extracted;
[0043] If the complete facial features cannot be extracted, the person moving the elbow is taken as the target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features;
[0044] Searching historical surveillance video data to see if there is a person with similar appearance features;
[0045] If so, extracting the video clip of the person with similar appearance features;
[0046] The video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0047] Furthermore, the key points of the human body include a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist and a right wrist, and the detection of whether there is a person moving his elbow in front of the camera includes
[0048] Obtaining the current video frame captured by the camera;
[0049] Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person;
[0050] Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person;
[0051] Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder;
[0052] If so, it is determined that the person in the posture sequence is moving his elbow;
[0053] If not present, it is determined that the person in the posture sequence is not moving his elbows.
[0054] Furthermore, the memory is also used to store a legal publicity video, which is used to publicize the relevant consequences of damaging public facilities. After the step of detecting whether there is a person moving his elbow in front of the camera, the method also includes:
[0055] If it is detected at the same time that the vibration value is within the preset second range and that a person is moving his elbow in front of the camera, the display screen of the vertical advertising machine is controlled to be split-screen and divided into a first display area and a second display area;
[0056] The legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area; wherein the numerical value in the second range is smaller than the numerical value in the first range.
[0057] Beneficial effects:
[0058] The vertical advertising machine provided by the embodiment of the present application is configured to: determine the range of the vibration value of the vibration sensor; detect whether there is a person moving his elbow in front of the camera; if it is detected that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, extract facial features of the person moving his elbow; if the complete facial features cannot be extracted, take the person moving his elbow as a target person and identify the appearance features of the target person; wherein the appearance features include: clothing features and body shape features; search whether there is a person similar to the appearance features in the historical monitoring video data; if there is, extract the video clip of the person similar to the appearance features; send the video clip collected by the camera when the vibration value is within the first range, the video clip of the person similar to the appearance features, and the alarm information to the background of the vertical advertising machine, so that even if the vandal blocks the facial features, the person with similar appearance features as the vandal in the historical video data can be searched and provided to the background for reference, so that the vandal can be identified more accurately and is more conducive to finding the vandal. In addition, the camera on the advertising machine of the present application does not need to be turned on when the vibration value is greater than the set value, but monitors in real time. Therefore, the problem that the camera cannot be started when the existing advertising machine is damaged and the photo of the destroyer cannot be obtained is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] Figure 1 It is a flow chart of a data processing method of a vertical advertising machine.
[0060] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0062] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "a", "an", "above", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of features, integers, steps, operations, elements, modules, modules and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more associated listed items.
[0063] Those skilled in the art will understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.
[0064] The embodiment of the present application provides a vertical advertising machine, which includes: a camera, which is arranged on the front of the vertical advertising machine; a vibration sensor, which is used to detect the vibration of the vertical advertising machine; a memory, which is used to store data, including storing monitoring video data; a display screen, which is used to display, including text, images and videos, and the camera is used to monitor the environment around the vertical advertising machine in real time; the processing module is used to perform the following steps:
[0065] S1. Determine the range of the vibration value of the vibration sensor;
[0066] S2, detecting whether there is a person moving his elbow in front of the camera;
[0067] S3, if it is detected that the vibration value is within the preset first range and it is detected that there is a person moving his elbow in front of the camera, extracting facial features of the person moving his elbow;
[0068] S4. If the complete facial features cannot be extracted, the person moving the elbow is taken as a target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features;
[0069] S5. Searching the historical surveillance video data for a person with similar appearance features;
[0070] S6. If so, extract the video clip of the person with similar appearance features;
[0071] S7. Send the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and alarm information to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0072] In the embodiment of the present application, the front of the advertising machine refers to the side on which the display screen is installed, the camera is arranged above the display screen of the advertising machine, and the vibration sensor may be provided in plurality. When multiple vibration sensors are provided, the average of the vibration values of the vibration sensors is taken as the vibration value of the advertising machine. The display screen of the advertising machine is an LCD (Liquid Crystal Display) display screen. The processing module is used to execute steps S1-S7. Specifically, the steps S1 and S2 are performed simultaneously, that is, the processing module can also detect whether there is a person moving his elbow in front of the camera when judging the range of the vibration value of the vibration sensor. Detection of whether there is a person