Monitoring video analysis alarm method and related equipment

Abstract

The invention discloses a monitoring video analysis alarm method and related equipment. The monitoring video analysis alarm method comprises the following steps: acquiring a detection frame identifier and a detection line identifier delimited by a user in a monitoring video picture; determining a trigger detection area of the monitoring video according to the detection frame identifier; for the detection line identifier which is an undirected line, carrying out cross-line trigger detection on the moving personnel in the monitoring video according to an undirected line segment in the trigger detection area, and determining a first trigger event; for a detection line identifier which is a directed line, performing movement trigger detection on a moving person in the monitoring video according to a labeling position and a labeling direction of a directed line segment in a trigger detection area, and determining a second trigger event; and counting the first trigger event and the second trigger event, and triggering an alarm in combination with a preset alarm mechanism. According to the invention, through introduction of the flexible detection frame and the detection line identifier, the classification triggering detection strategy and the statistical alarm function, comprehensive, efficient and intelligent analysis of the monitoring video is realized.

Description

Technical Field

[0001] The present application relates to the field of video analysis, and more specifically, to a monitoring video analysis alarm method and related equipment. Background Art

[0002] With the continuous development of video surveillance technology, the monitoring method is gradually changing from the traditional monitoring method that relies entirely on manual video viewing to a more intelligent and automated direction. As a common method in the field of video surveillance, motion detection and analysis technology is based on the identification of the movement of objects in the picture by comparing consecutive video frames. This technology can automatically detect and respond to changes in the picture. Once a moving object is detected, an alarm message will be triggered and the user will be immediately reminded on the client interface.

[0003] Although motion detection analysis can detect changes in the picture, it has obvious deficiencies in target positioning and detection area display. Users can only know that some changes have occurred in the picture, but cannot intuitively understand the specific location, scope and shape of the change. In practical applications, this may cause users to miss key information, increase the risk of false alarms and missed alarms, and require users to spend extra time to locate and analyze. In addition, when detecting objects that trigger boundaries, existing technologies often cannot accurately capture targets, and are unable to judge changes in the number of targets. The count detection values ​​are often not accurate enough to meet the needs of accurate statistics and analysis of the number of targets.

[0004] Based on this, the present application provides a more comprehensive surveillance video analysis and alarm solution, which effectively makes up for the shortcomings of the existing technology and improves the intelligence level and practical application effect of surveillance video analysis. Summary of the invention

[0005] In view of this, the present application provides a surveillance video analysis and alarm method and related equipment, which realizes comprehensive, efficient and intelligent analysis of surveillance videos by introducing flexible detection frame and detection line identification, classification trigger detection strategy and statistical alarm function, and effectively makes up for the shortcomings of the existing technology.

[0006] A monitoring video analysis alarm method, comprising:

[0007] Obtaining a detection frame identifier and a detection line identifier drawn by a user in a surveillance video screen, wherein the detection line identifier includes an undirected line and a directed line;

[0008] Determining a trigger detection area for the surveillance video according to the detection frame identifier;

[0009] For the detection line marker that is an undirected line, performing a line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area to determine a first trigger event;

[0010] For the detection line marker being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event;

[0011] The first trigger event and the second trigger event are counted, and an alarm is triggered in combination with a preset alarm mechanism.

[0012] Optionally, also include:

[0013] Acquire a trigger detection option of a user, and determine a line crossing detection baseline according to the trigger detection option;

[0014] When the line-crossing detection baseline is a detection target frame line, performing line-crossing trigger detection on a moving person in the surveillance video according to an undirected line segment in the trigger detection area to determine a first trigger event includes:

[0015] Performing background matching and scene recognition on the surveillance video picture corresponding to the area where the undirected line segment in the trigger detection area is located, determining the detection target represented by the undirected line segment, and generating a detection target frame line;

[0016] A cross-line trigger detection is performed on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event.

[0017] Optionally, performing motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event includes:

[0018] Performing background matching and scene recognition on the surveillance video images corresponding to the marked positions and marked directions of the directed line segments in the trigger detection area to determine the movement triggering conditions represented by the directed line segments;

[0019] Based on the motion trigger condition, motion trigger detection is performed on the moving person in the monitoring video to determine a second trigger event.

[0020] Optionally, after determining the trigger detection area for the surveillance video according to the detection frame identifier, the method further includes:

[0021] Identify the moving person in the trigger detection area and form a human-shaped detection frame;

[0022] Performing a cross-line trigger detection on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event, including:

[0023] The mobile person to be detected is obtained by screening according to the scale of the video image and the size of the human detection frame;

[0024] A cross-line trigger detection is performed on the person to be detected in the monitoring video according to the detection target frame line to determine a first trigger event.

[0025] Optionally, background matching and scene recognition are performed on the surveillance video screen corresponding to the marked position and the marked direction of the directed line segment in the trigger detection area to determine the movement trigger condition represented by the directed line segment, including:

[0026] Performing background matching and scene recognition on the surveillance video screen corresponding to the marked position of the directed line segment in the trigger detection area to determine the moving path represented by the directed line segment;

[0027] Determining the marked direction of the directed line segment in the trigger detection area as the moving direction represented by the directed line segment;

[0028] A movement trigger condition is generated based on the movement path and the movement direction.

[0029] Optionally, also include:

[0030] Identify mobile personnel in the trigger detection area and count the real-time number of people in the area;

[0031] When the real-time number of people in the area exceeds the preset number alarm threshold, an alarm is triggered.

[0032] A monitoring video analysis and alarm device, comprising:

[0033] An identification acquisition unit, used to acquire a detection frame identification and a detection line identification defined by a user in a surveillance video screen, wherein the detection line identification includes an undirected line and a directed line;

[0034] An area determination unit, configured to determine a trigger detection area for the surveillance video according to the detection frame identifier;

[0035] A first trigger unit is configured to perform a line crossing trigger detection on a moving person in the monitoring video according to the undirected line segment in the trigger detection area for the detection line identifier being an undirected line, and determine a first trigger event;

[0036] A second trigger unit is used to perform a motion trigger detection on a moving person in the monitoring video according to the marked position and marked direction of the directed line segment in the trigger detection area for the detection line marker being a directed line, and determine a second trigger event;

[0037] The alarm statistics unit is used to count the first trigger event and the second trigger event, and trigger an alarm in combination with a preset alarm mechanism.

[0038] A surveillance video analysis alarm device, comprising a memory and a processor;

[0039] The memory is used to store programs;

[0040] The processor is used to execute the program to implement each step of the monitoring video analysis and alarm method as described in any one of the above items.

[0041] A readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, each step of the monitoring video analysis and alarm method as described in any one of the above items is implemented.

[0042] A computer program product includes a computer program, wherein when the computer program is run by a processor, each step of the monitoring video analysis and alarm method as described in any one of the above items is executed.

[0043] It can be seen from the above technical solutions that the monitoring video analysis alarm method and related equipment provided by the embodiment of the present application realize the accurate definition of the monitoring video trigger detection area by obtaining the detection frame mark and detection line mark flexibly defined by the user in the monitoring video screen. This feature enables the user to freely draw irregularly shaped detection frames and detection lines with orientation indicators according to actual monitoring needs, thereby greatly improving the flexibility and accuracy of detection.

[0044] In terms of trigger detection, this application adopts different detection strategies for directed line segments based on undirected line segments. For undirected line segments, it is possible to detect whether a moving person in the trigger detection area has crossed these line segments, thereby determining the first trigger event; and for directed line segments, it is possible to determine whether the moving direction of the moving person is consistent with the direction indicated by the line segment based on the marked position and marked direction of the line segment, thereby determining the second trigger event. This design not only enhances the event detection capability, but also can more accurately identify different types of trigger events, providing strong support for subsequent alarm processing.

[0045] In addition, the present application can automatically count the number and type of the first trigger event and the second trigger event, and trigger the corresponding alarm according to the preset alarm mechanism. This intelligent processing method not only improves the monitoring efficiency, but also enables users to obtain key information in a timely manner and make effective responses.

[0046] In summary, this application achieves comprehensive, efficient and intelligent analysis of surveillance videos by introducing flexible detection frame and detection line identification, classification trigger detection strategy and statistical alarm function. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0048] Figure 1 A flowchart of a monitoring video analysis and alarm method disclosed in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of a detection frame mark and a detection line mark disclosed in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of a detection target frame line disclosed in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of screening a mobile person to be detected disclosed in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of a detection line marker for a directed line disclosed in an embodiment of the present application;

[0053] Figure 6 A schematic diagram of a surveillance video analysis and alarm device disclosed in an embodiment of the present application;

[0054] Figure 7 This is a hardware structure block diagram of a surveillance video analysis and alarm device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0057] Next, the present application scheme is introduced. The present application proposes the following technical scheme, please see below for details.

[0058] Figure 1 This is a flowchart of a surveillance video analysis and alarm method disclosed in an embodiment of the present application.

[0059] like Figure 1 As shown, the method may include:

[0060] Step S1, obtaining a detection frame mark and a detection line mark drawn by a user in a monitoring video screen, wherein the detection line mark includes an undirected line and a directed line.

[0061] Specifically, the user can freely draw the required detection marks, including detection frame marks and detection line marks, in the real-time monitoring video stream using the intuitive graphical user interface (GUI) provided by the system, a mouse, a touch pad or other input devices. Figure 2 As shown, the blue one is the detection frame mark and the red one is the detection line mark.

[0062] The detection frame logo can be not only a regular rectangle or circle, but also supports user-defined irregular polygons with up to 20 vertices to meet the target monitoring needs in various complex scenarios. Users can flexibly adjust the size and shape of the detection frame according to the actual size, shape and movement path of the monitored target to ensure the accuracy and effectiveness of monitoring.

[0063] In addition to the detection frame mark, users can also set detection line marks in the video screen. The detection line marks are further divided into undirected lines and directed lines. The detection line marks can be straight lines or curves. Undirected lines are mainly used to monitor whether the target crosses a specific path, regardless of its moving direction; directed lines are more flexible. They have clear direction indications, such as from left to right, from right to left, or bidirectional, and can accurately identify the moving direction of the target. This is especially important for application scenarios such as crowd counting and vehicle traffic management. Users can easily draw the required detection line in the video screen and specify its direction by simply dragging and clicking.

[0064] It is worth noting that, whether it is a detection frame or a detection line, users can configure specific detection rules for it during setting, such as target type (people, cars, animals, etc.), moving speed range, size limit, etc. These rules will serve as the basis for subsequent target detection and behavior analysis. In addition, the system will automatically record and save all detection frame and detection line information set by the user, including its position, shape, direction and related detection rules, so that it can be continuously used in the subsequent monitoring process without repeated settings.

[0065] Step S2: determining a trigger detection area for the surveillance video according to the detection frame identifier.

[0066] Specifically, based on the detection frame identifier set by the user in the previous steps, the trigger detection area can be accurately determined in the surveillance video. The system first parses the position, shape, size and related detection rule information in the detection frame identifier, and then maps this information to the real-time surveillance video stream to ensure that the detection frame accurately corresponds to the video scene. On this basis, the system further determines the trigger boundary and configures the trigger detection area according to the detection rules set by the user (such as target type, movement speed, size limit, etc.). Finally, the system saves all configuration information about the trigger detection area for continuous use in subsequent monitoring processes to ensure the accuracy and effectiveness of target detection.

[0067] Step S3: for the detection line marker being an undirected line, performing line crossing trigger detection on a moving person in the surveillance video according to the undirected line segments in the trigger detection area to determine a first trigger event.

[0068] Specifically, for the detection line marker that is an undirected line, first identify and locate all undirected line segments in the trigger detection area, and monitor in real time whether the moving personnel in the surveillance video cross these undirected line segments. Once it is detected that the moving personnel crosses the undirected line segment, it will be immediately triggered and recorded as the first trigger event. This cross-line trigger detection mechanism can capture and respond to potential safety hazards or behavioral anomalies in real time for personnel flow management, intrusion detection, and security warnings in the monitoring scene.

[0069] Step S4: For the detection line marker that is a directed line, according to the marked position and marked direction of the directed line segment in the trigger detection area, a motion trigger detection is performed on the moving person in the monitoring video to determine a second trigger event.

[0070] Specifically, for the detection line marker that is a directed line, the marked position and marked direction of all directed line segments in the trigger detection area will first be identified. Subsequently, the moving trajectory of the mobile personnel in the surveillance video is monitored in real time to determine whether they are moving along the direction marked by the directed line segment. Once it is detected that the mobile personnel is moving in the direction of the directed line segment and the moving path conforms to the path formed by the marked position, the system will immediately trigger and record it as the second trigger event. This mobile trigger detection mechanism plays an important role in traffic monitoring, crowd guidance, and specific area management, and can accurately capture and respond to the behavior patterns of mobile personnel.

[0071] Step S5: Count the first trigger event and the second trigger event, and trigger an alarm in combination with a preset alarm mechanism.

[0072] Specifically, the first trigger event (i.e., undirected line crossing event) and the second trigger event (i.e., directed line movement event) detected previously are counted and analyzed. By accumulating information such as the number, occurrence time, and specific location of various trigger events, the system can fully grasp the dynamic situation in the monitoring area. According to the alarm mechanism preset by the user, these trigger events are intelligently evaluated. The alarm mechanism may include judgment criteria in multiple dimensions such as event type, occurrence frequency, and duration. Once the trigger event meets the preset alarm conditions, the system will immediately trigger an alarm and warn the user through various methods such as sound, image flashing, and SMS push, ensuring that the user can quickly respond and deal with potential safety hazards or abnormal situations.

[0073] The statistical alarm function not only realizes real-time analysis and processing of surveillance videos, but also provides users with timely and accurate alarm information, effectively improving the practicality and security of the monitoring system.

[0074] In addition, this application also incorporates a real-time people counting function, which includes the following two core steps:

[0075] ① Identify the moving personnel in the trigger detection area and count the real-time number of people in the area.

[0076] ② When the real-time number of people in the area exceeds the preset alarm threshold, an alarm is triggered.

[0077] Specifically, the system identifies the moving personnel in the trigger detection area and counts the real-time number of people in the area. Once the real-time number of people detected in the area exceeds the preset number alarm threshold, the system will immediately trigger the number alarm. This alarm mechanism sends a warning to the user through various means such as sound, image flashing, and SMS push, reminding the user to pay attention to the gathering of people in the monitoring area, so that the user can take corresponding measures in time to prevent possible safety hazards or abnormal situations.

[0078] It can be seen from the above technical solutions that the monitoring video analysis alarm method and related equipment provided by the embodiment of the present application realize the accurate definition of the monitoring video trigger detection area by obtaining the detection frame mark and detection line mark flexibly defined by the user in the monitoring video screen. This feature enables the user to freely draw irregularly shaped detection frames and detection lines with orientation indicators according to actual monitoring needs, thereby greatly improving the flexibility and accuracy of detection.

[0079] In terms of trigger detection, this application adopts different detection strategies for directed line segments based on undirected line segments. For undirected line segments, it is possible to detect whether a moving person in the trigger detection area has crossed these line segments, thereby determining the first trigger event; and for directed line segments, it is possible to determine whether the moving direction of the moving person is consistent with the direction indicated by the line segment based on the marked position and marked direction of the line segment, thereby determining the second trigger event. This design not only enhances the event detection capability, but also can more accurately identify different types of trigger events, providing strong support for subsequent alarm processing.

[0080] In addition, the system can automatically count the number and type of the first trigger event and the second trigger event, and trigger the corresponding alarm according to the preset alarm mechanism. This intelligent processing method not only improves the monitoring efficiency, but also enables users to obtain key information in a timely manner and make effective responses.

[0081] In summary, this application achieves comprehensive, efficient and intelligent analysis of surveillance videos by introducing flexible detection frame and detection line identification, classification trigger detection strategy and statistical alarm function.

[0082] In some embodiments of the present application, a user-defined trigger detection option is further introduced to provide a more flexible and accurate monitoring service. This option allows the user to customize the baseline for cross-line detection according to actual needs, thereby ensuring that the detection range of the monitoring system is highly consistent with the user's focus. The present application also includes:

[0083] A trigger detection option of a user is obtained, and a line crossing detection baseline is determined according to the trigger detection option.

[0084] Specifically, under normal circumstances, whether an event is triggered is determined by judging whether the moving person crosses the detection line mark drawn by the user. However, in order to make the event detection more accurate, the user can further choose to use the cross-line detection baseline as the detection target for event triggering. That is, after selecting the cross-line detection baseline option, the cross-line trigger detection will no longer be determined by the detection line mark drawn by the user, but by the generated detection target frame line.

[0085] On this basis, step S3, for the detection line identifier being an undirected line, performing line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area, and determining the process of the first trigger event may further include:

[0086] Step S31, performing background matching and scene recognition on the surveillance video picture corresponding to the area where the undirected line segment in the trigger detection area is located, determining the detection target represented by the undirected line segment, and generating a detection target frame line.

[0087] Specifically, the system first separates the static background and dynamic foreground from the surveillance video through background matching operations in order to more accurately capture and identify the target object. By comparing the difference between the current video frame and the background model, the system can identify the changed part of the surveillance picture, which is usually the location of the moving person or object.

[0088] Next, the dynamic foreground obtained after background matching is further analyzed through scene recognition to determine the detection target represented by the undirected line segment. For example, in the entry and exit detection scenario, the system may identify key locations such as access control areas and passageways as detection targets.

[0089] Once the detection target is determined, the system will automatically generate a detection target frame line based on the shape, size and location information of the target. This frame line closely fits the outline of the detection target and provides an accurate reference benchmark for subsequent cross-line detection.

[0090] Step S32: performing a line-crossing trigger detection on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event.

[0091] Specifically, based on the detection target frame line generated in the previous step, the mobile personnel in the surveillance video are monitored and analyzed in real time. The surveillance images within the detection target frame line are continuously tracked to accurately capture the dynamic behavior of the mobile personnel. Once a mobile person jumps out of the frame line, it is considered that a crossing line behavior has occurred, and this event will be immediately triggered and recorded as the first trigger event.

[0092] In order to ensure the accuracy and reliability of line crossing detection, the system will also perform a series of verification and confirmation operations on the mobile personnel's line crossing behavior. For example, it checks whether the moving trajectory of the mobile personnel is continuous, whether the speed is reasonable, and whether the line crossing behavior meets the user's preset trigger conditions. Only when all verification conditions are met will the first trigger event be finally confirmed and recorded.

[0093] Cross-line detection by cross-line detection baseline has obvious advantages in application scenarios such as entry and exit detection. Figure 3 The red color is the detection line mark. The purpose of the user making the detection line mark is to detect the entry and exit of the first door on the left side of the video screen. Therefore, the detection target is the first door on the left side of the video screen. The yellow color is the detection target frame line. At this time, the detection target frame line, i.e., the yellow frame line, can be selected to perform cross-line trigger detection on the moving person in the monitoring video to determine the first trigger event.

[0094] Further, determining the first trigger event may include the following two methods:

[0095] The first type: personnel appearance

[0096] Directly identify the appearance of moving personnel to trigger cross-line detection.

[0097] Specifically, the system uses video analysis technology to directly identify the appearance of moving people in the surveillance video. When a moving person is identified, the system will track its movement trajectory in real time and determine whether it crosses the preset detection target frame line. Once the moving person crosses the line, the system will immediately trigger and record the first trigger event.

[0098] Second, human detection frame method

[0099] After determining the trigger detection area of ​​the surveillance video according to the detection frame identifier, the method further includes:

[0100] Identify the moving person in the trigger detection area and form a human-shaped detection frame;

[0101] Performing a cross-line trigger detection on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event, including:

[0102] ① Screening the moving person to be detected according to the scale of the video screen and the size of the human detection frame;

[0103] ② Performing a cross-line trigger detection on the person to be detected in the surveillance video according to the detection target frame line to determine a first trigger event.

[0104] Specifically, after determining the trigger detection area of ​​the surveillance video according to the detection frame identification, the system will use advanced human detection technology to identify mobile personnel in the area and form a human detection frame for each identified person. After that, the identified mobile personnel are screened according to the scale of the video screen and the size of the human detection frame. The purpose of this process is to exclude those mobile personnel who do not meet the cross-line detection conditions, such as those who are too far away, too small or abnormal in shape. Through screening, the system can ensure that only qualified personnel to be detected will be included in the subsequent cross-line trigger detection process. After screening out the personnel to be detected, the system will continue to track their movement trajectory and perform cross-line detection according to the detection target frame line. Once it is detected that the person to be detected has crossed the detection target frame line, the system will immediately trigger and record the first trigger event.

[0105] like Figure 4As shown, there are two moving persons in the picture, with green and purple human detection frames respectively. According to the detection target frame line (yellow frame line), it can be known that the current detection purpose is to detect the entry and exit of the second door on the left. At this time, according to the scale of the video screen and the size of the human detection frame, the moving persons in the purple human detection frame can be screened out, because their proportion is obviously small and does not meet the human detection frame size range that people should have when entering and exiting the second door. The moving persons to be detected are screened as those in the green human detection frame. After that, it is only necessary to perform cross-line trigger detection on the moving persons in the green human detection frame according to the detection target frame line to determine whether the first trigger event is triggered.

[0106] In some embodiments of the present application, step S4, for the detection line identifier being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area, and determining the process of the second trigger event is introduced, which may specifically include:

[0107] Step S41: performing background matching and scene recognition on the surveillance video images corresponding to the marked positions and marked directions of the directed line segments in the trigger detection area to determine the movement triggering conditions represented by the directed line segments.

[0108] Specifically, the background matching and scene recognition are first performed on the surveillance video corresponding to the directed line segments in the trigger detection area. The purpose of this step is to separate the static background elements and dynamic foreground elements from the complex surveillance images, so as to clearly outline the actual movement path represented by the directed line segments. By comparing the current video frame with the background model, the system can accurately identify the parts of the surveillance image that have changed, and these changes usually correspond to the trajectory of the moving person.

[0109] Next, the system will read the annotated direction of the directed line segment, which has been clearly specified during the creation of the detection line mark. The system will use this direction information as the movement direction represented by the directed line segment. Based on the movement path and movement direction determined in the above steps, the system will generate a specific movement trigger condition. This condition is a composite condition that includes the movement path and movement direction information, and is used in the subsequent movement trigger detection process.

[0110] like Figure 5As shown, the detection line mark of the red directed line, the user's detection goal is to detect the entry of the first door on the left side of the video screen, so the movement trigger condition represented by the red directed line segment is that the mobile person moves along the direction of the red directed line and enters the first door on the left and disappears. The detection line mark of the yellow directed line, the user's detection goal is to detect the situation of the mobile person walking from the end of the corridor and then turning back in the video screen, so the movement trigger condition represented by the yellow directed line segment is that the mobile person walks along the direction of the yellow directed line from the end of the corridor and then turns back.

[0111] That is, the process of determining the movement triggering condition represented by the directed line segment may include:

[0112] ① Performing background matching and scene recognition on the surveillance video screen corresponding to the marked position of the directed line segment in the trigger detection area to determine the moving path represented by the directed line segment;

[0113] ② Determining the marked direction of the directed line segment in the trigger detection area as the moving direction represented by the directed line segment;

[0114] ③ Generate a movement trigger condition based on the movement path and the movement direction.

[0115] The setting of motion trigger conditions should be as comprehensive and detailed as possible to ensure that the specific behavior of moving people in the surveillance video can be accurately captured. In addition to the basic moving path and moving direction information, there may be some specific elements in the background of the directed line path, such as doors, obstructions, etc. These elements have an important impact on the behavior of moving people. Therefore, the trigger conditions can be further enriched and improved by combining the specific situation of the background of the directed line path, and the accuracy and practicality of the detection can be improved.

[0116] For example, if the moving path passes through a door, a trigger condition can be set to require the moving person to pass through the door within a specific time. This can be used to monitor entry and exit behaviors, such as employee clocking in and out, visitor entry and exit registration, etc. If the moving path is blocked by an obstruction (such as a pillar, wall, etc.), a trigger condition can be set to require the moving person to continue moving along the specified path after bypassing the obstruction. This can be used to monitor the movement trajectory of people in complex environments to ensure that they do not deviate from the predetermined route.

[0117] Step S42: Perform motion trigger detection on the moving person in the surveillance video based on the motion trigger condition to determine a second trigger event.

[0118] Specifically, the dynamic behavior of mobile personnel is captured and tracked by real-time acquisition and continuous analysis of surveillance video images. The movement of mobile personnel in the surveillance video is matched according to the mobile trigger conditions. This process will comprehensively consider the real-time position, movement speed and direction of the mobile personnel to ensure the accuracy of the detection. Once the system detects that a mobile person meets the mobile trigger conditions, it will immediately trigger and record the second trigger event, and record key information such as the trigger time, location, and mobile person identity in detail. This information is crucial for subsequent security management, behavior analysis, and alarm processing. The system will handle the trigger event accordingly according to the preset rules and processes, such as sending alarm information, recording logs, or triggering other security devices.

[0119] A monitoring video analysis and alarm device provided in an embodiment of the present application is described below. The monitoring video analysis and alarm device described below and the monitoring video analysis and alarm method described above can refer to each other.

[0120] See also Figure 6 , Figure 6 A schematic diagram of a surveillance video analysis and alarm device disclosed in an embodiment of the present application.

[0121] like Figure 6 As shown, the monitoring video analysis and alarm device may include:

[0122] The identification acquisition unit 110 is used to acquire the detection frame identification and the detection line identification drawn by the user in the monitoring video screen, and the detection line identification includes an undirected line and a directed line;

[0123] An area determination unit 120, configured to determine a trigger detection area for the surveillance video according to the detection frame identifier;

[0124] A first trigger unit 130 is used for performing a line crossing trigger detection on a moving person in the monitoring video according to the undirected line segment in the trigger detection area for the detection line identifier being an undirected line, and determining a first trigger event;

[0125] The second trigger unit 140 is used to perform a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area for the detection line marker being a directed line, and determine a second trigger event;

[0126] The alarm statistics unit 150 is used to count the first trigger event and the second trigger event, and trigger an alarm in combination with a preset alarm mechanism.

[0127] It can be seen from the above technical solutions that the monitoring video analysis alarm method and related equipment provided by the embodiment of the present application realize the accurate definition of the monitoring video trigger detection area by obtaining the detection frame mark and detection line mark flexibly defined by the user in the monitoring video screen. This feature enables the user to freely draw irregularly shaped detection frames and detection lines with orientation indicators according to actual monitoring needs, thereby greatly improving the flexibility and accuracy of detection.

[0128] In terms of trigger detection, this application adopts different detection strategies for directed line segments based on undirected line segments. For undirected line segments, it is possible to detect whether a moving person in the trigger detection area has crossed these line segments, thereby determining the first trigger event; and for directed line segments, it is possible to determine whether the moving direction of the moving person is consistent with the direction indicated by the line segment based on the marked position and marked direction of the line segment, thereby determining the second trigger event. This design not only enhances the event detection capability, but also can more accurately identify different types of trigger events, providing strong support for subsequent alarm processing.

[0129] In addition, the system can automatically count the number and type of the first trigger event and the second trigger event, and trigger the corresponding alarm according to the preset alarm mechanism. This intelligent processing method not only improves the monitoring efficiency, but also enables users to obtain key information in a timely manner and make effective responses.

[0130] In summary, this application achieves comprehensive, efficient and intelligent analysis of surveillance videos by introducing flexible detection frame and detection line identification, classification trigger detection strategy and statistical alarm function.

[0131] Optionally, the monitoring video analysis and alarm device may further include:

[0132] A detection option unit, used to obtain a trigger detection option of a user, and determine a line crossing detection baseline according to the trigger detection option;

[0133] The first trigger unit can also be used to perform background matching and scene recognition on the surveillance video images corresponding to the area where the undirected line segment in the trigger detection area is located, determine the detection target represented by the undirected line segment, and generate a detection target frame line. According to the detection target frame line, cross-line trigger detection is performed on moving personnel in the surveillance video to determine the first trigger event.

[0134] Optionally, the second triggering unit may include:

[0135] A trigger condition unit, used to perform background matching and scene recognition on the surveillance video screen corresponding to the marked position and marked direction of the directed line segment in the trigger detection area, and determine the movement trigger condition represented by the directed line segment;

[0136] The motion detection unit is used to perform motion trigger detection on the moving person in the monitoring video based on the motion trigger condition to determine the second trigger event.

[0137] Optionally, the area determination unit may also be configured to identify moving persons in the trigger detection area and form a human-shaped detection frame after determining the trigger detection area for the surveillance video according to the detection frame identifier.

[0138] The first trigger unit may include:

[0139] A ratio screening unit, used for screening the moving persons to be detected according to the scale of the video image and the size of the human detection frame;

[0140] A line-crossing detection unit is used to perform line-crossing trigger detection on the person to be detected in the monitoring video according to the detection target frame line to determine a first trigger event.

[0141] Optionally, the trigger condition unit may include:

[0142] A moving path unit, used to perform background matching and scene recognition on the surveillance video picture corresponding to the marked position of the directed line segment in the trigger detection area, and determine the moving path represented by the directed line segment;

[0143] A moving direction unit, used to determine the marked direction of the directed line segment in the trigger detection area as the moving direction represented by the directed line segment;

[0144] A condition generating unit is used to generate a movement triggering condition based on the movement path and the movement direction.

[0145] Optionally, the monitoring video analysis and alarm device may further include:

[0146] The population counting unit identifies mobile persons in the trigger detection area and counts the real-time population of the area, and triggers an alarm when the real-time population of the area exceeds a preset population alarm threshold.

[0147] The monitoring video analysis alarm device provided in the embodiment of the present application can be applied to monitoring video analysis alarm equipment. Figure 7 The hardware structure diagram of the monitoring video analysis alarm device is shown in FIG. Figure 7 ,The hardware structure of the monitoring video analysis alarm device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0148] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0149] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0150] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0151] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0152] Obtaining a detection frame identifier and a detection line identifier drawn by a user in a surveillance video screen, wherein the detection line identifier includes an undirected line and a directed line;

[0153] Determining a trigger detection area for the surveillance video according to the detection frame identifier;

[0154] For the detection line marker that is an undirected line, performing a line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area to determine a first trigger event;

[0155] For the detection line marker being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event;

[0156] The first trigger event and the second trigger event are counted, and an alarm is triggered in combination with a preset alarm mechanism.

[0157] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0158] The embodiment of the present application further provides a readable storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0159] Obtaining a detection frame identifier and a detection line identifier drawn by a user in a surveillance video screen, wherein the detection line identifier includes an undirected line and a directed line;

[0160] Determining a trigger detection area for the surveillance video according to the detection frame identifier;

[0161] For the detection line marker that is an undirected line, performing a line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area to determine a first trigger event;

[0162] For the detection line marker being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event;

[0163] The first trigger event and the second trigger event are counted, and an alarm is triggered in combination with a preset alarm mechanism.

[0164] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0165] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the execution method is as follows:

[0166] Obtaining a detection frame identifier and a detection line identifier drawn by a user in a surveillance video screen, wherein the detection line identifier includes an undirected line and a directed line;

[0167] Determining a trigger detection area for the surveillance video according to the detection frame identifier;

[0168] For the detection line marker that is an undirected line, performing a line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area to determine a first trigger event;

[0169] For the detection line marker being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event;

[0170] The first trigger event and the second trigger event are counted, and an alarm is triggered in combination with a preset alarm mechanism.

[0171] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0172] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0173] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0174] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A monitoring video analysis alarm method, characterized in that: include: Obtaining a detection frame identifier and a detection line identifier drawn by a user in a surveillance video screen, wherein the detection line identifier includes an undirected line and a directed line; Determining a trigger detection area for the surveillance video according to the detection frame identifier; For the detection line marker that is an undirected line, performing a line crossing trigger detection on a moving person in the surveillance video according to the undirected line segment in the trigger detection area to determine a first trigger event; For the detection line marker being a directed line, performing a motion trigger detection on a moving person in the surveillance video according to the marked position and marked direction of the directed line segment in the trigger detection area to determine a second trigger event; The first trigger event and the second trigger event are counted, and an alarm is triggered in combination with a preset alarm mechanism.

2. The method according to claim 1, characterized in that Also includes: Acquire a trigger detection option of a user, and determine a line crossing detection baseline according to the trigger detection option; In the case where the line crossing detection baseline is a detection target frame line, performing line crossing trigger detection on a moving person in the surveillance video according to an undirected line segment in the trigger detection area to determine a first trigger event includes: Performing background matching and scene recognition on the surveillance video picture corresponding to the area where the undirected line segment in the trigger detection area is located, determining the detection target represented by the undirected line segment, and generating a detection target frame line; A cross-line trigger detection is performed on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event.

3. The method according to claim 1, characterized in that According to the marked position and the marked direction of the directed line segment in the trigger detection area, a motion trigger detection is performed on the moving person in the monitoring video to determine a second trigger event, including: Performing background matching and scene recognition on the surveillance video images corresponding to the marked positions and marked directions of the directed line segments in the trigger detection area to determine the movement triggering conditions represented by the directed line segments; Based on the motion trigger condition, motion trigger detection is performed on the moving person in the monitoring video to determine a second trigger event.

4. The method according to claim 2, characterized in that: After determining the trigger detection area of ​​the surveillance video according to the detection frame identifier, the method further includes: Identify the moving person in the trigger detection area and form a human-shaped detection frame; Performing a cross-line trigger detection on a moving person in the surveillance video according to the detection target frame line to determine a first trigger event, including: The mobile person to be detected is obtained by screening according to the scale of the video image and the size of the human detection frame; A cross-line trigger detection is performed on the person to be detected in the monitoring video according to the detection target frame line to determine a first trigger event.

5. The method according to claim 3, characterized in that: Performing background matching and scene recognition on the surveillance video screen corresponding to the marked position and marked direction of the directed line segment in the trigger detection area to determine the movement trigger condition represented by the directed line segment includes: Performing background matching and scene recognition on the surveillance video screen corresponding to the marked position of the directed line segment in the trigger detection area to determine the moving path represented by the directed line segment; Determining the marked direction of the directed line segment in the trigger detection area as the moving direction represented by the directed line segment; A movement trigger condition is generated based on the movement path and the movement direction.

6. The method according to claim 1, characterized in that Also includes: Identify mobile personnel in the trigger detection area and count the real-time number of people in the area; When the real-time number of people in the area exceeds the preset number alarm threshold, an alarm is triggered.

7. A monitoring video analysis and alarm device, characterized in that: include: An identification acquisition unit, used to acquire a detection frame identification and a detection line identification defined by a user in a surveillance video screen, wherein the detection line identification includes an undirected line and a directed line; An area determination unit, configured to determine a trigger detection area for the surveillance video according to the detection frame identifier; A first trigger unit is configured to perform a line crossing trigger detection on a moving person in the monitoring video according to the undirected line segment in the trigger detection area for the detection line identifier being an undirected line, and determine a first trigger event; A second trigger unit is used to perform a motion trigger detection on a moving person in the monitoring video according to the marked position and marked direction of the directed line segment in the trigger detection area for the detection line marker being a directed line, and determine a second trigger event; The alarm statistics unit is used to count the first trigger event and the second trigger event, and trigger an alarm in combination with a preset alarm mechanism.

8. A surveillance video analysis and alarm device, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the monitoring video analysis and alarm method as described in any one of claims 1-6.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the monitoring video analysis and alarm method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, each step of the monitoring video analysis and alarm method as described in any one of claims 1 to 6 is executed.

Images