CN115052110B - Security method, security system and computer readable storage medium - Google Patents
Security method, security system and computer readable storage medium Download PDFInfo
- Publication number
- CN115052110B CN115052110B CN202210978161.2A CN202210978161A CN115052110B CN 115052110 B CN115052110 B CN 115052110B CN 202210978161 A CN202210978161 A CN 202210978161A CN 115052110 B CN115052110 B CN 115052110B
- Authority
- CN
- China
- Prior art keywords
- determining
- security
- target object
- monitoring device
- video stream
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/646—Circuits for processing colour signals for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a security method, a security system and a computer readable storage medium, which are applied to the technical field of data processing, and the method comprises the following steps: acquiring a first video stream acquired by a first monitoring device, and detecting a target object based on the first video stream; when a target object is detected in the first video stream, determining a motion track of the target object according to the first video stream; determining a target security area according to the motion track, and determining a second monitoring device according to the target security area; starting a second monitoring device and acquiring a second video stream acquired by the second monitoring device; determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream; and determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level, and reducing resource loss while improving security through the scheme.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a security method, a security system, and a computer-readable storage medium.
Background
With the wide use of monitoring devices, the problem of security is effectively solved. Particularly for dark environments. At present, a plurality of monitoring devices are mainly arranged in a security area, video information in the security area is collected in real time through the monitoring devices and then transmitted to a monitoring terminal connected with the monitoring devices for monitoring, and a worker responds when monitoring abnormity, so that security in a dark environment is realized. However, in the course of designing and implementing the present application, the inventors found that at least the following problems exist: the monitoring device needs to be in an on state for a long time, which causes serious resource loss.
Disclosure of Invention
The application aims to solve the problem of resource loss caused by the fact that a monitoring device is in an open state for a long time by providing a security method, a security system and a computer readable storage medium.
The application provides a security method, which comprises the following steps:
acquiring a first video stream acquired by a first monitoring device, and detecting a target object based on the first video stream;
when the target object is detected in the first video stream, determining a motion track of the target object according to the first video stream;
determining a target security area according to the motion track, and determining a second monitoring device according to the target security area, wherein the second monitoring device is a monitoring device which is in a dormant state in other monitoring devices except the first monitoring device in the target security area;
starting the second monitoring device and acquiring a second video stream acquired by the second monitoring device;
determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream;
and determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level.
Optionally, the step of determining a target security area according to the motion trajectory and determining a second monitoring device according to the target security area includes:
determining the initial position and the current position of the target object according to the motion track of the target object, wherein the initial position of the target object is the position of the initial point of the motion track;
determining the slope of the motion trail according to the starting position and the current position;
when the slope is larger than or smaller than a preset value, determining a first security area as the target security area, and determining the second monitoring device according to the environmental parameters in the target security area; alternatively, the first and second liquid crystal display panels may be,
and when the slope is equal to a preset value, determining a second security area as the target security area, and determining the second monitoring device according to the movement speed of the target object in the target security area, which is detected by the first monitoring device, wherein the first security area is larger than the second security area.
Optionally, the environmental parameters include ambient brightness and ambient noise; the step of determining the second monitoring device according to the environmental parameters in the target security area comprises:
acquiring the ambient brightness and the ambient noise in the target security area;
determining an environment brightness interval where the environment brightness is located and determining an environment noise interval where the environment noise is located;
acquiring a monitoring device serial number associated with the environment brightness interval and acquiring a monitoring device serial number associated with the environment noise interval;
determining the accumulated association times of the serial numbers of the monitoring devices;
determining the second monitoring device based on the cumulative number of associations.
Optionally, the step of determining the second monitoring device according to the movement speed of the target object in the target security area detected by the first monitoring device includes:
determining a first monitoring position corresponding to the target object at a first monitoring moment and a second monitoring position corresponding to the target object at a second monitoring moment according to the first video stream, wherein the second monitoring moment is the next moment of the first monitoring moment;
determining the movement speed of the target object according to the first monitoring time, the first monitoring position, the second monitoring time and the second monitoring position;
when the movement speed is lower than a preset speed, determining the monitoring device closest to the first monitoring device as a second monitoring device;
and when the movement speed is greater than or equal to the preset speed, determining the monitoring device in the target security area as the second monitoring device.
Optionally, after the step of determining the slope of the motion trajectory according to the starting position and the current position, the method further includes:
when the slope is updated to be equal to the preset value from being larger than the preset value, or when the slope is updated to be equal to the preset value from being smaller than the preset value, determining the starting time of each second monitoring device in the first security area and the second security area;
and sequentially starting each second monitoring device based on the starting time.
Optionally, the step of determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream includes:
performing contrast enhancement processing and color correction processing on the first video stream and the second video stream;
an act of identifying the pose of the target object and the action of the target object in the first video stream and the second video stream after the contrast enhancement and the color correction processing;
and determining a behavior prediction result and/or a security risk level associated with the target object according to the pose of the target object, the action of the target object and the environmental parameters in the target security area.
Optionally, determining the security risk level associated with the target object according to the pose of the target object, the action of the target object, and the environmental parameter includes:
comparing the action of the target object with a preset action in a risk database;
when a preset action matched with the action of the target object exists in the risk database, determining a risk score associated with the preset action as an action score of the target object;
determining a pose score of the target object and an environment score of the environmental parameter;
acquiring risk factors corresponding to the action scores, the pose scores and the environment scores respectively;
and determining the security risk level according to the action score, the pose score, the environment score and the corresponding risk factors.