moving his elbow in front of the camera will be described later, so it will not be elaborated on here. In step S3, if the vibration value is within the preset first range, it means that the advertising machine is hit with great force, which has reached the point where it can be determined that the advertising machine is maliciously damaged. However, the vibration value within the preset first range may also be caused by non-human factors, such as being affected by an earthquake or other external vibrations. Therefore, it is also necessary to detect whether there is a person in front of the camera. Since there may be multiple people passing or staying in front of the advertising machine, when people damage the advertising machine, they generally wave their hands to directly hit it or use external objects to hit it. Therefore, in order to improve the accuracy of identifying the vandal, people who are moving their elbows are detected as target persons. In addition, in order to determine whether the target person covers his face, for example, wearing a mask, sunglasses, etc., the facial features of the person are extracted, specifically, the features of the eyes, nose and mouth of the person are extracted. If any one of the eyes, nose and mouth cannot be identified, it is determined that the complete facial features cannot be extracted. Next, the appearance features of the target person are identified; wherein the appearance features include: wearing features and body shape features; wearing features can specifically be the color of clothes, the type of clothes (such as short sleeves, long sleeves, coats, suits), the color of pants (suits, jeans, sweatpants, casual pants), the color of shoes, hair color, and the appearance features can be height, shoulder width, etc. Since color recognition is required, the camera needs to use an RGB camera, and the height and shoulder width of the target person can be determined by the key points of the human body, which can include: head, neck, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee, left ankle and right ankle, etc., which can be determined according to the distance from the head to the left ankle, and the shoulder width can be determined according to the distance between the left shoulder and the right shoulder. It can also be determined by the outline of the human body, that is, the distance between the top of the head and the ground, and the distance between the outer outline of the left shoulder and the outer outline of the right shoulder.In step S4, generally speaking, people's clothing rarely changes in a short period of time. For example, within a week, they wear the first set on the first day, the second set on the second day, and the first set again on the third day. Therefore, by identifying the target person's clothing characteristics combined with the body shape characteristics, people with similar appearance characteristics to the target person can be found in the historical video data. The video segments of the people with similar appearance characteristics to the target person and the video segments of the target person are sent to the background of the advertising machine and stored, and provided to the police, which is conducive to reducing the difficulty of finding the vandal. In addition, the police do not need to view a large number of videos, thereby improving the work efficiency of the police and reducing the workload of the police.
[0073] Through the above settings, even if the vandal covers his facial features, people with similar appearance features to the vandal can be searched in the historical video data and provided to the background for reference, which is more conducive to finding the vandal. In addition, the camera on the advertising machine of the present application does not need to be turned on when the vibration value is greater than the set value, but is monitored in real time. Therefore, the problem that the camera cannot be turned on when the existing advertising machine is damaged, so the vandal's photo cannot be obtained.
[0074] In one embodiment, the key points of the human body include a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist, and a right wrist, and detecting whether there is a person moving his elbow in front of the camera includes:
[0075] Obtaining the current video frame captured by the camera;
[0076] Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person;
[0077] Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person;
[0078] Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder;
[0079] If so, it is determined that the person in the posture sequence is moving his elbow;
[0080] If not present, it is determined that the person in the posture sequence is not moving his elbows.
[0081] In this embodiment, the purpose is to provide a method for detecting whether there is a person moving his elbow in front of the camera. Specifically, after obtaining a posture sequence of the same person, the elbow joint angle in each posture in the posture sequence is calculated, and based on the elbow joint angle sequence corresponding to the posture sequence, it is determined whether there is a posture in the posture sequence with an elbow joint angle within a set range, and the elbow joint angles of two adjacent postures are different. If so, it is determined that the person in the posture sequence is moving his elbow, otherwise it is determined that the person in the posture sequence is not moving his elbow. In this way, it is possible to determine whether there is a person moving his elbow in front of the camera, laying the foundation for the implementation of subsequent solutions. It should be noted that extracting the posture sequence of the same person based on video frames is a prior art, and the embodiments of the present invention will not be elaborated in detail here.
[0082] In one embodiment, the memory is further used to store a legal publicity video; wherein the legal publicity video is used to publicize the relevant consequences of damaging public facilities;
[0083] If the processing module simultaneously detects that the vibration value is within a preset second range and detects that there is a person moving his elbow in front of the camera, the processing module is further configured to:
[0084] Controlling the display screen of the vertical advertising machine to perform split-screen display, and dividing it into a first display area and a second display area;
[0085] The legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area; wherein the numerical value in the second range is smaller than the numerical value in the first range.
