CN113191293B - Advertisement detection method, device, electronic equipment, system and readable storage medium - Google Patents
Advertisement detection method, device, electronic equipment, system and readable storage medium Download PDFInfo
- Publication number
- CN113191293B CN113191293B CN202110510155.XA CN202110510155A CN113191293B CN 113191293 B CN113191293 B CN 113191293B CN 202110510155 A CN202110510155 A CN 202110510155A CN 113191293 B CN113191293 B CN 113191293B
- Authority
- CN
- China
- Prior art keywords
- target
- area
- image
- current image
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The application provides an advertisement detection method, an advertisement detection device, electronic equipment, an advertisement detection system and a readable storage medium, wherein the method comprises the following steps: acquiring a current image containing a target area; detecting whether a target object exists in a target area; the target object is a preset object which can cause interference to advertisement detection in the target area; when a target object exists in the target area, acquiring an object area of the target object in the target area, inputting a current image into a preset advertisement recognition model to obtain each suspected advertisement area on the current image, and removing an area overlapped with the object area from each suspected advertisement area to obtain a target advertisement area; or when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain the target advertisement area on the image to be recognized. The scheme improves the reliability of advertisement detection and reduces the risk of false alarm.
Description
Technical Field
The present application relates to the field of detection technologies, and in particular, to an advertisement detection method, apparatus, electronic device, system, and readable storage medium.
Background
With the advance of city construction, the pressure of city management is increasing. In many places where the pasting of the small messy advertisements is forbidden in the open statue, such as bus shelters, public columns and other areas, the small messy advertisements are often pasted, so that the reasonable use of the relevant areas is seriously interfered, and the urban image is influenced.
Currently, a common advertisement detection method is to recognize whether an advertisement exists in an area by using an advertisement recognition model by training a corresponding advertisement recognition model in advance. However, in the practical application process, various objects (such as people, vehicles, animals, etc.) usually appear in the area, and the objects entering the area may carry advertisements (such as advertisements on clothes of people, advertisements printed on vehicle bodies, etc.), so that the situation of misinformation often occurs, thereby causing an ineffective workload to related workers and affecting the working efficiency of the workers.
Disclosure of Invention
An object of the embodiments of the present application is to provide an advertisement detection method, an advertisement detection device, an electronic device, an advertisement detection system, and a readable storage medium, so as to improve advertisement detection reliability in an actual application process and reduce a false alarm risk.
The embodiment of the application provides an advertisement detection method, which comprises the following steps: acquiring a current image containing a target area; the target area is an area needing to be supervised; detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area; when the target object exists in the target area, acquiring an object area of the target object in the target area, inputting the current image into a preset advertisement recognition model to obtain each suspected advertisement area on the current image, and removing an area overlapped with the object area from each suspected advertisement area to obtain a target advertisement area; or when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
In the implementation process, the target advertisement area is obtained by obtaining the object area of the target object in the target area and filtering the suspected advertisement area output by the advertisement recognition model through the object area (namely, eliminating the area overlapped with the object area); or the region of the target object is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement region. The target advertisement area obtained in the way eliminates the influence of objects entering the target area and causing interference on advertisement detection, so that the finally obtained target advertisement area is more credible, the reliability of advertisement detection in the practical application process is improved, and the risk of misinformation is reduced.
Further, when the target object is detected to exist in the target area, the method further includes: comparing the pixel values of the positions in the target area in the current image with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image; if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
It should be understood that, in the practical application process, the advertisement recognition model can only detect the trained advertisements, and for the untrained advertisements or the advertisements with fewer training samples, the detection effect is not good, and the situations of false reports or missing reports are easy to occur. Therefore, in the implementation process, the pixel values of the positions in the target area in the current image are respectively compared with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image, so that the positions with the pixel difference value larger than the preset difference threshold value are used as the positions of suspected advertisements, and the positions are identified in the current image and reported, so that the detection and supplement of the advertisement recognition model are realized, the advertisement detection reliability is improved, and the risks of advertisement omission and false alarm are reduced.
Further, identifying a position where the pixel difference value is greater than a preset difference threshold value in the current image, and reporting the position to a preset auditing platform for auditing, wherein the position includes: identifying each target pixel position in the current image, and reporting each target pixel position to a preset auditing platform for auditing; wherein: the target pixel position is a position where a pixel difference value in the current image is larger than a preset difference threshold, and the target pixel position is located in the target area and outside the object area.
In the implementation process, the interference of the target object on the pixel comparison result is eliminated by identifying the target pixel position located in the target area and outside the target area, so that the advertisement detection reliability is further improved, and the risks of advertisement omission and false alarm are reduced.
Further, after the region where the target object is located is removed from the current image to obtain an image to be recognized, the method further includes: comparing the pixel values of the positions in the target area in the image to be identified with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image respectively; if the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the image to be recognized, the position of the pixel difference value larger than the preset difference threshold value is identified in the image to be recognized, and the image to be recognized is reported to a preset auditing platform for auditing.
In the implementation process, the pixel comparison is carried out on the basis of the image to be recognized in the region where the target object is removed, so that the detection and supplement of the advertisement recognition model are realized, and meanwhile, the interference of the target object on the pixel comparison result is eliminated, the advertisement detection reliability is improved, and the risks of advertisement omission and false alarm are reduced.
