CN106919892A - Behavior monitoring method and device - Google Patents

Abstract

The invention discloses a behavior monitoring method and device. The method includes: when it is determined that the first sensor arranged in the first space detects the movement of the object to be monitored, triggering the second sensor to monitor the behavior of the first sensor in the first space. A parameter is detected, and the detection result of the first parameter is obtained; the detection result of the first parameter obtained within a time period not less than the first set duration is compared with the reference detection result, and when the comparison result When the characterization fit reaches a set threshold, it is determined that the first behavior of the object to be monitored occurs; when it is determined that the duration of the first behavior of the object to be monitored occurs longer than a second set duration, an alarm message is output.

Description

Behavior monitoring method and device

technical field

The invention relates to behavior monitoring technology, in particular to a behavior monitoring method and device.

Background technique

Existing human behavior recognition technologies are mostly implemented based on video surveillance technology. Data are collected through video equipment and image processing algorithms are used to analyze the data to identify user behavior. Recognizing user behavior through video will lead to insufficient protection of user privacy, complex image processing algorithms, and high hardware costs. To achieve detailed behavior recognition, a large number of video surveillance equipment needs to be deployed, and the recognition accuracy of video recognition user behavior is low. , the validity of the recognition result is easily affected by the structure of the house and the light in the house.

In view of the above shortcomings, it is difficult to carry out large-scale promotion of video surveillance technology in the application of real human behavior recognition.

Contents of the invention

In order to solve the above technical problems, embodiments of the present invention provide a behavior monitoring method and device.

A behavioral monitoring method, said method comprising:

When it is determined that the first sensor arranged in the first space detects the movement of the object to be monitored, trigger the second sensor to detect the first parameter in the first space, and obtain the detection result of the first parameter;

comparing the detection result of the first parameter obtained within a time period not less than the first set duration with the reference detection result, and when the comparison result indicates that the degree of fit reaches a set threshold, determine that the to-be-monitored The object's first behavior occurs;

When it is determined that the occurrence time of the first behavior of the object to be monitored is longer than the second set time, an alarm message is output.

In an embodiment of the present invention, the method further includes:

During the time period not less than the first set duration, when it is determined that the first sensor disposed in the second space detects the movement of the object to be monitored, it is determined that the object to be monitored does not have the first behavior, so that the The second sensor stops detecting work.

In an embodiment of the present invention, the method further includes:

When the degree of fit of the comparison result does not reach the set threshold, continue to obtain the detection result of the first parameter, and continue to detect the first parameter obtained within a time period not less than the first set duration The result is compared with the reference detection result, but the comparison result shows that the fitting degree has not reached the set threshold, and it is determined that the first sensor installed in other spaces has never detected the movement of the object to be monitored, and the duration is longer than the third sensor. When the duration is set, an alarm message will be output.

In an embodiment of the present invention, the method further includes:

In the set period, when the first behavior of the object to be monitored occurs, triggering the second sensor to detect the first parameter in the first space;

Using the detection result of the first parameter in the set period as a training sample, using the least squares algorithm in the supervised learning algorithm to fit the detection result of the first parameter in the set period to obtain the to-be Monitoring the trend information of the first parameter changing over time in the first space during the occurrence of the first behavior of the object, and using the trend information changing over time of the first parameter as the reference detection result.

In an embodiment of the present invention, the first sensor includes a passive infrared PIR sensor;

The second sensor includes a humidity sensor.

A behavior monitoring device, the device comprising: a first determination unit, a trigger unit, an acquisition unit, a comparison unit, a judgment unit and an output unit, wherein:

The first determination unit is configured to determine whether the first sensor arranged in the first space detects the movement of the object to be monitored, and triggers the trigger unit when the movement of the object to be monitored is detected;

a trigger unit, configured to trigger the second sensor to detect the first parameter in the first space;

an acquisition unit, configured to acquire a detection result of the first parameter of the second sensor;

A comparison unit, configured to compare the detection result of the first parameter acquired within a time period not less than the first set duration with the reference detection result, and when the comparison result indicates that the degree of fit reaches the set threshold, determining that the first behavior of the subject to be monitored occurs;

A judging unit, configured to judge whether the duration of the first behavior of the object to be monitored is greater than a second set duration, and trigger the output unit when greater than the second set duration;

The output unit is used to output alarm information.