Optionally, the determining or generating a security processing scheme according to the security risk level includes:
when the security risk level is smaller than a preset risk level, generating alarm information based on the security risk level, and sending the alarm information to a monitoring terminal so that the monitoring terminal executes a corresponding security processing scheme;
and when the security risk level is greater than or equal to the preset risk level, starting an alarm function.
In addition, to achieve the above object, the present invention also provides a security system, including:
the acquisition module is used for acquiring a first video stream acquired by a first monitoring device and detecting a target object based on the first video stream;
the first determining module is used for determining the motion trail of the target object according to the first video stream when the target object is detected in the first video stream;
a second determining module, configured to determine a target security area according to the motion trajectory, and determine a second monitoring device according to the target security area, where the second monitoring device is a monitoring device in a dormant state in the target security area and other monitoring devices except the first monitoring device;
the starting module is used for starting the second monitoring device and acquiring a second video stream acquired by the second monitoring device;
a third determining module, configured to determine a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream;
and the fourth determining module is used for determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium having a security program stored thereon, which when executed by a processor implements the steps of the security method described above.
According to the technical scheme of the security method, the security system and the computer-readable storage medium, a first video stream acquired by a first monitoring device is acquired, target object detection is carried out based on the first video stream, when a target object is detected in the first video stream, a motion track of the target object is determined according to the first video stream, a target security area is further determined according to the motion track, a second monitoring device in a dormant state is determined in other monitoring devices out of the first monitoring device in the target security area according to the target security area, the second monitoring device is started, a second video stream is acquired by the second monitoring device, a behavior prediction result and/or a security risk level associated with the target object are determined according to the first video stream and the second video stream, a security processing scheme is determined or generated according to the behavior prediction result and/or the security risk level, the security processing scheme is further determined or generated according to the behavior prediction result and/or the security risk level, and the security processing scheme is further determined according to the operation track of the target security area and the security level of the security object which needs to be started, the security processing scheme is further determined according to the behavior prediction result and/or security processing scheme, and the security processing resource loss of the security processing scheme is further determined, and the security processing resource loss is reduced, and the security processing problem is solved.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of a security method of the present invention;
FIG. 2 is a detailed flowchart of step S131 of the security method according to the first embodiment of the present invention;
FIG. 3 is a detailed flowchart of step S151 of the security method according to the first embodiment of the present invention;
FIG. 4 is a functional block diagram of the security system of the present invention.
The objects, features, and advantages of the present application will be further understood by reference to the following description, taken in conjunction with the accompanying drawings, which are a single embodiment and are not intended to be all-inclusive.
Detailed Description
The method comprises the steps of acquiring a first video stream acquired by a first monitoring device, detecting a target object based on the first video stream, determining a motion track of the target object according to the first video stream when the target object is detected in the first video stream, further determining a target security area according to the motion track, determining the target security area in the target security area according to the target security area, determining other monitoring devices except the first monitoring device in a dormant state by using a second monitoring device, starting the second monitoring device, acquiring a second video stream by using the second monitoring device, determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video, further determining or generating a technical scheme of a security processing scheme according to the behavior prediction result and/or the security risk level, and further determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level of the target object, and determining or increasing the security processing risk level of the target security area, and further determining or increasing the security processing scheme of the target security processing scheme.
For a better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The security method can be used in the scenes of community security, campus security, factory security and the like; the method can also be used for security protection in the daytime or at night through the security protection method, so that the safety in the target security protection area is improved, and the power consumption of the monitoring device in the target security protection area is reduced.
The technical solutions of the present application will be specifically described below by way of examples.
As shown in fig. 1, in a first embodiment of the present application, a security method of the present application includes the following steps:
step S110, a first video stream acquired by a first monitoring device is acquired, and target object detection is performed based on the first video stream.
In this embodiment, the first monitoring device is a camera. The first monitoring device can be one or even a plurality of first monitoring devices, the first monitoring device can be arranged at the entrance, and the first monitoring device can be selectively arranged at some hidden and inconspicuous corners according to actual conditions. The first monitoring device has a function of communicating with the monitoring terminal, and is used for collecting a first video stream and sending the first video stream to the monitoring terminal through a wireless network or a wired network so as to be monitored by a worker of the monitoring terminal, wherein the monitoring terminal can be a computer, a mobile phone and other terminal equipment. The monitoring terminal and the first monitoring device are preset with a communication connection relation. The first video stream is video data acquired by the first monitoring device, that is, video data at an entrance acquired by the first monitoring device; the first video stream may be composed of video data collected by a plurality of first monitoring apparatuses.
Optionally, the first video stream may be collected in real time and pushed to the monitoring terminal, and the first video stream may also be collected to the first video stream at regular time. For example, the state of the terminal may be monitored, when the monitoring terminal is in an idle state, the first video stream is pushed to the monitoring terminal in real time, and when the monitoring terminal is in a busy state, the first video stream is pushed to the monitoring terminal at regular time. Optionally, when there are a plurality of first monitoring devices, the video stream collected by each first monitoring device may be further sent to an intermediate processing device, and the intermediate processing device may be configured to store and/or process the video stream transmitted by each first monitoring device. When the intermediate processing equipment receives a video stream acquisition request of the monitoring terminal, the corresponding video stream is acquired from the intermediate processing equipment. Optionally, the first monitoring devices may interact with each other, one of the first monitoring devices may be designated as a main monitoring device, and the video streams collected by the other first monitoring devices may be sent to the main device for aggregation and then sent to the monitoring terminal for monitoring, or when a video stream acquisition request of the monitoring terminal is received, the corresponding video stream is acquired from the main monitoring device.