Further, the method further comprises: when it is detected that the target object does not exist in the target area of the current image but exists in the target area of the previous frame of image of the current image, comparing the pixels at the positions in the target area in the current image with the pixels at the corresponding positions in the target area in the reference image respectively; if the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
It should be appreciated that in an actual application process, advertisements may be posted by target objects (such as people). At this time, a possible person may shield the advertisement, and if the advertisement just belongs to an advertisement with an untrained advertisement recognition model, a missed detection situation may occur. In order to avoid the situation of subsequent missed detection caused by the shielding of the target object, in the implementation process, the image of the target object just leaving the target area is compared with the reference image in a mode of setting the reference image, so that the reliability of advertisement detection is improved.
Further, the method further comprises: when the target object exists in the target area of the current image and the target object does not exist in the target area of the previous frame of image of the current image, saving the previous frame of image; and the previous frame image is a reference image.
In the implementation process, one frame of image before the target object enters the target area is used as a reference image, so that the image of the target object just leaving the target area is compared with the image of the target object just before entering the target area, the change detection of the target area can be effectively realized when the target object is in the target area, and the reliability of advertisement detection is improved.
The embodiment of the application further provides an advertisement detection method, which comprises the following steps: acquiring a current image containing a target area; the target area is an area needing to be supervised; comparing the pixel values of the positions in the target area in the current image with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image; if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
In the practical application process, the advertisement recognition model can only realize the detection of the trained advertisements, and for the untrained advertisements or the advertisements with less training samples, the detection effect is not good, and the condition of missing report or false report is easy to occur. In the implementation process, the pixel values of the positions in the target area in the current image are compared with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image, so that the positions with the pixel difference value larger than the preset difference threshold value are used as the positions of suspected advertisements, and the suspected advertisements are identified in the current image and reported.
Further, the method further comprises: detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area; identifying the position of the pixel difference value larger than a preset difference threshold value in the current image, and reporting the position to a preset auditing platform for auditing, wherein the method comprises the following steps: when the target object exists in the target area, identifying each target pixel position in the current image, and reporting each target pixel position to a preset auditing platform for auditing; wherein: the target pixel position is a position where a pixel difference value in the current image is larger than a preset difference threshold, and the target pixel position is located in the target area and outside the object area where the target object is located.
Further, the method further comprises: detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area; comparing the pixel values at the positions in the target area in the current image with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image, respectively, including: when the target object exists in the target area, the area of the target object is removed from the current image; and comparing the pixel values of all positions in the target area in the current image after the area of the target object is removed with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image.
An embodiment of the present application further provides an advertisement detection device, including: the device comprises an acquisition module, a detection module and a processing module; the acquisition module is used for acquiring a current image containing a target area; the target area is an area needing to be supervised; the detection module is used for detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area; the processing module is configured to, when the target object exists in the target area, acquire an object area of the target object in the target area, input the current image to a preset advertisement recognition model to obtain suspected advertisement areas on the current image, and remove, from the suspected advertisement areas, an area overlapping with the object area to obtain a target advertisement area; or, when the target object exists in the target area, eliminating the area where the target object is located in the current image to obtain an image to be recognized, and inputting the image to be recognized to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
The embodiment of the present application further provides an advertisement detection device, including: the device comprises an acquisition unit, a comparison unit and a processing unit; the acquisition unit is used for acquiring a current image containing a target area; the target area is an area needing to be supervised; the comparison unit is configured to compare the pixel values at the positions in the target area in the current image with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image; and the processing unit is used for identifying the position of the pixel difference value larger than the preset difference threshold value in the current image if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, and reporting the position to a preset auditing platform for auditing.
The embodiment of the application also provides electronic equipment, which comprises a processor, a memory and a communication bus; the communication bus is used for realizing connection communication between the processor and the memory; the processor is configured to execute one or more programs stored in the memory to implement any of the above advertisement detection methods.
An embodiment of the present application further provides an advertisement detection system, including: a camera apparatus and an electronic apparatus as described above which are connected in communication; the camera shooting equipment is arranged outside the area needing to be supervised, is used for shooting images containing the area needing to be supervised, and sends the images to the electronic equipment; the electronic equipment is used for receiving the image sent by the camera equipment and realizing any one of the advertisement detection methods.
Also provided in embodiments of the present application is a readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement any of the above advertisement detection methods.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of an advertisement detection method according to an embodiment of the present application;
FIG. 2 is a diagram illustrating an example of screening out targeted advertisement areas from suspected advertisement areas according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart illustrating another advertisement detection method according to an embodiment of the present disclosure;
fig. 4 is a schematic view of a bus shelter provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of an advertisement detection device according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of another advertisement detection apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
The first embodiment is as follows:
in order to improve the reliability of advertisement detection in the practical application process and reduce the risk of false alarm, the embodiment provides an advertisement detection method. As shown in fig. 1, fig. 1 is a schematic flow chart of the advertisement detection method provided in this embodiment, and includes:
s101: a current image containing a target area is acquired.
It should be noted that the target area described in the embodiment of the present application is an area that needs to be supervised.