[0086] In this embodiment, if the vibration value is within the preset second range, it means that the advertising machine has been gently tapped, and the tapping force is not large. This situation is considered to be non-malicious tapping. Therefore, by controlling the display screen of the vertical advertising machine to display a legal publicity video, and the legal publicity video is used to publicize the relevant consequences of damaging public facilities, it can serve as a warning to people who tap the advertising machine, and they dare not continue to tap, thereby reducing the damage to the advertising machine. In addition, when some users click on the advertising machine, if they use too much force, the vibration value of the vibration sensor will be within the preset second range. If the page currently displayed by the advertising machine is directly replaced with the legal publicity video, it will affect the user experience. Therefore, when the present application detects that the vibration value is within the preset second range and that there is a person moving his elbow in front of the camera, the display screen of the vertical advertising machine is controlled to display in a split screen, and is divided into a first display area and a second display area; the legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area, which can avoid affecting the user experience and also serve as a warning to people who tap the advertising machine.
[0087] In one embodiment, the vertical advertising machine further includes an alarm. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further used to control the alarm to sound an alarm.
[0088] If it is detected at the same time that the vibration value is within the preset first range and a person moving his elbow is detected in front of the camera, it means that the advertising machine is being damaged. The advertising machine also includes an alarm, and when it is detected that the advertising machine is being damaged, the alarm is controlled to sound an alarm, which is beneficial for merchants / staff to grasp the situation in time, and to discover the destructive behavior or catch the vandal in time.
[0089] In one embodiment, the alarm is a sound alarm or a sound and light alarm.
[0090] In this embodiment, the sound alarm or the sound and light alarm uses sound to give an alarm, and the sound alarm can quickly attract the attention of merchants or staff. Therefore, the sound alarm or the sound and light alarm is helpful for merchants or staff to quickly discover the vandalism or catch the vandal.
[0091] In one embodiment, the vertical advertising machine further includes a positioning module, and the positioning module is connected to the processing module. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further configured to:
[0092] Acquiring positioning data of the positioning module;
[0093] The positioning data and the alarm information are sent to the background of the vertical advertising machine.
[0094] In the embodiment of the present application, by setting a positioning module on the advertising machine and sending the positioning data of the positioning module, that is, the location of the advertising machine to the background of the vertical advertising machine, it is helpful for merchants / staff to quickly understand where the damaged advertising machine is.
[0095] In one embodiment, the vertical advertising machine further includes a speaker, which is connected to the processing module. After the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the background of the vertical advertising machine, the processing module is further used to:
[0096] Receiving voice information sent by the monitoring background of the vertical advertising machine;
[0097] The voice information is played through the speaker.
[0098] In the embodiment of the present application, by providing a speaker on the vertical advertising machine and playing the voice message sent by the monitoring background through the speaker, the vandal can be warned remotely, which has a deterrent effect on the vandal. The vandal may stop the destructive behavior out of fear, so that the advertising machine can avoid further damage and reduce the loss of the merchant.
[0099] In one embodiment, the processing module is further configured to:
[0100] The surveillance video stored in the memory is deleted regularly.
[0101] In the embodiment of the present application, the smooth operation of the advertising machine can be ensured by regularly deleting the surveillance video stored in the memory. In addition, the timing time can be set according to the actual situation. Further, the surveillance video stored in the memory can also be deleted according to the remaining storage space of the memory. Specifically, when the remaining storage space of the memory is less than a set threshold, the surveillance video stored in the memory is deleted.
[0102] In one embodiment, if it is simultaneously detected that the vibration value is within a preset first range and that a person moving his elbow is present in front of the camera, after extracting facial features of the person moving his elbow, the processing module is further configured to:
[0103] If complete facial features are extracted, a facial image of the target person is collected;
[0104] Performing denoising and image enhancement processing on the face image in sequence to obtain a processed face image;
[0105] The processed face image, the video clip collected by the camera when the vibration value is within the first range, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0106] In an embodiment of the present application, if complete facial features are extracted, it is considered that the target person does not cover his face. At this time, the facial image of the target person is collected and the facial image is subjected to denoising and image enhancement processing in sequence. This can improve the recognition of the target person and facilitate back-end management personnel (merchants or staff) to find the vandals.
[0107] In one embodiment, the alarm information further includes an image of the vertical advertising machine.