Optionally, when the monitoring terminal acquires the first video stream acquired by the first monitoring device, the first video stream may be analyzed to identify and detect whether a target object exists in the first video stream. Alternatively, a general identification algorithm, such as a YOLO target detection algorithm, a kalman filtering algorithm, may be used to identify the target object in the first video stream. The target object is a suspicious person, the identified and marked object can be matched with objects in a preset database, and if the target object does not belong to one of the objects in the preset database, the marked object is determined as the target object. The object in the preset database is an object passing identity authentication and has a passing authority in the region.
Optionally, in other application scenarios, other detection devices may be used in combination with the monitoring device to perform security in the area, for example, the other detection devices may be an infrared detection device, a laser radar device, or the like.
Step S120, when the target object is detected in the first video stream, determining a motion trajectory of the target object according to the first video stream.
In this embodiment, when the target object is identified to be present in the first video stream, the motion trajectory of the target object may be determined based on the first video stream. Specifically, when the existence of the target object is identified based on the first video stream, the target object may be labeled and tracked, so as to obtain the motion trajectory of the target object. Optionally, the position of the target object at each time may be marked in the first video stream at each time after the time when the target object is identified, and the position of the target object marked at each time may be fitted, so that the first video stream may be pushed in real time, and thus the moving track of the target object may be determined.
Step S130, determining a target security area according to the motion track, and determining a second monitoring device according to the target security area, wherein the second monitoring device is a monitoring device in a dormant state in the target security area and other monitoring devices except the first monitoring device.
In this embodiment, after the movement track of the target object is determined, the area in which the target object moves is determined, the map information of the area is acquired, and the target security area is defined on the map information. Optionally, the target security area may be dynamically updated based on the motion trajectory of the target object. A plurality of monitoring devices are installed in the target security area. The installation positions of the monitoring devices can be set according to actual conditions, for example, the monitoring devices can be arranged at equal intervals, and the monitoring devices can also be installed at important places such as a toilet door, a dining room door, a building door and the like.
Alternatively, in order to reduce the security process, the monitoring device is started for a long time, which causes a serious power consumption problem. After the target security area is determined, the second monitoring device needing to be started can be determined according to the target security area, and then the second monitoring device can be adopted for monitoring. The second monitoring device is a monitoring device which is in a dormant state in other monitoring devices except the first monitoring device in the target security area. The number of the second monitoring devices can be set to be more than one, and can be set according to a specific application scene.
Alternatively, a three-dimensional model of the target security area may be obtained, and the installation position of each monitoring device and the state, i.e., the operating state or the sleep state, of each monitoring device may be displayed on the three-dimensional model at the same time. The monitoring terminal can remotely designate a second monitoring device on the three-dimensional model according to the target security area and remotely control the second monitoring device to be turned on and turned off. The second monitoring device can also be automatically determined according to the target security area.
Optionally, referring to fig. 2, determining a target security area according to the motion trajectory, and determining a second monitoring device according to the target security area specifically includes the following steps:
step S131, determining the initial position and the current position of the target object according to the motion track of the target object, wherein the initial position of the target object is the position of the initial point of the motion track;
step S132, determining the slope of the motion track according to the initial position and the current position;
step S133, when the slope is greater than or less than a preset value, determining a first security area as the target security area, and determining the second monitoring device according to the environmental parameters in the target security area; or, in step S134, when the slope is equal to a preset value, determining a second security area as the target security area, and determining the second monitoring device according to the movement speed of the target object in the target security area detected by the first monitoring device, where the first security area is larger than the second security area.
In this embodiment, after the motion trajectory of the target object is determined, the start position and the current position of the target object are determined according to the motion trajectory, and then the slope of the motion trajectory is determined according to the start position and the current position. The slope is used to characterize the direction of motion of the target object. Optionally, when the slope is positive, it indicates that the target object may have a tendency to turn left, when the slope is negative, it indicates that the target object may have a tendency to turn right, and when the slope is zero, it indicates that the target object is in a straight-going state. Therefore, a preset value can be preset, and optionally, the preset value can be 0. Optionally, when the slope is greater than 0 or less than 0, the first security area is determined as the target security area. Optionally, when the slope is equal to 0, the second security area is determined as the target security area. The first security area is larger than the second security area, and under an application scene, the first security area comprises the second security area.
For example, when it is determined that the target object may have a tendency to turn left or right according to the slope of the running track of the target object, the region that can be captured by the monitoring device on the left curve and the region that can be captured by the monitoring device on the right curve are determined as the target security region. The regions that can be photographed by the monitoring devices between the left curve and the right curve (including the straight road) may be determined as the target security region together.
According to the technical scheme, the slope can be determined according to the motion track of the target object, the motion direction or the motion trend of the target object is further determined according to the slope, and the target security area and the second monitoring device which needs to be started and is in the dormant state are further determined, so that the problem of resource loss caused by long-time starting of the monitoring device is avoided, and power consumption loss is reduced on the premise of realizing security.
Optionally, after determining the slope of the motion trajectory according to the starting position and the current position of the target object, the method further includes switching the trajectories of the target object, and further determining the turn-on time of each second monitoring device. Optionally, when the slope is updated from being greater than the preset value to being equal to the preset value, that is, the target object may change from a left curve to a straight lane, or when the slope is updated from being less than the preset value to being equal to the preset value, that is, the target object may change from a left curve to a straight lane, the start time of each of the second monitoring devices in the first security area and the second security area may be determined according to the current movement speed of the target object, the current ambient noise, and the current ambient brightness, and each of the second monitoring devices may be sequentially started based on the start time. Optionally, the starting sequence of the second monitoring devices in the first security area and the second security area may also be determined, and the second monitoring devices may be sequentially started based on the starting sequence. Therefore, when the change range of the motion trail of the target object is large, the monitoring device can respond quickly and is started, so that monitoring is realized, and the purpose of security is achieved.
Alternatively, since the target object turns left and right, the light on the curved road may also change, and a safety problem is liable to occur with respect to a relatively narrow curved road. Therefore, when the first security area is determined as the target security area, the second monitoring device is determined according to the environmental parameters in the target security area. The environment parameter comprises environment brightness and environment noise, the environment brightness and the environment noise can be obtained by measuring through a sensor in the target security area, the sensor has a function of being in communication connection with the monitoring terminal, and data collected by the sensor can be sent to the monitoring terminal.
Optionally, the ambient brightness and the ambient noise in the target security area may be obtained, and the second monitoring device that needs to be turned on is determined according to the interval in which the ambient brightness and the ambient noise are located. Specifically, an ambient brightness interval in which ambient brightness is located and an ambient noise area in which ambient noise is located can be determined, each ambient brightness area and each ambient noise interval have associated monitoring devices to be turned on, the accumulated association times of each monitoring device can be comprehensively determined according to the ambient brightness and the ambient noise, and then the second monitoring device to be turned on is determined according to the accumulated association times. For example, there are three monitoring devices on the left curve, and each monitoring device has a corresponding monitoring device serial number, and is arranged in order of serial numbers, that is, monitoring device No. 1, monitoring device No. 2, and monitoring device No. 3. The monitoring device serial number associated with the ambient brightness area and the monitoring device serial number associated with the ambient noise area may be represented by the following table:
| ambient brightness interval (sheet)Bit: cd/m 2) | Ambient noise interval (Unit: db) | Monitor serial number |
| [10，20] | [10，30] | Monitoring device No. 1 |
| [21，30] | [30，50] | Monitoring device No. 1 and monitoring device No. 2 |
| [31，40] | [50，90] | Monitoring device No. 1, monitoring device No. 2 and monitoring device No. 3 |
Assume that the current ambient luminance L is 15cd/m 2 When the current environmental noise is 80db, the cumulative number of correlations for monitoring apparatus No. 1 is determined to be 2 times, and the cumulative number of correlations for monitoring apparatus No. 2 and monitoring apparatus No. 3 is determined to be 1 time, respectively. After determining the cumulative number of associations for each monitoring device, a second monitoring device may be determined based further on the cumulative number of associations. For example, in the above example, monitoring apparatus No. 1 may be determined as the second monitoring apparatus. The starting sequence or the turn-on time of each second monitoring device may also be determined according to the cumulative number of associations of each monitoring device, for example, in the above example, monitoring device No. 1 may be turned on in sequence while monitoring device No. 2 and monitoring device No. 3 are turned on. Therefore, the environmental parameters in the target security area can be monitored in real time, and the second monitoring device needing to be started is determined for monitoring, so that the resource is saved.
Alternatively, on a curve, the second monitoring device to be turned on may also be determined jointly according to the moving speed of the target object in the target security area (first security area), the ambient brightness and the ambient noise in the target security area.
Alternatively, the light on the straight road is generally brighter when the target object is straight. Therefore, when the second security area is determined to be the target security area, the second monitoring device which needs to be started can be determined according to the movement speed of the target object in the target security area. Optionally, a first monitoring position corresponding to the target object at a first monitoring time and a second monitoring position corresponding to a second monitoring time may be determined on a motion trajectory of the target object determined according to the first video stream, where the second monitoring time is a next time of the first monitoring time, and a motion speed of the target object in the target security area may be further determined according to the first monitoring time, the first monitoring position, the second monitoring time, and the second monitoring position. For example, if the first monitoring time is 3 o 'clock, the second monitoring time is 3 o' clock 02 min, the first monitoring position is point a, and the second monitoring position is point B, the moving speed of the target object in the target security area is: (A point position-B point position)/(3 point 02 min-3 point adjustment).
Optionally, after the movement speed of the target object in the second security area is determined, the movement speed is compared with a preset speed, and then the second monitoring device needing to be started is determined according to a comparison result. The preset speed can be preset according to actual conditions or specific application scenes. Optionally, when the movement speed of the target object is less than the preset speed, the monitoring device closest to the first monitoring device may be determined as the second monitoring device, so that in the process of low-speed movement of the target object, the movement track of the target object may be recorded by starting the second monitoring device closest to the first monitoring device. Alternatively, when the moving speed of the target object is greater than or equal to the preset speed, the monitoring device in the target security area (second security area) is determined as the second monitoring device. All monitoring devices in the second security area can be determined as second monitoring devices, and second monitoring devices which need to be started in the second security area can also be determined according to the movement speed of the target object, for example, monitoring devices which are arranged at intervals can be determined as second monitoring devices which need to be started, so that in the process of quick movement of the target object, related monitoring devices can be started and corresponding monitoring devices can be started based on quick response of the movement speed of the target object, and monitoring of the target object is realized.