It should be understood that, in the embodiment of the present application, the image capturing apparatus may be disposed outside an area that needs to be supervised, and a captured image of the image capturing apparatus includes the area that needs to be supervised.
In the embodiment of the present application, an execution subject for executing the advertisement detection method provided in the embodiment of the present application is an electronic device with an image processing function, such as a host, a server, a single chip, and the like. The camera can be in communication connection with the camera device in a wired or wireless mode, so that the image transmitted by the camera device is received.
In the embodiment of the present application, the electronic device executing the advertisement detection method provided in the embodiment of the present application may be a device independent from the image capturing device, or may be a device such as a processing chip and a single chip integrated in the image capturing device.
It should be noted that, in the embodiment of the present application, in order to ensure the reliability of advertisement detection, regions other than the target region in the current image may be removed, and the image of the region other than the removed target region may be processed.
S102: whether a target object exists in the target area is detected.
In the embodiment of the present application, the target object refers to a preset object that may interfere with the detection of the advertisement in the target area. For example, the target object may include at least one of a person, a car, an animal, and the like.
In the embodiment of the present application, a correlation detection algorithm may be adopted to achieve detection of a target object. For example, assuming that the target object is a human, a deep learning based human detection model may be employed to achieve detection of the target object, but not by way of limitation.
S103: and carrying out advertisement detection according to the current image and the region of the target object in the target region.
In this embodiment of the present application, when a target object exists in a target area, step S103 may be implemented in at least the following two ways:
the first method is as follows: the object area of the target object in the target area can be obtained, and the current image is input into a preset advertisement recognition model to obtain each suspected advertisement area on the current image. Then, the areas overlapped with the object areas are removed from the suspected advertisement areas to obtain target advertisement areas.
For example, referring to fig. 2, assuming that the a area is an object area of the target object within the target area, and the areas 1 to 3 are suspected advertisement areas detected by the advertisement recognition model, since the area 2 is located within the a area, the areas 1 and 3 can be determined as the target advertisement areas.
The target advertisement area is an area determined to have an advertisement.
It should be further noted that, in the embodiment of the present application, the advertisement recognition model may be implemented by using various existing network models for object recognition, for example, may be implemented by using a deep learning model.
The object region is a region where the target object is located in the current image.
The second method comprises the following steps: the target area of the target object in the target area can be obtained, and then the target area is removed from the current image to obtain the image to be identified. And then inputting the image to be recognized into a preset advertisement recognition model, and obtaining a target advertisement area on the image to be recognized.
It should be understood that, the above two modes can both eliminate the influence of the target object entering the target area on the advertisement detection, thereby improving the reliability of the advertisement detection in the actual application process and reducing the false alarm risk.
It should be noted that, in the embodiment of the present application, if it is not detected that the target object exists in the target area, a possible implementation manner at this time is: the current image can be directly detected by adopting a preset advertisement recognition model, so that a target advertisement area is obtained.
In another possible implementation manner of the embodiment of the present application, if the target object is not detected in the target area, the advertisement detection may not be performed, and the advertisement detection may be performed only when the target object is detected in the target area, so as to reduce resource consumption of the electronic device.
It should be understood that, in the practical application process, the advertisement recognition model can only detect the trained advertisements, and for the untrained advertisements or the advertisements with fewer training samples, the detection effect is not good, and the situations of false reports or false reports are easy to occur.
Therefore, in a feasible implementation manner of the embodiment of the application, the advertisement recognition model can be supplemented with advertisement detection in a pixel comparison manner, so that the reliability of advertisement detection is further improved, and the risks of missed advertisement detection and false advertisement are reduced.
In the present possible implementation, at least the following two implementations can be adopted to implement:
mode A: the pixel values at the positions in the target area in the current image may be compared with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image. If the comparison result represents that a position where the pixel difference value is larger than the preset difference threshold exists in the target area in the current image, the position where the pixel difference value is larger than the preset difference threshold can be identified in the current image, and the position is reported to a preset auditing platform for auditing.
It should be understood that, theoretically, since the advertisement is pasted in the target area, the pixel value of the advertisement will be greatly changed from the pixel value of the corresponding position in the previous frame of image, and therefore, based on the comparison of the pixel values, the position where the pixel difference value is greater than the preset difference threshold value is identified, and the detection of the advertisement can be realized.
And because the reliability of the pixel comparison is slightly worse than that of the advertisement identification model, the positions of which the pixel difference values are larger than the preset difference threshold value are obtained through the pixel comparison and then can be reported to a preset auditing platform for auditing, and finally, the positions are determined to be illegal advertisements, so that the reliability of advertisement detection is improved.
It should be understood that, in order to avoid false alarm caused by the existence of the target object, in the above manner a, when the position identification is performed, where the pixel difference value is greater than the preset difference threshold, only the target pixel position, where the pixel difference value of each pixel in the target area in the current image and outside the target area where the target object is located is greater than the preset difference threshold, may be identified, so that only each target pixel position is reported to the preset auditing platform for auditing. Thus, false positives caused by the target object are eliminated.
Mode B: after the target object is detected, the area where the target object is located can be removed from the current image, and the image to be recognized is obtained. And then comparing the pixel values of all positions in the target area in the image to be identified with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image respectively. If the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the image to be recognized, the position of the pixel difference value larger than the preset difference threshold value can be identified in the image to be recognized, and the position is reported to a preset auditing platform for auditing.
It should be understood that, in the mode B, if a position where the pixel difference value is greater than the preset difference threshold value exists in the target area in the image to be recognized, the position may also be identified at a corresponding position in the current image of the area where the target object is not removed, so as to report the current image to the auditing platform.
In the method B, the previous frame image for performing the pixel value comparison may be an image from which the target object in the previous frame image is not removed, or an image from which the target object in the previous frame image is removed.
If the image from which the target object in the previous frame of image is removed is adopted, since the target object in the two images may have a position change, a certain position in the target area in the image to be recognized may not have a corresponding position in the previous frame of image, and optionally, such a position may not be marked.
It should be understood that the review platform may be set by an engineer in advance, and the review may be performed manually when performing the review, which is not limited in the embodiment of the present application.
It should be understood that, in practical applications, the above manner a and manner B may be adopted in any combination with the foregoing manner one and manner two, and are not limited in the embodiments of the present application.
It should be appreciated that in an actual application process, advertisements may be posted by target objects (such as people). At the moment, a possible person can shield the advertisement, and if the advertisement belongs to the advertisement which is not trained by the advertisement recognition model, the condition of missed detection can occur.
In order to avoid a situation that subsequent missed detection occurs due to occlusion of the target object, in a feasible implementation manner of the embodiment of the present application, when it is detected that the target object does not exist in the target area of the current image but the target object exists in the target area of the previous frame image of the current image, the pixels at the positions in the target area in the current image are respectively compared with the pixels at the corresponding positions in the target area in the reference image.
If the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
Optionally, in this embodiment of the application, the reference image may be a standard image that is shot in advance and has no illegal advertisement or target object in the target area.
In addition, in the embodiment of the present application, the reference image may also be the previous frame image in which the target object is initially detected to enter the target area. That is, when it is detected that a target object exists in the target area of the current image but the target object does not exist in the target area of the previous frame image of the current image, the previous frame image may be saved and used as the reference image.
It is to be understood that, at this time, different target objects may have different reference images.
For example, when it is detected that the target object a enters the target area and the target object a does not exist in the target area in the previous frame of image, the previous frame of image may be used as a reference image (denoted as image 1) of the target object a. Then, when it is detected that the target object a does not exist in the target area of the current image and the target object a exists in the target area of the previous frame of image of the current image (note that a new current image is continuously obtained due to the lapse of time, so that a new previous frame of image is continuously generated, and therefore the previous frame of image at this time is not the image 1), the pixel value of the current image and the pixel value of the image 1 may be compared, so that a position where the pixel difference value is greater than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
It should be noted that, in the embodiment of the present application, the difference threshold may be set by an engineer according to actual needs.
According to the advertisement detection method provided by the embodiment of the application, the target advertisement area is obtained by obtaining the object area of the target object in the target area and filtering the suspected advertisement area output by the advertisement identification model through the object area (namely, eliminating the area overlapped with the object area); or the region of the target object is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement region. The target advertisement area obtained in the way eliminates the influence of objects entering the target area and causing interference on advertisement detection, so that the finally obtained target advertisement area is more credible, the reliability of advertisement detection in the practical application process is improved, and the risk of misinformation is reduced.
In addition, the advertisement detection method provided by the embodiment of the application can also take the position with the pixel difference value larger than the preset difference threshold value as the position of the suspected advertisement in a pixel comparison mode, and the position is identified in the current image for reporting, so that the detection and supplement of the advertisement identification model are realized, the reliability of advertisement detection is improved, and the risks of missed detection and false alarm of the advertisement are reduced.
The second embodiment:
in order to improve the reliability of advertisement detection in the practical application process and reduce the risk of false alarm, the embodiment also provides an advertisement detection method. As shown in fig. 3, fig. 3 is a schematic flow chart of the advertisement detection method provided in this embodiment, and includes:
s301: a current image containing a target area is acquired.
Referring to the description of the first embodiment, the target area in the embodiment of the present application is an area that needs to be monitored, and the following explanations of related terms may refer to the same description of the first embodiment, which is not repeated herein.
S302: and comparing the pixel values of the positions in the target area in the current image with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image.
It should be understood that in the embodiment of the present application, the electronic device may continuously acquire the latest current image, so as to continuously generate a new previous frame image.
S303: if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
It should be understood that, in an actual application process, if a target object exists in a target area, due to the existence of the target object, that is, the area where the target object is located, a pixel difference value may be larger than a preset difference threshold value, so that the target object is erroneously identified as an area suspected of being an advertisement, and then the area is reported to a preset auditing platform for auditing.
In order to prevent false alarm caused by the target object, in a possible implementation manner of this embodiment, it may be further detected whether the target object exists in the target area. Then, when step S303 is executed, only the target pixel positions where the pixel difference values of the target pixels located in the target area and the target pixels located outside the target area in the current image are greater than the preset difference threshold may be identified, so that only the target pixel positions are reported to a preset auditing platform for auditing.
In another possible implementation manner of this embodiment, similarly, whether the target object exists in the target area may be detected first. Then, when step S302 is executed, if there is a target object in the target area, the area where the target object is located is removed from the current image, and then the pixel values at the positions in the target area in the current image after the area where the target object is located is removed are respectively compared with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image.
It should be understood that, in another possible implementation manner, the previous frame image used for performing the pixel value comparison may be an image from which the target object in the previous frame image is not removed, or an image from which the target object in the previous frame image is removed.
If the image from which the target object in the previous frame of image is removed is adopted, since the target object in the two images may have a position change, a certain position in the target area in the current image from which the target object is removed may not exist in the previous frame of image, and optionally, such a position may not be marked.
In this embodiment, similar to the embodiment, in order to avoid a situation of subsequent missed detection due to occlusion of the target object, in a feasible implementation manner of the embodiment of the present application, when it is detected that the target object does not exist in the target area of the current image but the target object exists in the target area of the previous frame image of the current image, the pixels at the positions in the target area in the current image may be respectively compared with the pixels at the corresponding positions in the target area in the reference image.
If the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
Optionally, in the embodiment of the present application, the reference image may be a standard image that is shot in advance and has no illegal advertisement or target object in the target area.
In addition, in the embodiment of the present application, the reference image may also be the previous frame image in which the target object is initially detected to enter the target area. That is, when it is detected that a target object exists in the target area of the current image but the target object does not exist in the target area of the previous frame image of the current image, the previous frame image may be saved and used as the reference image.
In addition, in the embodiment, advertisement identification can be performed by combining with an advertisement identification model.
That is, in an alternative implementation, after a current image including the target area is obtained, the current image may be further input into the advertisement recognition model.
In this case, each suspected advertisement area output by the advertisement recognition model may be directly set as a target advertisement area.
However, in order to reduce false positives due to the target objects and improve the reliability of advertisement detection, in the above alternative implementation, it is also possible to detect whether a target object exists in the target area, and further, to remove an area overlapping with the target area of the target object from each suspected advertisement area output by the advertisement recognition model, thereby obtaining a target advertisement area.
In another optional implementation manner, whether a target object exists in the target area or not can be detected, and then when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and then the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
In the advertisement detection method provided by this embodiment, the pixel values at the positions in the target area in the current image are respectively compared with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image, so that the positions with the pixel difference values larger than the preset difference threshold are used as the positions of suspected advertisements, and the suspected advertisements are identified in the current image and reported.
Example three:
the embodiment takes a bus shelter scene as an example on the basis of the first embodiment and the second embodiment, and further illustrates the present application.
The target object is set as a person, and the target area is an advertisement column of a bus shelter.
Referring to fig. 4, the camera device is arranged at the top of the bus shelter, faces to the advertisement column, and monitors the advertisement column.
And step 0, the electronic equipment continuously acquires video frame images from the camera equipment.
Step 1, detecting the newly acquired image by using a human body detection model based on deep learning.
It should be understood that human body detection may also be implemented by a human body segmentation detection manner, and the region where the human is located is obtained, which is not limited in the embodiment of the present application.
And 2, if the person is detected in the image, entering the next step. If no person is detected, the processing of the image of the current frame is finished, and the image of the next frame is acquired again.
And 3, eliminating the areas outside the advertisement columns in the images and the areas where people are located.
And 4, detecting whether a target area suspected of illegal advertisements exists in the picture processed in the step 3 based on the deep learning detection model, and alarming aiming at the target area.
And 5, comparing the pixel values of the positions in the picture processed in the step 3 with the pixel values of the corresponding positions in the previous frame of image, identifying the positions with the pixel difference values larger than the preset difference threshold value in the picture processed in the step 3, and reporting the positions to a preset auditing platform for auditing.
And (5) after receiving the alarm in the step (4), the relevant personnel can perform treatment. After receiving the location identified in step 5, the user can manually check whether the relevant location is an illegal advertisement, thereby performing further actions.
By the scheme, the behavior of the illegally-pasted advertisement can be timely and effectively discovered, so that the behavior can be timely and effectively struck, and the working difficulty of urban environment supervision personnel and the workload of cleaning the illegal advertisement by sanitation workers are effectively reduced.
Example four:
based on the same inventive concept, the embodiment of the present application further provides an advertisement detection apparatus 100 and an advertisement detection apparatus 200. Referring to fig. 5 and 6, fig. 5 illustrates an advertisement detection apparatus using the method shown in fig. 1, and fig. 6 illustrates an advertisement detection apparatus using the method shown in fig. 3. It should be understood that the specific functions of the apparatus 100 and the apparatus 200 can be referred to the above description, and the detailed description is omitted here as appropriate to avoid redundancy. The apparatus 100 and the apparatus 200 include at least one software functional module or unit that can be stored in a memory in the form of software or firmware or solidified in an operating system of the apparatus 100 and the apparatus 200. Specifically, the method comprises the following steps:
referring to fig. 5, the apparatus 100 includes: the device comprises an acquisition module 101, a detection module 102 and a processing module 103. Wherein:
the acquiring module 101 is configured to acquire a current image including a target area; the target area is an area needing to be supervised;
the detecting module 102 is configured to detect whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area;
the processing module 103 is configured to, when the target object exists in the target area, obtain an object area of the target object in the target area, input the current image to a preset advertisement recognition model to obtain suspected advertisement areas on the current image, and remove, from the suspected advertisement areas, an area overlapping with the object area to obtain a target advertisement area; or, when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
In a feasible implementation manner of the embodiment of the present application, when it is detected that the target object exists in the target area, the processing module 103 is further configured to compare pixel values at positions in the target area in the current image with pixel values at corresponding positions in the target area in a previous frame of image of the current image, respectively, identify, in the current image, a position where a pixel difference value is greater than a preset difference threshold value if a comparison result represents that a position where a pixel difference value is greater than the preset difference threshold value exists in the target area in the current image, and report the position to a preset auditing platform for auditing.
In the feasible embodiment, the processing module 103 is specifically configured to identify each target pixel position in the current image, and report each target pixel position to a preset auditing platform for auditing; wherein: the target pixel position is a position where a pixel difference value in the current image is larger than a preset difference threshold, and the target pixel position is located in the target area and outside the object area.
In this embodiment of the application, after the region where the target object is located is removed from the current image to obtain an image to be recognized, the processing module 103 is further configured to compare pixel values at positions in the target region in the image to be recognized with pixel values at corresponding positions in the target region in a previous frame of image of the current image, respectively, identify, in the image to be recognized, a position where the pixel difference value is greater than a preset difference threshold value if a position where the pixel difference value is greater than the preset difference threshold value exists in the target region in the image to be recognized, and report the position to a preset auditing platform for auditing.
In a possible implementation manner of the embodiment of the present application, the processing module 103 is further configured to:
when it is detected that the target object does not exist in the target area of the current image but exists in the target area of the previous frame of image of the current image, comparing the pixels at the positions in the target area in the current image with the pixels at the corresponding positions in the target area in the reference image respectively;
if the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
In the possible embodiment, the processing module 103 is further configured to: when the target object exists in the target area of the current image and the target object does not exist in the target area of the previous frame of image of the current image, saving the previous frame of image; and the previous frame image is a reference image.
Referring to fig. 6, the apparatus 200 includes: an acquisition unit 201, a comparison unit 202 and a processing unit 203. Wherein:
the acquiring unit 201 is configured to acquire a current image including a target area; the target area is an area needing to be supervised;
the comparing unit 202 is configured to compare the pixel value at each position in the target area in the current image with the pixel value at the corresponding position in the target area in the previous frame of image of the current image;
the processing unit 203 is configured to identify, if the comparison result represents that a position where the pixel difference value is greater than a preset difference threshold exists in the target region in the current image, the position where the pixel difference value is greater than the preset difference threshold is identified in the current image, and report the position to a preset auditing platform for auditing.
In a possible implementation manner of the embodiment of the present application, the processing unit 203 is further configured to detect whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area.
At this time, the identifying, by the processing unit 203, a position where the pixel difference value is greater than a preset difference threshold in the current image, and reporting the position to a preset auditing platform for auditing may include: when the target object exists in the target area, identifying each target pixel position in the current image, and reporting each target pixel position to a preset auditing platform for auditing; wherein: the target pixel position is a position where a pixel difference value in the current image is larger than a preset difference threshold, and the target pixel position is located in the target area and outside the object area where the target object is located.
In another possible implementation manner of the embodiment of the present application, the processing unit 203 is further configured to detect whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area; the comparing unit 202 is specifically configured to, when the target object exists in the target region, remove a region where the target object exists from the current image; and comparing the pixel values of all positions in the target area in the current image after the area where the target object is located is removed with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image.
It should be understood that, for the sake of brevity, the contents described in some embodiments are not repeated in this embodiment.
Example five:
the present embodiment provides an electronic device, which is shown in fig. 7 and includes a processor 701, a memory 702, and a communication bus 703. Wherein:
the communication bus 703 is used to enable communications between the processor 701 and the memory 702.
The processor 701 is configured to execute one or more first programs stored in the memory 702 to implement the advertisement detection method in the first embodiment and/or the second embodiment.
It will be appreciated that the configuration shown in fig. 7 is merely illustrative and that the electronic device may include more or fewer components than shown in fig. 7 or have a different configuration than shown in fig. 7. For example, it also has components such as a wireless communication module.
The present embodiment provides an advertisement detection system including a communication-connected image pickup apparatus and an electronic apparatus as shown in fig. 7.
The camera device can be a high-definition camera and can have a wireless communication function, so that a shot image is sent to the electronic device.
In addition, the image pickup apparatus should be disposed outside the area that needs to be supervised, so as to capture an image including the area that needs to be supervised.
The electronic device may implement the advertisement detection method provided in the embodiment of the present application as described above.
The present embodiment further provides a readable storage medium, such as a floppy disk, an optical disk, a hard disk, a flash Memory, a usb (Secure Digital Card), an MMC (Multimedia Card), etc., in which one or more programs for implementing the above steps are stored, and the one or more programs can be executed by one or more processors to implement the advertisement detection method in the first embodiment and/or the second embodiment. And will not be described in detail herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
In this context, a plurality means two or more.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. An advertisement detection method, comprising:
acquiring a current image containing a target area; the target area is an area needing to be supervised;
detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area;
when the target object exists in the target area, acquiring an object area of the target object in the target area, inputting the current image into a preset advertisement recognition model to obtain each suspected advertisement area on the current image, and removing an area overlapped with the object area from each suspected advertisement area to obtain a target advertisement area;
or when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
2. The advertisement detection method of claim 1, wherein upon detecting the presence of the target object within the target area, the method further comprises:
comparing the pixel values of the positions in the target area in the current image with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image;
if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
3. The method of claim 2, wherein identifying the position in the current image where the pixel difference is greater than a preset difference threshold and reporting the position to a preset auditing platform for auditing comprises:
identifying each target pixel position in the current image, and reporting each target pixel position to a preset auditing platform for auditing; wherein:
the target pixel position is a position where a pixel difference value in the current image is larger than a preset difference threshold, and the target pixel position is located in the target area and outside the object area.
4. The advertisement detection method of claim 1, wherein after the region where the target object is located is removed from the current image to obtain an image to be recognized, the method further comprises:
comparing the pixel values of the positions in the target area in the image to be identified with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image respectively;
if the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the image to be recognized, the position of the pixel difference value larger than the preset difference threshold value is identified in the image to be recognized, and the image to be recognized is reported to a preset auditing platform for auditing.
5. The advertisement detection method of any of claims 1-4, wherein the method further comprises:
when it is detected that the target object does not exist in the target area of the current image but exists in the target area of the previous frame of image of the current image, comparing the pixels at the positions in the target area in the current image with the pixels at the corresponding positions in the target area in a reference image respectively;
if the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
6. The advertisement detection method of claim 5, wherein the method further comprises:
when the target object is detected to exist in the target area of the current image but the target object does not exist in the target area of the previous frame of image of the current image, saving the previous frame of image; the previous frame image is a reference image.
7. An advertisement detection method, comprising:
acquiring a current image containing a target area; the target area is an area needing to be supervised;
comparing the pixel values of the positions in the target area in the current image with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image;
if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, the position of the pixel difference value larger than the preset difference threshold value is identified in the current image, and the position is reported to a preset auditing platform for auditing.
8. The advertisement detection method of claim 7, wherein the method further comprises:
detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area;
identifying the position of the current image where the pixel difference value is greater than a preset difference threshold value, and reporting the position to a preset auditing platform for auditing, wherein the method comprises the following steps:
when the target object exists in the target area, identifying each target pixel position in the current image, and reporting each target pixel position to a preset auditing platform for auditing; wherein:
the target pixel position is a position where a pixel difference value in a current image is larger than a preset difference threshold value, and the target pixel position is located in the target area and outside an object area where the target object is located.
9. The advertisement detection method of claim 7, further comprising: detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area;
comparing the pixel values at the positions in the target area in the current image with the pixel values at the corresponding positions in the target area in the previous frame of image of the current image, respectively, including:
when the target object exists in the target area, the area of the target object is removed from the current image;
and comparing the pixel values of all positions in the target area in the current image after the area where the target object is located is removed with the pixel values of the corresponding positions in the target area in the previous frame of image of the current image.
10. An advertisement detection device, comprising: the device comprises an acquisition module, a detection module and a processing module;
the acquisition module is used for acquiring a current image containing a target area; the target area is an area needing to be supervised;
the detection module is used for detecting whether a target object exists in the target area; the target object is a preset object which can interfere with the advertisement detection in the target area;
the processing module is configured to, when the target object exists in the target area, acquire an object area of the target object in the target area, input the current image to a preset advertisement recognition model to obtain suspected advertisement areas on the current image, and remove, from the suspected advertisement areas, an area overlapping with the object area to obtain a target advertisement area; or, when the target object exists in the target area, the area where the target object is located is removed from the current image to obtain an image to be recognized, and the image to be recognized is input to a preset advertisement recognition model to obtain a target advertisement area on the image to be recognized.
11. An advertisement detection device, comprising: the device comprises an acquisition unit, a comparison unit and a processing unit;
the acquisition unit is used for acquiring a current image containing a target area; the target area is an area needing to be supervised;
the comparison unit is configured to compare pixel values at positions in the target region in the current image with pixel values at corresponding positions in the target region in a previous frame of image of the current image;
and the processing unit is used for identifying the position of the pixel difference value larger than the preset difference threshold value in the current image if the comparison result represents that the position of the pixel difference value larger than the preset difference threshold value exists in the target area in the current image, and reporting the position to a preset auditing platform for auditing.
12. An electronic device, comprising: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute one or more programs stored in the memory to implement the commercial detection method of any one of claims 1 to 9.
13. An advertisement detection system, comprising: a communicatively connected camera device and an electronic device as claimed in claim 12;
the camera shooting equipment is arranged outside the area needing to be supervised, is used for shooting images containing the area needing to be supervised, and sends the images to the electronic equipment;
the electronic equipment is used for receiving the image sent by the camera equipment and realizing the advertisement detection method according to any one of claims 1 to 9.
14. A readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the advertisement detection method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510155.XA CN113191293B (en) | 2021-05-11 | 2021-05-11 | Advertisement detection method, device, electronic equipment, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510155.XA CN113191293B (en) | 2021-05-11 | 2021-05-11 | Advertisement detection method, device, electronic equipment, system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191293A CN113191293A (en) | 2021-07-30 |
| CN113191293B true CN113191293B (en) | 2023-04-07 |
Family
ID=76981040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110510155.XA Active CN113191293B (en) | 2021-05-11 | 2021-05-11 | Advertisement detection method, device, electronic equipment, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191293B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113870226B (en) * | 2021-09-29 | 2024-03-22 | 南京领行科技股份有限公司 | Compliance detection method and device for additional object, electronic equipment and storage medium |
| CN114758216B (en) * | 2022-05-05 | 2023-01-13 | 北京容联易通信息技术有限公司 | Illegal advertisement detection method and system based on machine vision |
| CN115240389A (en) * | 2022-08-03 | 2022-10-25 | 江苏商贸职业学院 | Monitoring and early warning system based on artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106899864A (en) * | 2015-12-18 | 2017-06-27 | 北京国双科技有限公司 | Commercial detection method and device |
| CN111639333A (en) * | 2020-05-28 | 2020-09-08 | 维沃移动通信有限公司 | Information management method and device and electronic equipment |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8098485B2 (en) * | 2007-07-03 | 2012-01-17 | 3M Innovative Properties Company | Wireless network sensors for detecting events occurring proximate the sensors |
| CN109598527A (en) * | 2017-09-30 | 2019-04-09 | 北京国双科技有限公司 | Analysis of advertising results method and device |
| JP2021511729A (en) * | 2018-01-18 | 2021-05-06 | ガムガム インコーポレイテッドＧｕｍｇｕｍ， Ｉｎｃ． | Extension of the detected area in the image or video data |
| CN110532833A (en) * | 2018-05-23 | 2019-12-03 | 北京国双科技有限公司 | A kind of video analysis method and device |
| CN110751678A (en) * | 2018-12-12 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Moving object detection method and device and electronic equipment |
| CN111368106B (en) * | 2018-12-26 | 2024-04-26 | 中兴通讯股份有限公司 | Method and device for processing wild advertisement and computer readable storage medium |
| CN110517095A (en) * | 2019-08-30 | 2019-11-29 | 北京三快在线科技有限公司 | A kind of method and device for launching advertisement |
| CN111027560B (en) * | 2019-11-07 | 2023-09-29 | 浙江大华技术股份有限公司 | Text detection method and related device |
| CN110889377A (en) * | 2019-11-28 | 2020-03-17 | 深圳市丰巢科技有限公司 | Method and device for identifying abnormality of advertising object, server device and storage medium |
| CN111178410A (en) * | 2019-12-19 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Illegal picture identification method and device |
| CN111754267B (en) * | 2020-06-29 | 2021-04-20 | 浙江德塔森特数据技术有限公司 | Data processing method and system based on block chain |
| CN111931862B (en) * | 2020-09-11 | 2021-07-23 | 杭州追猎科技有限公司 | Method and system for detecting illegal posted advertisements and electronic equipment |
| CN112613364A (en) * | 2020-12-10 | 2021-04-06 | 新华网股份有限公司 | Target object determination method, target object determination system, storage medium, and electronic device |
-
2021
- 2021-05-11 CN CN202110510155.XA patent/CN113191293B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106899864A (en) * | 2015-12-18 | 2017-06-27 | 北京国双科技有限公司 | Commercial detection method and device |
| CN111639333A (en) * | 2020-05-28 | 2020-09-08 | 维沃移动通信有限公司 | Information management method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191293A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113191293B (en) | Advertisement detection method, device, electronic equipment, system and readable storage medium | |
| US10212397B2 (en) | Abandoned object detection apparatus and method and system | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| CN108288025A (en) | A kind of car video monitoring method, device and equipment | |
| CN105608209B (en) | Video annotation method and video annotation device | |
| CN108230669B (en) | Road vehicle violation detection method and system based on big data and cloud analysis | |
| CN105976570A (en) | Driver smoking behavior real-time monitoring method based on vehicle video monitoring | |
| CN111079621A (en) | Method and device for detecting object, electronic equipment and storage medium | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN110913209A (en) | Camera shielding detection method and device, electronic equipment and monitoring system | |
| CN115412705A (en) | Real-time video monitoring method and system with vehicle information privacy protection function | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| WO2023124385A1 (en) | Photographic apparatus shielding detection method and apparatus, and electronic device, storage medium and computer program product | |
| CN113947795B (en) | Mask wearing detection method, device, equipment and storage medium | |
| CN114973135A (en) | Head-shoulder-based sequential video sleep post identification method and system and electronic equipment | |
| CN113743248A (en) | Identity information extraction method, device, electronic device and storage medium | |
| CN112597924A (en) | Electric bicycle track tracking method, camera device and server | |
| CN110581979B (en) | Image acquisition system, method and device | |
| CN113420631A (en) | Safety alarm method and device based on image recognition | |
| CN113038261A (en) | Video generation method, device, equipment, system and storage medium | |
| CN112419638A (en) | Method and device for acquiring alarm video | |
| CN112418234A (en) | Method and device for identifying license plate number, electronic equipment and storage medium | |
| CN112101134A (en) | Object detection method and device, electronic device and storage medium | |
| CN112270257A (en) | Motion trajectory determination method and device and computer readable storage medium | |
| CN115631477B (en) | Target identification method and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |