Intelligent security and protection monitoring method and system for intelligent building based on Internet of Things

Abstract

The invention relates to the technical field of image processing, and particularly discloses an intelligent security and protection monitoring method and system for an intelligent building based on the Internet of Things, and the method comprises the following steps: S1, carrying out the framing processing of a monitoring video, obtaining a monitoring video frame sequence, and determining a target region in the monitoring video; s2, determining a playing window of the target video on the reference plane, and marking a target area in the playing window; moving the reference line along the target direction, and recording the area proportion every preset duration; correcting the area proportion according to the proportion of the target area in the playing window to obtain a correction proportion, obtaining a target sequence based on the correction proportion, and determining a comparison value; s3, determining a screening sequence according to the comparison value, and counting a comparison number; and determining an adjustment window based on the comparison number, and preprocessing the target area in the adjustment window. According to the invention, the resolution of the overlapping region is reduced, the video data volume is reduced, and the normal operation of the monitoring system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an intelligent security monitoring method and system for a smart building based on the Internet of Things. Background Art

[0002] The Internet of Things originated in the field of media and is the third revolution in the information technology industry. It refers to connecting any object to the network through information sensing equipment according to agreed protocols. Objects exchange and communicate information through information dissemination media to achieve intelligent identification, positioning, tracking, supervision and other functions.

[0003] The monitoring inside the building mainly obtains video data in real time through the monitoring equipment installed in the building, and transmits the video stream to the centrally managed monitoring center through the network. After receiving the video, the staff of the monitoring center conducts real-time viewing and analysis to ensure the safety of the monitored area and promptly detect and handle abnormal situations.

[0004] However, there are usually a large number of monitoring devices inside a building, involving monitoring of multiple areas, and the amount of high-definition video data transmitted is huge, which will take up a lot of storage space and bandwidth resources, resulting in the amount of data that the system needs to process far exceeding the carrying capacity of ordinary computers; in addition, when storing high-definition video data, the storage burden will also be heavy, which will affect the overall operating efficiency of the monitoring system and may even cause problems such as system crashes. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent security monitoring method and system for smart buildings based on the Internet of Things to solve the following technical problems:

[0006] There are usually a large number of monitoring devices inside a building, involving monitoring of multiple areas. The amount of high-definition video data transmitted is huge, which will take up a lot of storage space and bandwidth resources, resulting in the amount of data that the system needs to process far exceeding the carrying capacity of ordinary computers; in addition, when storing high-definition video data, the storage burden will also be heavy, which will affect the overall operating efficiency of the monitoring system and may even cause problems such as system crashes.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent security monitoring method for a smart building based on the Internet of Things comprises the following steps:

[0009] S1: Obtain a surveillance video collected by a surveillance device inside a building, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, obtain an overlapping area in the surveillance videos collected by two surveillance devices based on the surveillance video frame sequence, and use the overlapping area as a target area;

[0010] S2: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window;

[0011] Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area;

[0012] Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1;

[0013] S3: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ;

[0014] An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

[0015] As a further solution of the present invention: in the step S1, the process of detecting the overlapping area in the monitoring video collected by the monitoring device specifically includes:

[0016] For any two surveillance video frames with the same timestamp, extract feature points in the surveillance video frames, match the feature points, calculate a homography matrix based on the matched feature points, and project the surveillance video frame to another surveillance video frame based on the homography matrix;

[0017] The projected surveillance video frame and the original surveillance video frame are weightedly superimposed to determine the overlapping area of ​​the two surveillance video frames, which is used as the initial overlapping area, and the union of the initial overlapping areas is determined, which is used as the overlapping area in the surveillance videos collected by the two surveillance devices.

[0018] As a further solution of the present invention: in step S2, the process of determining the comparison value specifically includes:

[0019] When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=1;

[0020] When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=-1;

[0021] When the correction ratio of the ath position in A in the target ranking is equal to the correction ratio of the ath position in A in the target ranking, the comparison value Xa=0.

[0022] As a further solution of the present invention: in the step S3, the process of reducing the definition of the target area in the adjustment window specifically includes:

[0023] When the comparison number C+ appears first 1 = Cys, the playback window corresponding to the target sorting A is used as the adjustment window, and Cys represents the preset comparison number threshold; when the comparison number C- 1 =Cys, the play window corresponding to the target sorting B is used as the adjustment window;

[0024] The resolution of the target area in the adjustment window is reduced so that the clarity of the target area in the adjustment window reaches a preset clarity.

[0025] As a further solution of the present invention: in the step S3, when the proportion of comparison values ​​of 0 in the screening sorting is greater than 0.4, the playback window in which the proportion of the target area to the playback window is larger is marked as an adjustment window.

[0026] As a further solution of the present invention: in the step S1, when the monitoring device collects the monitoring video, the posture of the monitoring device is kept unchanged.

[0027] As a further solution of the present invention: in the step S1, when the target area does not exist, an early warning message is sent for prompting.

[0028] An intelligent security monitoring system for a smart building based on the Internet of Things, comprising:

[0029] Area determination module: obtains the surveillance video collected by the monitoring equipment inside the building, performs frame processing on the surveillance video to obtain a surveillance video frame sequence, obtains the overlapping area in the surveillance videos collected by the two monitoring devices based on the surveillance video frame sequence, and uses it as the target area;

[0030] Analysis module: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window;

[0031] Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area;

[0032] Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1;

[0033] Adjustment module: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​of 1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ;

[0034] An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

[0035] Beneficial effects of the present invention: In this scheme, first, the video is decomposed into a frame sequence, and the overlapping area is extracted. The overlapping area only needs to maintain a high resolution in one playback window. By reducing the resolution of the overlapping area in the remaining playback windows, the overall video data volume is reduced; then, the change of the target area in the positive area and the negative area when the reference line moves is determined, and the resolution of the target area in which the playback window is reduced is determined by this. It is worth noting that the larger the area ratio, the higher the proportion of the target area in the positive area, which further indicates that the distance from the staff is farther and more difficult to view. Therefore, the resolution of the target area in the corresponding playback window is selected to be reduced. Similarly, the larger the proportion of the target area in the playback window, when the resolution is reduced, more monitoring videos can be reduced in resolution, further reducing the overall video data volume, and the space required for subsequent monitoring video storage is smaller; finally, by reducing the resolution of the target area in the adjustment window, the bandwidth and storage burden are reduced; it is worth noting that if the monitoring video screen of a monitoring device overlaps with multiple monitoring devices at the same time, the above steps are repeated to reduce the resolution. The present invention reduces the video data volume by reducing the resolution of the overlapping area to ensure the normal operation of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present invention will be further described below in conjunction with the accompanying drawings.

[0037] Figure 1 The present invention is a flow chart of an intelligent security monitoring method for a smart building based on the Internet of Things. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, the present invention is an intelligent security monitoring method for smart buildings based on the Internet of Things, comprising the following steps:

[0040] S1: Obtain a surveillance video collected by a surveillance device inside a building, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, obtain an overlapping area in the surveillance videos collected by two surveillance devices based on the surveillance video frame sequence, and use the overlapping area as a target area;

[0041] S2: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window;

[0042] Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area;

[0043] Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1;

[0044] S3: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ;

[0045] An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

[0046] It should be noted that, first, the video is decomposed into a frame sequence, and the overlapping area is extracted. The overlapping area only needs to maintain a high resolution in one playback window. By reducing the resolution of the overlapping area in the remaining playback windows, the overall video data volume is reduced; then, the change of the target area in the positive area and the negative area when the reference line moves is determined, and the resolution of the target area in which the playback window is reduced is determined. It is worth noting that the larger the area ratio, the higher the proportion of the target area in the positive area, which means that it is farther away from the staff and more difficult to view. Therefore, it is selected to reduce the resolution of the target area in the corresponding playback window. Similarly, the larger the proportion of the target area in the playback window, when the resolution is reduced, more surveillance videos can be reduced in resolution, further reducing the overall video data volume, and less space is required for subsequent surveillance video storage; finally, by reducing the resolution of the target area in the adjustment window, the bandwidth and storage burden are reduced; it is worth noting that if the surveillance video screen of a monitoring device has overlapping areas with multiple monitoring devices at the same time, the above steps are repeated to reduce the resolution.

[0047] In another preferred embodiment of the present invention, in step S1, the process of detecting the overlapping area in the monitoring video collected by the monitoring device specifically includes:

[0048] For any two surveillance video frames with the same timestamp, extract feature points in the surveillance video frames, match the feature points, calculate a homography matrix based on the matched feature points, and project the surveillance video frame to another surveillance video frame based on the homography matrix;

[0049] The projected surveillance video frame and the original surveillance video frame are weightedly superimposed to determine the overlapping area of ​​the two surveillance video frames, which is used as the initial overlapping area, and the union of the initial overlapping areas is determined, which is used as the overlapping area in the surveillance videos collected by the two surveillance devices.

[0050] It is worth noting that feature points are usually uniquely identifiable and significant points in an image, such as corner points, edges, etc. After extracting these feature points, image processing algorithms (such as SIFT, SURF, ORB, etc.) are used to match these feature points. The purpose of feature point matching is to find the same or corresponding areas in two video frames, so as to establish a corresponding relationship under different perspectives. The matched feature points are used to calculate the homography matrix. The homography matrix is ​​a matrix that describes the projection relationship between two planes. It can map points in one video frame to corresponding points in another video frame. Through the homography matrix, a video frame can be geometrically transformed and projected to the perspective of another video frame, so as to realize the spatial transformation relationship between video frames through the matched feature points. Weighted superposition can improve the accuracy of the overlapping area. The overlapping area is the common part of the surveillance video collected by the two monitoring devices, which represents the same scene area observed between the two perspectives. Further, the union of the initial overlapping areas is determined. The purpose of the union operation is to merge all valid parts in the overlapping area of ​​the two video frames to form a larger overlapping area, which represents the area that can be observed from the perspective of both devices.

[0051] In another preferred embodiment of the present invention, in step S2, the process of determining the comparison value specifically includes:

[0052] When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=1;

[0053] When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=-1;

[0054] When the correction ratio of the ath position in A in the target ranking is equal to the correction ratio of the ath position in A in the target ranking, the comparison value Xa=0.

[0055] In another preferred embodiment of the present invention, in step S3, the process of reducing the definition of the target area in the adjustment window specifically includes:

[0056] When the comparison number C+ appears first 1 = Cys, the playback window corresponding to the target sorting A is used as the adjustment window, and Cys represents the preset comparison number threshold; when the comparison number C- 1 =Cys, the play window corresponding to the target sorting B is used as the adjustment window;

[0057] The resolution of the target area in the adjustment window is reduced so that the clarity of the target area in the adjustment window reaches a preset clarity.

[0058] In another preferred embodiment of the present invention, in step S3, when the proportion of comparison values ​​​​in the screening and sorting is greater than 0.4, the playback window with a larger proportion of the target area in the playback window is marked as an adjustment window.

[0059] It should be noted that when the comparison value is 0, the window in which the target area occupies a larger proportion of the playback window will be marked as an adjustment window. Generally, a larger proportion means that the target area occupies a larger area in the playback window, which means that the area consumes more resources and requires more bandwidth for the monitoring system. Therefore, reducing the resolution of the target area in this playback window can better reduce the amount of video data.

[0060] In another preferred embodiment of the present invention, in the step S1, when the monitoring device collects the monitoring video, the posture of the monitoring device is kept unchanged.

[0061] In another preferred embodiment of the present invention, in the step S1, when the target area does not exist, an early warning message is sent for prompting.

[0062] An intelligent security monitoring system for a smart building based on the Internet of Things, comprising:

[0063] Area determination module: obtains the surveillance video collected by the monitoring equipment inside the building, performs frame processing on the surveillance video to obtain a surveillance video frame sequence, obtains the overlapping area in the surveillance videos collected by the two monitoring devices based on the surveillance video frame sequence, and uses it as the target area;

[0064] Analysis module: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window;

[0065] Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area;

[0066] Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1;

[0067] Adjustment module: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​of 1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ;

[0068] An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

[0069] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent security monitoring method for smart buildings based on the Internet of Things, characterized in that: The following steps are involved: S1: Obtain a surveillance video collected by a surveillance device inside a building, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, obtain an overlapping area in the surveillance videos collected by two surveillance devices based on the surveillance video frame sequence, and use the overlapping area as a target area; S2: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window; Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area; Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1; S3: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ; An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

2. According to claim 1, the intelligent security monitoring method for smart buildings based on the Internet of Things is characterized in that: In step S1, the process of detecting the overlapping area in the surveillance video collected by the surveillance device specifically includes: For any two surveillance video frames with the same timestamp, extract feature points in the surveillance video frames, match the feature points, calculate a homography matrix based on the matched feature points, and project the surveillance video frame to another surveillance video frame based on the homography matrix; The projected surveillance video frame and the original surveillance video frame are weightedly superimposed to determine the overlapping area of ​​the two surveillance video frames, which is used as the initial overlapping area, and the union of the initial overlapping areas is determined, which is used as the overlapping area in the surveillance videos collected by the two surveillance devices.

3. According to the method for intelligent security monitoring of smart buildings based on the Internet of Things in claim 1, it is characterized in that: In step S2, the process of determining the comparison value specifically includes: When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=1; When the correction ratio of the ath position in A in the target ranking is greater than the correction ratio of the ath position in A in the target ranking, the comparison value Xa=-1; When the correction ratio of the ath position in A in the target ranking is equal to the correction ratio of the ath position in A in the target ranking, the comparison value Xa=0.

4. The method for intelligent security monitoring for smart buildings based on the Internet of Things according to claim 1 is characterized in that: In the step S3, the process of reducing the definition of the target area in the adjustment window specifically includes: When the comparison number C+ appears first 1 = Cys, the playback window corresponding to the target sorting A is used as the adjustment window, and Cys represents the preset comparison number threshold; when the comparison number C- 1 =Cys, the play window corresponding to the target sorting B is used as the adjustment window; The resolution of the target area in the adjustment window is reduced so that the clarity of the target area in the adjustment window reaches a preset clarity.

5. The method for intelligent security monitoring for smart buildings based on the Internet of Things according to claim 1 is characterized in that: In the step S3, when the proportion of comparison values ​​of 0 in the screening and sorting is greater than 0.4, the playback window with a larger proportion of the target area in the playback window is marked as an adjustment window.

6. The method for intelligent security monitoring for smart buildings based on the Internet of Things according to claim 1 is characterized in that: In the step S1, when the monitoring device collects monitoring video, the posture of the monitoring device is kept unchanged.

7. The method for intelligent security monitoring for smart buildings based on the Internet of Things according to claim 1 is characterized in that: In the step S1, when the target area does not exist, an early warning message is sent for prompting.

8. An intelligent security monitoring system for smart buildings based on the Internet of Things, characterized in that: include: Area determination module: obtains the surveillance video collected by the monitoring equipment inside the building, performs frame processing on the surveillance video to obtain a surveillance video frame sequence, obtains the overlapping area in the surveillance videos collected by the two monitoring devices based on the surveillance video frame sequence, and uses it as the target area; Analysis module: taking the surveillance video corresponding to the target area as the target video, taking the surveillance screen in the surveillance center as the reference surface, determining the playback window of the target video on the reference surface, and marking the target area in the playback window; Taking the lower edge of the reference surface as a reference line, the area below the reference line as a positive area, and the area above the reference line as a negative area, the reference line is moved along a target direction at a set speed, the target direction is parallel to the side of the reference surface and points to the upper edge of the reference surface, and the area ratio d is recorded at a preset time interval, the area ratio being the ratio of the portion of the target area in the positive area to the portion of the target area in the negative area; Calculate the correction ratio D=d*b, where b represents the ratio of the target area to the playback window, sort the correction ratios according to the time axis order to obtain a target ranking, determine the target ranking A and the target ranking B corresponding to the target area, and determine a comparison value based on the size of the correction ratio at the same ranking position in the target ranking A and the target ranking B, where the comparison value includes 1, 0, and -1; Adjustment module: Sort the comparison values ​​in the order of the time axis to obtain a screening sort, and starting from the first comparison value in the screening sort, count the total number of comparison values ​​of 1 and -1 respectively, and record them as comparison numbers C+ 1 and comparison number C- 1 ; An adjustment window is determined based on the comparison number, and a target area within the adjustment window is preprocessed to reduce definition.

Images