[0108] In the embodiment of the present application, by making the alarm information also include the image of the vertical advertising machine, the backstage management personnel can have a more vivid understanding of the damaged advertising machine, which facilitates the backstage management personnel to quickly find the damaged advertising machine.
[0109] Embodiment 2:
[0110] The present application also provides a data processing method for a vertical advertising machine, wherein the vertical advertising machine comprises a camera, a vibration sensor and a memory, wherein the camera is arranged on the front of the vertical advertising machine, the vibration sensor is used to detect the vibration of the vertical advertising machine, the memory is used to store data, including storing monitoring video data, and the camera is used to monitor the environment around the vertical advertising machine in real time. The method comprises: Figure 1 As shown:
[0111] S21, obtaining the vibration value detected by the vibration sensor;
[0112] S22, determining the range of the vibration value;
[0113] S23, detecting whether there is a person moving his elbow in front of the camera;
[0114] S24, if it is detected that the vibration value is within the preset first range and it is detected that there is a person moving his elbow in front of the camera, extracting facial features of the person moving his elbow;
[0115] S25, if the complete facial features cannot be extracted, the person moving the elbow is taken as a target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features;
[0116] S26, searching the historical surveillance video data for a person with similar appearance features;
[0117] S27, if it exists, extracting the video clip of the person with similar appearance features;
[0118] S28. Send the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and alarm information to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
[0119] It should be noted that the data processing method of the above-mentioned vertical advertising machine and the step flow and method processed by the processing module of the above-mentioned vertical advertising machine are the same. Therefore, the above-mentioned explanations and descriptions of the first embodiment are applicable to the embodiment of the present application. Therefore, the embodiment of the present application will not be described in detail here.
[0120] In one embodiment, the key points of the human body include a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist, and a right wrist, and the detecting whether there is a person moving his elbow in front of the camera includes
[0121] Obtaining the current video frame captured by the camera;
[0122] Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person;
[0123] Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person;
[0124] Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder;
[0125] If so, it is determined that the person in the posture sequence is moving his elbow;
[0126] If not present, it is determined that the person in the posture sequence is not moving his elbows.
[0127] Furthermore, the memory is also used to store a legal publicity video, which is used to publicize the relevant consequences of damaging public facilities. After the step of detecting whether there is a person moving his elbow in front of the camera, the method also includes:
[0128] If it is detected at the same time that the vibration value is within the preset second range and that a person is moving his elbow in front of the camera, the display screen of the vertical advertising machine is controlled to be split-screen and divided into a first display area and a second display area;
[0129] The legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area; wherein the numerical value in the second range is smaller than the numerical value in the first range.
[0130] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0131] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0132] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A vertical advertising machine, comprising: A camera is arranged on the front of the vertical advertising machine; a vibration sensor is used to detect the vibration of the vertical advertising machine; A memory for storing data, including storing surveillance video data; The display screen is used for displaying, including text, images and videos, wherein the camera is used for real-time monitoring of the environment around the vertical advertising machine; the processing module is used for: Determining the range of the vibration value of the vibration sensor; Detecting whether there is a person moving his elbow in front of the camera; If it is detected at the same time that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, facial features of the person moving his elbow are extracted; If the complete facial features cannot be extracted, the person moving the elbow is taken as the target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features; Searching historical surveillance video data to see if there is a person with similar appearance features; If so, extracting the video clip of the person with similar appearance features; Sending the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and alarm information to the backend of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine; The memory is also used to store legal publicity videos; If the processing module simultaneously detects that the vibration value is within a preset second range and detects that there is a person moving his elbow in front of the camera, the processing module is further configured to: Controlling the display screen of the vertical advertising machine to perform split-screen display, and dividing it into a first display area and a second display area; Displaying the legal publicity video in the first display area and displaying the advertising content in the second display area; wherein the value in the second range is smaller than the value in the first range; The key points of the human body include the left shoulder, the right shoulder, the left elbow, the right elbow, the left wrist and the right wrist. The detecting whether there is a person moving his elbow in front of the camera includes: Obtaining the current video frame captured by the camera; Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person; Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person; Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder; If so, it is determined that the person in the posture sequence is moving his elbow; If not present, it is determined that the person in the posture sequence is not moving his elbows.
2. The vertical advertising machine according to claim 1, characterized in that: The legal publicity video is used to publicize the consequences of damaging public facilities.
3. The vertical advertising machine according to claim 1, characterized in that: The vertical advertising machine also includes an alarm. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further used to control the alarm to sound an alarm.
4. The vertical advertising machine according to claim 3, characterized in that: The alarm is a sound alarm or a sound and light alarm.
5. The vertical advertising machine according to claim 1, characterized in that: The vertical advertising machine further includes a positioning module, which is connected to the processing module. If it is simultaneously detected that the vibration value is within a preset first range and that there is a person moving his elbow in front of the camera, the processing module is further configured to: Acquiring positioning data of the positioning module; The positioning data and the alarm information are sent to the background of the vertical advertising machine.
6. The vertical advertising machine according to claim 1, characterized in that: The vertical advertising machine further includes a speaker, which is connected to the processing module. After the video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the backstage of the vertical advertising machine, the processing module is further used to: Receiving voice information sent by the monitoring background of the vertical advertising machine; The voice information is played through the speaker.
7. The vertical advertising machine according to claim 1, characterized in that: The processing module is also used for: The surveillance video stored in the memory is deleted regularly.
8. The vertical advertising machine according to claim 1, characterized in that: If it is detected that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, after extracting facial features of the person moving his elbow, the processing module is further used to: If complete facial features are extracted, a facial image of the target person is collected; Performing denoising and image enhancement processing on the face image in sequence to obtain a processed face image; The processed face image, the video clip collected by the camera when the vibration value is within the first range, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
9. The vertical advertising machine according to claim 1, characterized in that: The alarm information also includes an image of the vertical advertising machine.
10. A data processing method for a vertical advertising machine, characterized in that: The vertical advertising machine is a vertical advertising machine according to any one of claims 1 to 9, and the vertical advertising machine comprises a camera, a vibration sensor and a memory, wherein the camera is arranged on the front of the vertical advertising machine, the vibration sensor is used to detect the vibration of the vertical advertising machine, and the memory is used to store data, including monitoring video data, and is characterized in that the camera is used to monitor the environment around the vertical advertising machine in real time, and the method comprises: Acquiring a vibration value detected by the vibration sensor; Determining the range of the vibration value; Detecting whether there is a person moving his elbow in front of the camera; If it is detected at the same time that the vibration value is within the preset first range and that there is a person moving his elbow in front of the camera, facial features of the person moving his elbow are extracted; If the complete facial features cannot be extracted, the person moving the elbow is taken as the target person, and the appearance features of the target person are identified; wherein the appearance features include: clothing features and body shape features; Searching historical surveillance video data to see if there is a person with similar appearance features; If so, extracting the video clip of the person with similar appearance features; The video clips collected by the camera when the vibration value is within the first range, the video clips of people with similar appearance characteristics, and the alarm information are sent to the background of the vertical advertising machine; wherein the alarm information includes a unique identifier representing the vertical advertising machine.
11. The data processing method of the vertical advertising machine according to claim 10, characterized in that: The key points of the human body include a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist and a right wrist, and the detection of whether there is a person moving his elbow in front of the camera includes Obtaining the current video frame captured by the camera; Extracting images of the same person from the current video frame in chronological order to obtain an image sequence of the same person; Extracting key features of a human body from each image in the image sequence to obtain a posture sequence of the same person; Determine whether there is a posture in the posture sequence whose elbow joint angle is within a set range, and the elbow joint angles of two adjacent postures are different; wherein the elbow joint angle is the angle between the line segment from the left wrist to the left elbow and the line segment from the left elbow to the left shoulder, or the angle between the line segment from the right wrist to the right elbow and the line segment from the right elbow to the right shoulder; If so, it is determined that the person in the posture sequence is moving his elbow; If not present, it is determined that the person in the posture sequence is not moving his elbows.
12. The data processing method of the vertical advertising machine according to claim 10, characterized in that: The memory is also used to store a legal publicity video, which is used to publicize the consequences of damaging public facilities. After the step of detecting whether there is a person moving his elbow in front of the camera, the method further includes: If it is detected at the same time that the vibration value is within the preset second range and that a person is moving his elbow in front of the camera, the display screen of the vertical advertising machine is controlled to be split-screen and divided into a first display area and a second display area; The legal publicity video is displayed in the first display area and the advertising content is displayed in the second display area; wherein the numerical value in the second range is smaller than the numerical value in the first range.