In the embodiment of the present invention, the device further includes: a second determining unit and a stopping unit, wherein:

The second determination unit is configured to determine that the object to be monitored is not detected when the first sensor disposed in the second space detects the movement of the object to be monitored within the time period not less than the first set duration. A first behavior occurs, triggering the stopping unit;

a stop unit, configured to stop the detection work of the second sensor.

In the embodiment of the present invention, the device further includes: a third determining unit;

When the comparison result of the comparison unit indicates that the fitting degree does not reach the set threshold, continue to trigger the acquisition unit to obtain the detection result of the first parameter, and continue to trigger the comparison unit to set the first parameter to be no less than the first parameter. The detection result of the first parameter acquired within the time period of the set duration is compared with the reference detection result, and the comparison result indicates that the degree of fit has never reached the set threshold, and the setting is determined by the third determining unit The first sensor in other spaces never detects the movement of the object to be monitored, and when the duration is longer than a third set duration, the output unit is triggered to output an alarm message.

In an embodiment of the present invention, the device further includes:

The training unit is configured to trigger the second sensor to detect the first parameter in the first space when the first behavior of the object to be monitored occurs within the set period; The detection result of the first parameter is used as a training sample, and the least square product algorithm in the supervised learning algorithm is used to fit the detection result of the first parameter in the set period to obtain the occurrence process of the first behavior of the object to be monitored. The time-varying trend information of the first parameter in the first space is used as the reference detection result.

In an embodiment of the present invention, the first sensor includes a passive infrared PIR sensor;

The second sensor includes a humidity sensor.

In the behavior monitoring method and device provided by the embodiments of the present invention, the object to be monitored is detected by a PIR sensor to determine whether the object to be monitored is located in the set space, and when it is detected that the object to be monitored is located in the set space, other sensors are turned on The behavior of the object to be monitored is detected. When a behavior of the object to be monitored is detected, the duration of the behavior is detected. When the set threshold is exceeded, the corresponding alarm information is output. Corresponding alarm information can be output to specific objects, such as users related to the object to be monitored. The technical solution of the embodiment of the present invention uses a non-intrusive method to identify the behavior of the object to be monitored, protects the privacy of the object to be monitored, and uses sensors to detect the behavior of the object to be monitored, which reduces the difficulty of recognition algorithms and system deployment costs, and improves recognition reliability.

Description of drawings

FIG. 1 is a schematic flow diagram of a behavior monitoring method according to Embodiment 1 of the present invention;

2 is a schematic structural diagram of a behavior monitoring system according to an embodiment of the present invention;

3 is a schematic flow diagram of a behavior monitoring method according to Embodiment 2 of the present invention;

4 is a schematic diagram of statistical results of behavioral parameters of an object to be monitored according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of the structure and composition of the behavior monitoring device according to the embodiment of the present invention.

detailed description

In order to understand the characteristics and technical contents of the embodiments of the present invention in more detail, the implementation of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present invention.

Fig. 1 is a schematic flow diagram of a behavior monitoring method in Embodiment 1 of the present invention. As shown in Fig. 1, the behavior monitoring method in this example includes the following steps:

Step 101: When it is determined that the first sensor installed in the first space detects the movement of the object to be monitored, trigger the second sensor to detect the first parameter in the first space, and obtain the detection result of the first parameter .

In the embodiment of the present invention, the first sensor includes a passive infrared (PIR, Passive InfraRed) sensor and the like; the second sensor includes a humidity sensor and the like.

The first space may include a toilet, a bathroom, and the like. The objects to be monitored include the elderly and patients with limited mobility. Since the object to be monitored is inconvenient to move, it is necessary to monitor its behavior in a specific space to avoid accidents. Since the space to be monitored is generally a private place, if a camera or other methods are used to monitor, the privacy of the object to be monitored will not be effectively guaranteed. Therefore, in the embodiment of the present invention, the monitoring of the object to be monitored is realized by setting sensors.

In the embodiment of the present invention, when it is detected that the object to be monitored enters the bathroom or toilet, the humidity sensor is turned on to detect the object to be monitored. When it is detected that the object to be monitored is taking a bath, the bathing time of the object to be monitored will be detected. When the bathing time of the object to be monitored exceeds the set threshold, an alarm message will be output.

Step 102: Compare the detection result of the first parameter acquired within a time period not less than the first set duration with the reference detection result, and when the fit of the comparison result reaches the set threshold, determine the The first behavior of the object to be monitored occurs.

In the embodiment of the present invention, the detection result of the first parameter obtained by the second sensor, in order to ensure the accuracy of the behavior detection of the object to be monitored, it is necessary to obtain the detection result of the first parameter within a period of time, and the detection result of the first parameter within a period of time The detection result of the first parameter is compared with the reference detection result, and when the matching degree of the comparison result reaches a set threshold, it is determined that the relevant behavior of the object to be monitored occurs. For example, after it is determined that the user enters the bathroom, the humidity sensor data collected within a few minutes is fitted with the previous reference data. When the correlation coefficient R ² >70%, it is determined that the user is taking a bath. When the correlation coefficient R ² <70%, it is determined that the user is not taking a shower. In the embodiment of the present invention, the set threshold may be set according to the actual situation, and may also be set to 60%, 65%, 75%, 80%, 85% and so on.

In the embodiment of the present invention, when it is determined that the first sensor installed in the second space detects the movement of the object to be monitored within the time period not less than the first set duration, it is determined that the object to be monitored has not occurred. The first behavior is to stop the detection work of the second sensor. When it is determined that the object to be monitored is not taking a bath and waiting for the monitoring behavior, it is necessary to turn off the detection equipment of relevant parameters such as the depth sensor.

In the set period, when the first behavior of the object to be monitored occurs, triggering the second sensor to detect the first parameter in the first space;

Using the detection result of the first parameter in the set period as a training sample, using the least squares algorithm in the supervised learning algorithm to fit the detection result of the first parameter in the set period to obtain the to-be Monitoring the trend information of the first parameter changing over time in the first space during the occurrence of the first behavior of the object, and using the trend information changing over time of the first parameter as the reference detection result. In the embodiment of the present invention, the first parameter generated by the behavior of the object to be monitored is counted to form training data, so as to obtain the accuracy of the reference detection result of the object to be monitored as much as possible, so as to accurately determine whether the object to be monitored has occurred the behavior to be monitored .

Step 103: When it is determined that the occurrence time of the first behavior of the object to be monitored is longer than the second set time, an alarm message is output.

In the embodiment of the present invention, when it is determined that the first behavior of the object to be monitored takes place for a long time and exceeds an unreasonable time period, an alarm message will be output. The alarm information can be directly output, and can also be sent to a third party such as 999 center, the guardian of the object to be monitored, etc.

In an embodiment of the present invention, the method further includes:

When the degree of fit of the comparison result does not reach the set threshold, continue to obtain the detection result of the first parameter, and continue to detect the first parameter obtained within a time period not less than the first set duration The result is compared with the reference detection result, but the comparison result shows that the fitting degree has not reached the set threshold, and it is determined that the first sensor installed in other spaces has never detected the movement of the object to be monitored, and the duration is longer than the third sensor. When the duration is set, an alarm message will be output. That is, when the object to be monitored enters the first space, but the behavior to be detected does not occur, and the duration of the object to be monitored stays in the first space exceeds an unreasonable length of time, an alarm message will also be output.

The essence of the technical solution of the embodiment of the present invention is further clarified through examples below.

Fig. 2 is the structural representation of the behavior monitoring system of the embodiment of the present invention, as shown in Fig. 2, comprise humidity sensor, PIR sensor, processing terminal, memory, application server and warning output object such as PC in the behavior monitoring system of the embodiment of the present invention , mobile client or 999 center, etc. The embodiment of the present invention is only described with the structure shown in FIG. 2 , which is not intended to limit the protection scope of the present invention. In the embodiment of the present invention, whether the user takes a bath is used as the monitoring behavior to determine whether the user's behavior exceeds an unreasonable time period. The function description of each component in the behavior monitoring system of the embodiment of the present invention is as follows:

Humidity sensor for measuring the relative humidity in the air. For example, the humidity sensor can be installed in the bathroom or toilet.

PIR sensor, a passive infrared detector, can detect whether the human body is active. Through the PIR sensor, it can monitor whether the user has entered the corresponding monitoring area.

Process the terminal, collect sensor data and transmit the data to the storage server and application server. In the embodiment of the present invention, the storage may also be a storage server, or a storage device installed in the processing terminal, or the like. The storage device is used to store the historical data of each monitoring sensor and the bathing start time, end time and bathing duration transmitted by the application server, and transmit the historical data to the application server for the basis of bathing abnormality judgment. The application server is used to determine whether the monitored object is taking a bath according to the sensor data, and set an alarm threshold for excessive bathing time by mining historical data. If the user takes a bath overtime, the user's guardian and the like are notified of abnormal bathing information. The PC or mobile phone client is used to receive the bathing information and abnormal information sent by the application server and notify the user.

Fig. 3 is a schematic flow chart of the behavior monitoring method of Embodiment 2 of the present invention. As shown in Fig. 3, the behavior monitoring method of this example includes the following processing steps:

Detect whether the PIR sensor in the bathroom has a signal jump event from no one to someone.

If there is a signal jump event from no-occupancy to occupancy, the data of the humidity sensor in the bathroom is collected and stored.

During the data collection process of the humidity sensor, if there is a PIR signal mutation event in other rooms of the house, it is determined that the user has left the bathroom and has not taken a bath.

In the embodiment of the present invention, the behavior monitoring of the elderly or patients living alone is generally performed, and when there are many people in the room, the user behavior needs to be monitored.

During the data collection process of the humidity sensor, if there is no PIR signal mutation event in other rooms of the house, it is determined that the user is still in the bathroom and has not left.

The value of the humidity sensor during the bathing process of the user for 30 days is collected as a training sample for machine learning, and the least square product algorithm in the supervised learning algorithm is used to fit the data to obtain the trend graph and equation of the bathroom humidity changing with time during the bathing process, as shown in Figure 4 shows.

When it is determined that the user has entered the bathroom, the humidity sensor data collected within a few minutes is fitted with the previously learned model, and the fitting results are checked. When the correlation coefficient R ² >70%, it is determined that the user is taking a bath. When the correlation coefficient R ² <70%, it is determined that the user is not taking a shower.

When the user is taking a bath, when the PIR sensor in the bathroom changes from someone to no one, if the PIR sensor in other rooms of the house changes from no one to someone, it is determined that the user's bathing is over.

Count the bathing time of each user for 30 days, perform normal distribution fitting, and select a confidence interval of 95%, so as to set the alarm threshold for bathing timeout.

In the embodiment of the present invention, when it is determined that the user does not take a bath, and the time he stays in the bathroom is unreasonably long, such as staying in the bathroom for 15 minutes without taking a bath, an alarm message is also output to facilitate the guardian of the user to be monitored. Take corresponding measures in time to prevent accidents in the objects to be monitored.

Figure 5 is a schematic diagram of the structure of the behavior monitoring device of the embodiment of the present invention, as shown in Figure 5, the behavior monitoring device of the embodiment of the present invention includes: a first determination unit 50, a trigger unit 51, an acquisition unit 52, a comparison unit 53, Judging unit 54 and output unit 55, wherein:

The first determination unit 50 is configured to determine whether the first sensor arranged in the first space detects the movement of the object to be monitored, and triggers the trigger unit 51 when the movement of the object to be monitored is detected;

a trigger unit 51, configured to trigger the second sensor to detect the first parameter in the first space;

An acquisition unit 52, configured to acquire a detection result of the first parameter of the second sensor;

The comparison unit 53 is configured to compare the detection result of the first parameter obtained within a time period not less than the first set duration with the reference detection result, and when the comparison result indicates that the fitting degree reaches the set threshold , determining that the first behavior of the object to be monitored occurs;

A judging unit 54, configured to judge whether the duration of occurrence of the first behavior of the object to be monitored is greater than a second set duration, and trigger the output unit when greater than the second set duration;

The output unit 55 is configured to output alarm information.

On the basis of the behavior monitoring device shown in Figure 5, the behavior monitoring device of the embodiment of the present invention also includes: a second determination unit (not shown in Figure 5) and a stop unit (not shown in Figure 5), wherein:

The second determination unit is configured to determine that the object to be monitored is not detected when the first sensor disposed in the second space detects the movement of the object to be monitored within the time period not less than the first set duration. A first behavior occurs, triggering the stopping unit;

a stop unit, configured to stop the detection work of the second sensor.

On the basis of the behavior monitoring device shown in Figure 5, the behavior monitoring device according to the embodiment of the present invention further includes: a third determining unit (not shown in Figure 5);

When the comparison result of the comparison unit 53 indicates that the degree of fit does not reach the set threshold, continue to trigger the acquisition unit 52 to obtain the detection result of the first parameter, and continue to trigger the comparison unit 53 to reduce the number of parameters. The detection result of the first parameter obtained within the first set time period is compared with the reference detection result, and the comparison result indicates that the degree of fit has not reached the set threshold, and through the third determination The unit determines that the first sensor arranged in another space has not detected the movement of the object to be monitored, and when the duration is longer than the third set time, the output unit 55 is triggered to output an alarm message.

On the basis of the behavior monitoring device shown in Figure 5, the behavior monitoring device of the embodiment of the present invention also includes: a training unit (not shown in Figure 5), used to When the first behavior occurs, the second sensor is triggered to detect the first parameter in the first space; the detection result of the first parameter in the set period is used as a training sample, and the least squares method in the supervised learning algorithm is used. The product algorithm is used to fit the detection results of the first parameter in the set period, and obtain the trend information of the first parameter in the first space in the first space during the occurrence of the first behavior of the object to be monitored. Taking the trend information of the first parameter over time as the reference detection result.

In an embodiment of the present invention, the first sensor includes a passive infrared PIR sensor;

The second sensor includes a humidity sensor.

Those skilled in the art should understand that the functions implemented by the above units can be understood with reference to the relevant descriptions of the behavior monitoring methods of the foregoing embodiments. The functions of the above units can be realized by programs running on the processing modules, or by specific logic circuits.

The technical solutions described in the embodiments of the present invention may be combined arbitrarily if there is no conflict.

In the several embodiments provided by the present invention, it should be understood that the disclosed methods and smart devices can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the mutual coupling, or direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms. of.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be fully integrated into a second processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention.

Claims (10)

1. A method of behavior monitoring, characterized in that the method comprises: When it is determined that the first sensor arranged in the first space detects the movement of the object to be monitored, trigger the second sensor to detect the first parameter in the first space, and obtain the detection result of the first parameter; comparing the detection result of the first parameter obtained within a time period not less than the first set duration with the reference detection result, and when the comparison result indicates that the degree of fit reaches a set threshold, determine that the to-be-monitored The object's first behavior occurs; When it is determined that the occurrence time of the first behavior of the object to be monitored is longer than the second set time, an alarm message is output. 2. the behavior monitoring method according to claim 1, is characterized in that, described method also comprises: During the time period not less than the first set duration, when it is determined that the first sensor disposed in the second space detects the movement of the object to be monitored, it is determined that the object to be monitored does not have the first behavior, so that the The second sensor stops detecting work. 3. The behavior monitoring method according to claim 1 or 2, wherein the method further comprises: When the degree of fit of the comparison result does not reach the set threshold, continue to obtain the detection result of the first parameter, and continue to detect the first parameter obtained within a time period not less than the first set duration The result is compared with the reference detection result, but the comparison result shows that the fitting degree has not reached the set threshold, and it is determined that the first sensor installed in other spaces has never detected the movement of the object to be monitored, and the duration is longer than the third sensor. When the duration is set, an alarm message will be output. 4. the behavior monitoring method according to claim 1, is characterized in that, described method also comprises: In the set period, when the first behavior of the object to be monitored occurs, triggering the second sensor to detect the first parameter in the first space; Using the detection result of the first parameter in the set period as a training sample, using the least squares algorithm in the supervised learning algorithm to fit the detection result of the first parameter in the set period to obtain the to-be Monitoring the trend information of the first parameter changing over time in the first space during the occurrence of the first behavior of the object, and using the trend information changing over time of the first parameter as the reference detection result. 5. The behavior monitoring method according to any one of claims 1 to 4, wherein the first sensor comprises a passive infrared PIR sensor; The second sensor includes a humidity sensor. 6. A behavior monitoring device, characterized in that the device comprises: a first determination unit, a trigger unit, an acquisition unit, a comparison unit, a judgment unit and an output unit, wherein: The first determination unit is configured to determine whether the first sensor arranged in the first space detects the movement of the object to be monitored, and triggers the trigger unit when the movement of the object to be monitored is detected; a trigger unit, configured to trigger the second sensor to detect the first parameter in the first space; an acquisition unit, configured to acquire a detection result of the first parameter of the second sensor; A comparison unit, configured to compare the detection result of the first parameter acquired within a time period not less than the first set duration with the reference detection result, and when the comparison result indicates that the degree of fit reaches the set threshold, determining that the first behavior of the subject to be monitored occurs; A judging unit, configured to judge whether the duration of the first behavior of the object to be monitored is greater than a second set duration, and trigger the output unit when greater than the second set duration; The output unit is used to output alarm information. 7. The behavior monitoring device according to claim 6, further comprising: a second determination unit and a stop unit, wherein: The second determination unit is configured to determine that the object to be monitored is not detected when the first sensor disposed in the second space detects the movement of the object to be monitored within the time period not less than the first set duration. A first behavior occurs, triggering the stopping unit; a stop unit, configured to stop the detection work of the second sensor. 8. The behavior monitoring device according to claim 6 or 7, characterized in that the device further comprises: a third determination unit; When the comparison result of the comparison unit indicates that the fitting degree does not reach the set threshold, continue to trigger the acquisition unit to obtain the detection result of the first parameter, and continue to trigger the comparison unit to set the first parameter to be no less than the first parameter. The detection result of the first parameter acquired within the time period of the set duration is compared with the reference detection result, and the comparison result indicates that the degree of fit has never reached the set threshold, and the setting is determined by the third determining unit The first sensor in other spaces never detects the movement of the object to be monitored, and when the duration is longer than a third set duration, the output unit is triggered to output an alarm message. 9. The behavior monitoring device according to claim 6, wherein the device further comprises: The training unit is configured to trigger the second sensor to detect the first parameter in the first space when the first behavior of the object to be monitored occurs within the set period; The detection result of the first parameter is used as a training sample, and the least square product algorithm in the supervised learning algorithm is used to fit the detection result of the first parameter in the set period to obtain the occurrence process of the first behavior of the object to be monitored. The time-varying trend information of the first parameter in the first space is used as the reference detection result. 10. The behavior monitoring device according to any one of claims 6 to 9, wherein the first sensor comprises a passive infrared PIR sensor; The second sensor includes a humidity sensor.