Optionally, the second monitoring device to be started may also be determined according to the movement speed of the target object in the target security area (second security area) and the environmental parameter in the target security area.
Step S140, starting the second monitoring device, and acquiring a second video stream acquired by the second monitoring device.
In this embodiment, after the second monitoring device is determined, the second monitoring device may be remotely controlled to be turned on at the monitoring terminal, and the turned-on second monitoring device is used to collect the second video stream. The second video stream is video data collected by the second monitoring device. The acquisition mode of the second video stream is similar to that of the first video stream, and is not described herein again. Optionally, in an application scenario, after determining the second monitoring apparatus, the second monitoring apparatus may be turned on only when some conditions are satisfied. For example, the second monitoring device may be used in conjunction with other detection devices, such as an infrared detection device, to trigger the second monitoring device to turn on when the infrared detection device detects a target object. Or determining which second monitoring device is triggered to be started according to the position and the distance of the target object detected by the infrared detection device, thereby avoiding resource waste caused by long-time starting of each monitoring device.
And S150, determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream.
In this embodiment, after the second monitoring device is turned on and the second video stream is collected by the second monitoring device, the motion trajectory of the target object is tracked in real time. Alternatively, the behavior prediction result of the target object may be determined from the first video stream and the second video stream. The behavior prediction result may be a movement direction, a movement path, or the like of the target object. Optionally, a security risk level may also be determined from the first video stream and the second video stream. Optionally, the behavior prediction result and the security risk level associated with the target object may also be determined according to the first video stream and the second video stream. For example, a behavior prediction result associated with the target object may be determined according to the first video stream and the second video stream, and then a security risk level may be determined according to the behavior prediction result.
Optionally, referring to fig. 3, after the second monitoring device is started to collect the second video stream, the step of determining the behavior prediction result and/or the security risk level associated with the target object according to the first video stream and the second video stream specifically includes the following steps:
step S151, performing contrast enhancement processing and color correction processing on the first video stream and the second video stream;
step S152, identifying the pose of the target object and the action of the target object in the first video stream and the second video stream after the contrast enhancement and the color correction processing;
step S153, determining a behavior prediction result and/or a security risk level associated with the target object according to the pose of the target object, the action of the target object and the environmental parameters in the target security area.
In this embodiment, a first video frame sequence may be determined according to the first video stream, a second video frame sequence may be determined according to the second video stream, and each video frame in the first video frame sequence and the second video frame sequence may be processed respectively, so as to obtain the pose of the target object and the motion of the target object. Alternatively, since the video stream captured at night is not easily recognized due to low definition, each video frame in the first video frame sequence and the second video frame sequence needs to be subjected to contrast enhancement processing and color correction processing, respectively. Alternatively, the first video frame sequence and the second video frame sequence may be sequentially input to a contrast enhancement network and a color correction network for processing, so as to obtain a processed first video frame sequence and a processed second video frame sequence. The contrast enhancement network and the color correction network may adopt a passing network model, and detailed description thereof is omitted here.
Optionally, after obtaining the first video stream and the second video stream after the contrast enhancement processing and the color correction processing, the poses (positions and postures) of the target object in the first video stream and the second video stream after the contrast enhancement processing and the color correction processing and the actions of the target object are identified, and then the behavior prediction result and/or the security risk level of the target object are determined according to the position of the target object, the actions of the target object and the combination of the environmental parameters in the current target security area. The security risk level can be determined according to the identification results of the first video stream and the second video stream. The higher the security risk level, the more insecure the target security area, whereas the lower the security risk level, the more secure the target security area. For example, when the first video stream and the second video stream determine that the movement locus of the target object changes from straight on a wide road to turning into a narrow path, the security risk level of the target object is determined to be higher.
Optionally, the security risk level may be determined according to the action score of the target object, the environment score of the environment parameter, the pose score of the target object, and the respective corresponding risk factors. Optionally, the actions of the target object may be compared with preset actions in a risk database, and each preset action has an associated risk score. And searching whether a preset action matched with the action of the target object exists in the risk database, if so, determining the risk score associated with the preset action as the action score of the target object, and if not, recording the action score of the target object as 0. For example, when the motion of the target object is "clenching the fist", the score of the motion corresponding to the motion is 60. Optionally, corresponding pose scores also exist for different poses, corresponding environment scores also exist for different environment parameters, corresponding risk factors exist for different types of scores, and the risk factors can be set according to actual conditions.
Optionally, after the pose score, the environment score and the action score are determined, a total score can be determined according to the scores and the risk factors corresponding to the scores, and a corresponding security risk level can be determined according to a section of the total score, wherein each total score section has a corresponding security risk level, and can be determined according to actual conditions. Assuming that the pose score, the environment score and the action score are 30, 50 and 20 in sequence, and the risk factors corresponding to the three dimensions of the pose, the environment and the action are 0.2, 0.4 and 0.4 respectively, the determined total score is: 30, 0.2, 50, 0.4, 20, 0.4, 34 points, from which the corresponding security risk rating can be determined.
And step S160, determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level.
In this embodiment, after determining the behavior prediction result and/or the security risk level associated with the target object, optionally, the security processing scheme may be determined or generated according to the behavior prediction result of the target object. Optionally, a security processing scheme may also be determined or generated according to the security risk level. Optionally, the corresponding security processing scheme may be determined or generated according to different security risk levels. Optionally, when the security risk level is less than the preset risk level, alarm information may be generated based on the security risk level, and the alarm information is sent to the monitoring terminal, so that the monitoring terminal executes a corresponding security processing scheme. Optionally, when the security risk level is greater than or equal to the preset risk level, an alarm function is started. Optionally, a security processing scheme can be determined or generated according to the security risk level and the behavior prediction result. For example, when the behavior prediction result indicates that the running direction of the target object turns left or right, the determined security processing scheme is to generate first alarm information and send the first alarm information to the monitoring terminal for prompting. And when the behavior prediction result is that the running direction of the target object is fast running and the security risk level is the second level, generating second alarm information by the determined security processing scheme, and sending the alarm information to the monitoring terminal to prompt that security needs to be carried out. According to the method and the device, the corresponding alarm function or alarm function can be generated according to the security risk level, so that timely response and security can be carried out, and the safety management in the region is improved.
According to the technical scheme, the first video stream acquired by the first monitoring device is acquired, the target object detection is carried out based on the first video stream, when the target object is detected in the first video stream, the motion track of the target object is determined according to the first video stream, the target security area is determined according to the motion track, the second monitoring device in the dormant state is determined in other monitoring devices except the first monitoring device according to the target security area, the second monitoring device is started, the second monitoring device is adopted to acquire the second video stream, the behavior prediction result and/or the security risk level associated with the target object are determined according to the first video stream and the second video, the security processing scheme is determined or generated according to the behavior prediction result and/or the security risk level, the behavior prediction result and/or the security processing scheme of the target object which need to be started in the dormant state are determined according to the motion track of the target object, the behavior prediction result and/or the security processing scheme is determined in real time, the security processing scheme is determined, and the security processing loss of the target object is reduced, and the security processing problem is solved.
It should be noted that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be performed in an order different from that shown or described herein.
As shown in fig. 4, the present application provides a security system, which includes:
the system comprises an acquisition module 10, a target object detection module and a target object detection module, wherein the acquisition module is used for acquiring a first video stream acquired by a first monitoring device and detecting a target object based on the first video stream;
a first determining module 20, configured to determine, when the target object is detected in the first video stream, a motion trajectory of the target object according to the first video stream;
a second determining module 30, configured to determine a target security area according to the motion trajectory, and determine a second monitoring device according to the target security area, where the second monitoring device is a monitoring device in a dormant state in the target security area and other monitoring devices except the first monitoring device;
a starting module 40, configured to start the second monitoring apparatus and obtain a second video stream acquired by the second monitoring apparatus;
a third determining module 50, configured to determine a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream;
a fourth determining module 60, configured to determine or generate a security processing scheme according to the behavior prediction result and/or the security risk level.
Optionally, the second determining module 30 is further configured to determine a starting position and a current position of the target object according to the motion trajectory of the target object, where the starting position of the target object is a position of a starting point of the motion trajectory; determining the slope of the motion trail according to the starting position and the current position; when the slope is larger than or smaller than a preset value, determining a first security area as the target security area, and determining the second monitoring device according to the environmental parameters in the target security area; or when the slope is equal to a preset value, determining a second security area as the target security area, and determining the second monitoring device according to the movement speed of the target object in the target security area, which is detected by the first monitoring device, wherein the first security area is larger than the second security area.
Optionally, the second determining module 30 is further configured to obtain ambient brightness and ambient noise in the target security area; determining an environment brightness interval where the environment brightness is located and determining an environment noise interval where the environment noise is located; acquiring a monitoring device serial number associated with the environment brightness interval and acquiring a monitoring device serial number associated with the environment noise interval; determining the accumulated association times of the serial numbers of the monitoring devices; determining the second monitoring device based on the accumulated association times.
Optionally, the second determining module 30 is further configured to determine, according to the first video stream, a first monitoring position corresponding to the target object at a first monitoring time and a second monitoring position corresponding to the target object at a second monitoring time, where the second monitoring time is a next time of the first monitoring time; determining the movement speed of the target object according to the first monitoring time, the first monitoring position, the second monitoring time and the second monitoring position; when the movement speed is lower than a preset speed, determining a monitoring device closest to the first monitoring device as a second monitoring device; and when the movement speed is greater than or equal to the preset speed, determining the monitoring device in the target security area as the second monitoring device.
Optionally, the second determining module 30 is further configured to determine, when the slope is updated from being greater than the preset value to being equal to the preset value, or when the slope is updated from being smaller than the preset value to being equal to the preset value, the turn-on time of each of the second monitoring devices in the first security area and the second security area; and sequentially starting each second monitoring device based on the starting time.
Optionally, the third determining module 50 is further configured to perform contrast enhancement processing and color rectification processing on the first video stream and the second video stream; identifying the pose of the target object and the action of the target object in the first video stream and the second video stream after the contrast enhancement and the color correction processing; and determining a behavior prediction result and/or a security risk level associated with the target object according to the pose of the target object, the action of the target object and the environmental parameters in the target security area.
Optionally, the third determining module 50 is further configured to compare the action of the target object with a preset action in a risk database; when a preset action matched with the action of the target object exists in the risk database, determining a risk score associated with the preset action as an action score of the target object; determining a pose score of the target object and an environment score of the environmental parameter; acquiring risk factors corresponding to the action scores, the pose scores and the environment scores respectively; and determining the security risk level according to the action score, the pose score, the environment score and the corresponding risk factors.
Optionally, the fourth determining module 60 is further configured to generate alarm information based on the security risk level when the security risk level is smaller than a preset risk level, and send the alarm information to the monitoring terminal, so that the monitoring terminal executes a corresponding security processing scheme; and when the security risk level is greater than or equal to the preset risk level, starting an alarm function.
The specific implementation of the security system of the present invention is substantially the same as the embodiments of the security method described above, and will not be described herein again.
Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, where a security program is stored, and when the security program is executed by a processor, the security program implements the steps of the security method described above, and can achieve the same technical effects, and in order to avoid repetition, the details are not repeated here.
Since the storage medium provided in the embodiments of the present application is a storage medium used for implementing the method in the embodiments of the present application, based on the method described in the embodiments of the present application, a person skilled in the art can understand a specific structure and a modification of the storage medium, and thus details are not described here. Any storage medium used in the methods of the embodiments of the present application is intended to be within the scope of the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A security method, comprising:
acquiring a first video stream acquired by a first monitoring device, and detecting a target object based on the first video stream;
when the target object is detected in the first video stream, determining a motion track of the target object according to the first video stream;
determining the initial position and the current position of the target object according to the motion track of the target object, wherein the initial position of the target object is the position of the initial point of the motion track;
determining the slope of the motion trail according to the starting position and the current position;
when the slope is larger than or smaller than a preset value, determining a first security area as a target security area, acquiring environmental brightness and environmental noise in the target security area, determining an environmental brightness interval in which the environmental brightness is located and an environmental noise interval in which the environmental noise is located, acquiring a monitoring device serial number associated with the environmental brightness interval and a monitoring device serial number associated with the environmental noise interval, determining cumulative association times of the serial numbers of the monitoring devices, and determining starting time or starting sequence of a second monitoring device and each second monitoring device based on the cumulative association times; or when the slope is equal to a preset value, determining a second security area as the target security area, and determining the second monitoring device according to the movement speed of the target object in the target security area, which is detected by the first monitoring device; the first security area is larger than the second security area, and the second monitoring device is a monitoring device which is in a dormant state in other monitoring devices except the first monitoring device in the target security area;
starting the second monitoring device and acquiring a second video stream acquired by the second monitoring device;
determining a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream;
and determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level.
2. The security method of claim 1, wherein the step of determining the second monitoring device based on the speed of movement of the target object within the target security area detected by the first monitoring device comprises:
determining a first monitoring position corresponding to the target object at a first monitoring moment and a second monitoring position corresponding to the target object at a second monitoring moment according to the first video stream, wherein the second monitoring moment is the next moment of the first monitoring moment;
determining the movement speed of the target object according to the first monitoring moment, the first monitoring position, the second monitoring moment and the second monitoring position;
when the movement speed is lower than a preset speed, determining the monitoring device closest to the first monitoring device as a second monitoring device;
and when the movement speed is greater than or equal to the preset speed, determining the monitoring device in the target security area as the second monitoring device.
3. The security method of claim 1, wherein the step of determining the slope of the motion trajectory from the starting position and the current position is followed by:
when the slope is updated to be equal to the preset value from being larger than the preset value, or when the slope is updated to be equal to the preset value from being smaller than the preset value, determining the starting time of each second monitoring device in the first security area and the second security area;
and sequentially starting each second monitoring device based on the starting time.
4. The security method of claim 1, wherein the step of determining a behavioral prediction result and/or a security risk level associated with the target object from the first video stream and the second video stream comprises:
performing contrast enhancement processing and color correction processing on the first video stream and the second video stream;
an act of identifying the pose of the target object and the action of the target object in the first video stream and the second video stream after the contrast enhancement and the color correction processing;
and determining a behavior prediction result and/or a security risk level associated with the target object according to the pose of the target object, the action of the target object and the environmental parameters in the target security area.
5. The security method of claim 4, wherein determining the security risk level associated with the target object as a function of the pose of the target object, the motion of the target object, and the environmental parameters comprises:
comparing the action of the target object with a preset action in a risk database;
when a preset action matched with the action of the target object exists in the risk database, determining a risk score associated with the preset action as an action score of the target object;
determining a pose score of the target object and an environment score of the environmental parameter;
acquiring risk factors corresponding to the action scores, the pose scores and the environment scores respectively;
and determining the security risk level according to the action score, the pose score, the environment score and the corresponding risk factors.
6. The security method of claim 1, wherein the determining or generating a security treatment plan according to the security risk level comprises:
when the security risk level is smaller than a preset risk level, generating alarm information based on the security risk level, and sending the alarm information to a monitoring terminal so that the monitoring terminal executes a corresponding security processing scheme;
and when the security risk level is greater than or equal to the preset risk level, starting an alarm function.
7. A security system, comprising:
the acquisition module is used for acquiring a first video stream acquired by a first monitoring device and detecting a target object based on the first video stream;
the first determining module is used for determining the motion trail of the target object according to the first video stream when the target object is detected in the first video stream;
the second determining module is used for determining the initial position and the current position of the target object according to the motion track of the target object, wherein the initial position of the target object is the position of the initial point of the motion track; determining the slope of the motion trail according to the starting position and the current position; when the slope is larger than or smaller than a preset value, determining a first security area as a target security area, acquiring the ambient brightness and the ambient noise in the target security area, determining an ambient brightness interval where the ambient brightness is located, determining an ambient noise interval where the ambient noise is located, acquiring a monitoring device serial number associated with the ambient brightness interval, acquiring a monitoring device serial number associated with the ambient noise interval, determining the cumulative association times of the serial numbers of the monitoring devices, and determining a second monitoring device based on the cumulative association times; or when the slope is equal to a preset value, determining a second security area as the target security area, and determining the second monitoring device according to the movement speed of the target object in the target security area, which is detected by the first monitoring device; the first security area is larger than the second security area, and the second monitoring device is a monitoring device which is in a dormant state in other monitoring devices except the first monitoring device in the target security area;
the starting module is used for starting the second monitoring device and acquiring a second video stream acquired by the second monitoring device;
a third determining module, configured to determine a behavior prediction result and/or a security risk level associated with the target object according to the first video stream and the second video stream;
and the fourth determining module is used for determining or generating a security processing scheme according to the behavior prediction result and/or the security risk level.
8. A computer-readable storage medium, characterized in that it stores a security program which, when executed by a processor, implements the steps of the security method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210978161.2A CN115052110B (en) | 2022-08-16 | 2022-08-16 | Security method, security system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210978161.2A CN115052110B (en) | 2022-08-16 | 2022-08-16 | Security method, security system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115052110A CN115052110A (en) | 2022-09-13 |
| CN115052110B true CN115052110B (en) | 2022-11-18 |
Family
ID=83167882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210978161.2A Active CN115052110B (en) | 2022-08-16 | 2022-08-16 | Security method, security system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115052110B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101207638A (en) * | 2007-12-03 | 2008-06-25 | 浙江树人大学 | Method for tracking target based on prognostic wireless sensor network |
| CN104079885A (en) * | 2014-07-07 | 2014-10-01 | 广州美电贝尔电业科技有限公司 | Nobody-monitored and linkage-tracked network camera shooting method and device |
| CN106709436A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Cross-camera suspicious pedestrian target tracking system for rail transit panoramic monitoring |
| CN109040709A (en) * | 2018-09-21 | 2018-12-18 | 深圳市九洲电器有限公司 | Video monitoring method and device, monitoring server and video monitoring system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6465600B2 (en) * | 2014-09-19 | 2019-02-06 | キヤノン株式会社 | Video processing apparatus and video processing method |
-
2022
- 2022-08-16 CN CN202210978161.2A patent/CN115052110B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101207638A (en) * | 2007-12-03 | 2008-06-25 | 浙江树人大学 | Method for tracking target based on prognostic wireless sensor network |
| CN104079885A (en) * | 2014-07-07 | 2014-10-01 | 广州美电贝尔电业科技有限公司 | Nobody-monitored and linkage-tracked network camera shooting method and device |
| CN106709436A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Cross-camera suspicious pedestrian target tracking system for rail transit panoramic monitoring |
| CN109040709A (en) * | 2018-09-21 | 2018-12-18 | 深圳市九洲电器有限公司 | Video monitoring method and device, monitoring server and video monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115052110A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10868712B1 (en) | Cooperative monitoring networks | |
| US10460456B2 (en) | Motion detection of object | |
| US9948902B1 (en) | Video camera and sensor integration | |
| AU2019295856B2 (en) | Object tracking using disparate monitoring systems | |
| RU2670429C1 (en) | Systems and methods of tracking moving objects on video image | |
| US20170053504A1 (en) | Motion detection system based on user feedback | |
| CN110032966B (en) | Human body proximity detection method for intelligent service, intelligent service method and device | |
| CN102855716A (en) | Doorbell system and automatic visitor identification method thereof | |
| US10791420B2 (en) | Information processing device and information processing method | |
| CN112365522A (en) | Method for tracking personnel in park across borders | |
| US20100002083A1 (en) | Moving object automatic tracking apparatus | |
| KR20200080402A (en) | System and method for detecting abnormal situation | |
| CN110246241A (en) | A kind of gate control method and device | |
| CN112733690A (en) | High-altitude parabolic detection method and device and electronic equipment | |
| KR101630286B1 (en) | Apparatus for separating foreground from background and method thereof | |
| JP2011123742A (en) | Intruding object detector | |
| CN100589135C (en) | Automatic door bell and its implementation | |
| CN112394647B (en) | Control method, device, equipment and storage medium of household equipment | |
| CN115346060A (en) | Picture abnormity identification method and device, electronic equipment and storage medium | |
| CN115052110B (en) | Security method, security system and computer readable storage medium | |
| CN111563989B (en) | Intelligent control method of gate, gate and computer readable storage medium | |
| CN113936293A (en) | Video information-based off-duty personnel detection method, control device and storage medium | |
| CN116866711A (en) | Energy-saving monitoring method, system, equipment and storage medium | |
| CN112580522A (en) | Method, device and equipment for detecting sleeper and storage medium | |
| JP6784254B2 (en) | Retained object detection system, retained object detection method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |