JP6381189B2 - Monitoring device - Google Patents

Description

  The present invention relates to a monitoring device that sets a monitoring range of a monitoring target.

  When it is desired to set the monitoring range of the monitoring target, it is required to easily set an appropriate monitoring range considering the behavior of the monitoring target.

  As a conventional technique for setting a region to be monitored with a light pen in a region displayed on a display device, there is a monitoring device disclosed in Patent Document 1. This device compares an image at a certain point in time with an intruding object in an area set with a light pen, and issues an alarm when there is a change in the image.

  Further, as a conventional technique for setting a monitoring range by installing a marker in a range to be monitored and detecting the marker from an image, there is an apparatus of Patent Document 2. This apparatus detects a marker from an image by installing a marker in an area captured by a surveillance camera. And this device determines the straight line with a certain interval parallel to the straight line that the marker constitutes from the information of the marker coordinates, the camera height, and the marker interval, and monitors the range surrounded by these Range.

JP 05-007363 A JP 2001-204007 A

  However, in the systems such as Patent Document 1 and Patent Document 2, the monitoring person must set the range to be originally monitored with a light pen or marker after analyzing the behavior pattern to be monitored. The load is large.

  An object of the present invention is to provide a monitoring apparatus that addresses such problems, acquires a flow line from an image, analyzes it, and sets a set of areas in which the flow line is detected at a predetermined frequency as a monitoring range.

Monitoring apparatus of the present invention includes an acquisition unit setting means for setting at least one or more lines as flow line acquisition condition, and based on the said flow line acquisition condition, acquires a flow line passing through the line, the dynamic analyze the lines, and analyzing means for flow line passing through said line to extract more sensed area than a predetermined number, extracted by the analyzing means, the flow line passing through the line is more than a predetermined number A setting unit configured to set a set of detected areas as a monitoring range, wherein the setting unit sets the monitoring range; a set of areas where more than a predetermined number of flow lines passing through the line are detected; If there is a change in, characterized in that issues an alarm.

Thereby, in the monitoring device of the present invention, it is possible to notify the monitor that there has been a change in the monitoring range, which is a set of areas in which flow lines are detected at a predetermined frequency .

It is a schematic diagram which shows an example of schematic structure of the system which concerns on Example 1 of this invention. It is a flowchart which shows an example of the process sequence which sets the monitoring range. It is a schematic diagram which shows an example of condition setting. It is a schematic diagram which shows an example of the acquired flow line. It is a schematic diagram which shows an example of the relationship between a flow line, the monitoring object, and an area | region. It is a schematic diagram which shows an example of the collection of the extracted area | region. It is a flowchart which shows an example of the process sequence which sets the monitoring range. It is a schematic diagram which shows an example of the relationship between the acquired flow line, monitoring object, and movement time. It is a schematic diagram which shows an example of schematic structure of the system which concerns on Example 2 of this invention. It is a flowchart which shows an example of the process sequence which sets the monitoring range. It is a schematic diagram which shows an example of condition setting. It is a schematic diagram which shows an example of the acquired flow line. It is a schematic diagram which shows an example of the relationship between a flow line, the monitoring object, and an area | region. It is a schematic diagram which shows an example of the collection of the extracted area | region.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The embodiment described below is an example of an implementation means of the present invention, and the present invention is also applied to a modified or modified embodiment described below without departing from the spirit of the invention.

  FIG. 1 is a schematic diagram illustrating an example of a schematic configuration of a monitoring apparatus according to the first embodiment of the present invention.

  As shown in FIG. 1, the monitoring apparatus according to the present embodiment includes a terminal 11. The monitoring apparatus includes a terminal 11 and includes condition setting means 115a, flow line acquisition means 115b, flow line analysis means 115c, and monitoring range setting means. The condition setting unit 115a sets a flow line acquisition condition, and the flow line acquisition unit 115b acquires a flow line based on the flow line acquisition condition. The flow line analyzing unit 115c analyzes the flow line and extracts a region where the flow line is detected at a predetermined frequency, and the monitoring range setting unit sets a set of the extracted regions as a monitoring range.

  The terminal 11 includes a control unit 111, a storage unit 112, a display unit 113, an input unit 114, a monitoring range setting unit 115, a RAM 116, and a ROM 117, and a bus 118 for connecting these elements.

  Video information captured by the imaging device is stored in the video information storage unit 112a. The monitoring target identification information storage unit 112c stores the identification information of the monitoring target. The monitoring target identification information may be information for manually registering information such as a number, name, and contact phone number assigned to identify the monitoring target. The identification information of the monitoring target may be information for automatically acquiring and registering the face and shape of the monitoring target. The flow line information storage unit (storage unit) 112c stores the flow line information to be monitored acquired from the video information. The monitoring range information storage unit (storage unit) 112d stores monitoring range information for each monitoring target.

  The display unit 113 displays video data monitored by the monitor. The input unit 114 is an input device such as a mouse or a keyboard.

  The condition setting unit 115 a is a unit that sets a start line, an end line, and the like for acquiring a flow line using the input unit 114. In addition to setting the start line and the end line, the flow line acquisition condition is such that one or a plurality of lines passing during movement are set and a flow line passing through the one or more lines is acquired. Good.

  The flow line acquisition unit 115b acquires a flow line that matches the set condition, and records the flow line information in the storage unit 112c. The flow line analysis means 115c divides the video into an arbitrary number of divisions, gives an identifier for each area, and determines whether or not the flow lines obtained by the flow line acquisition means 115b appear more frequently than a predetermined frequency in the area. analyse. Then, the flow line analyzing unit 115c records, in the storage unit 112c, the identifier of the area determined to appear more frequently than the predetermined frequency.

  The monitoring range setting means 115d records the set of areas obtained as a result of the flow line analysis means 115c as the monitoring range in association with the area identifier and the monitoring target identification information in the storage unit 112d. That is, the flow line analyzing unit 115c analyzes the flow line and extracts a region where the flow line is detected at a predetermined frequency. The monitoring range setting unit 115d sets a set of extracted areas as a monitoring range.

  In addition, the RAM 116 is a semiconductor memory that can be read and written by designating an arbitrary address, and an application program for the terminal 11 is installed. Data necessary for processing in the terminal 11 is temporarily stored and output to the bus 118 as necessary. The ROM 117 is a read-only memory that stores a control program necessary for processing in the control unit 111, reads a necessary program at a predetermined timing, and outputs it to the bus 118. The control unit 111 performs arithmetic processing by itself based on an application program stored in the RAM 116 or controls each component described above to cause the terminal 11 to function.

  Next, the procedure for setting the monitoring range in this embodiment will be described with reference to FIG. Here, in this embodiment, a care system is taken as an example, and one cared person is described as a monitoring target. FIG. 2 is a flowchart showing an operation when the control unit 111 is configured by a CPU that is a computer and a program executed thereon. The ROM 117 is a storage medium that stores this program so that the CPU can read it out. This CPU reads the program from the ROM 117 and executes the processing shown in FIG. Each step of FIG. 2 shows a procedure that the program causes the CPU to execute.

  Step S301 is processing of the condition setting unit 115a, and sets a start line and an end line for acquiring a flow line as shown in FIG.

  The subsequent step S302 is processing of the flow line acquisition means 115b, acquires a flow line that matches the conditions set in S301 as shown in FIG. 4A, and uses the acquired flow line information as monitoring target identification information. Correlate and record in the storage unit 112c. In the case of FIG. 4, seven flow lines are acquired, the flow line ID is 1 to 7, and the monitoring target ID of the monitoring target is 1 for any flow line. When the start line and the end line in FIG. 3 are set, it is determined that the flow line that passes through the start line and then passes through the end line matches the condition.

  The next steps S303 to S307 are processing of the flow line analyzing means 115c. In S303, the video is divided into arbitrary division numbers as shown in FIG. 4B, and an identifier is given for each area. Steps S304, S305, S306, and S307 are steps for analyzing the number of flow lines that appear for each of the divided areas. If there are more than a predetermined number of flow lines that appear, they are associated with the identifier of the area. As shown in FIG. In this example, since seven flow lines are detected, it is determined that there are more than a predetermined number of flow lines that have appeared. FIG. 5 shows that the flow line with the flow line ID 1 has passed through the areas with the area IDs 29, 43, 57, 71,.

  Step S308 is processing of the monitoring range setting unit 115d, and extracts a region where a flow line is detected at a predetermined frequency as shown in FIG. 6 from the result of the flow line analysis unit 115c. Then, the set of the extracted areas is set as a monitoring range, and the area identifier and monitoring target identification information are associated with each other and recorded in the storage unit 112d. In the present embodiment, the areas of area IDs 30, 31, 32,..., 124 through which two or more flow lines have passed are stored in the storage unit 112d as a monitoring range. Note that a region where a flow line is detected even once may be a monitoring range.

  The monitoring range ID of this monitoring range is 1, and the monitoring target ID of the care recipient to be monitored is 1. Further, the flow line analyzing unit 115c may analyze the flow line and extract a region where the flow line is detected with a predetermined frequency, and the monitoring range setting unit 115d may set a set of the extracted regions as a monitoring range. . The flow line analysis unit 115c divides the video into regions having an arbitrary number of divisions, and analyzes whether or not a flow line is generated at a predetermined frequency for each region.

  With the above processing, it is possible to extract a region having a high appearance frequency from the flow line to be monitored, and set a set of the extracted regions as a monitoring range of the monitoring target. The above processing is repeated for the monitoring target for which the monitoring range is set, and when there is a difference in the monitoring range, the monitoring range may be updated or a warning may be issued to the monitor. That is, the monitoring range setting unit 115d updates the monitoring range when the monitoring range is changed for the monitoring target for which the monitoring range is set. In addition, the monitoring range setting unit 115d issues an alarm when the monitoring range is changed with respect to the monitoring target for which the monitoring range is set. This embodiment can be applied to the case where it is desired to acquire the walking speed only when the monitoring target moves in the monitoring range and to grasp the health condition of the monitoring target.

  Next, Example 2 shows an example in which the flow line acquisition unit acquires the moving time of the monitoring target from the flow line.

  The monitoring apparatus of the present embodiment has the same configuration as that of FIG. 1 described in the first embodiment.

  A processing procedure for calculating the evaluation value of the video content in this embodiment will be described with reference to the flowchart of FIG. FIG. 7 is a flowchart showing an operation when the control unit 111 is configured by a CPU and a program executed thereon. The ROM 117 is a storage medium that stores this program so that the CPU can read it out. This CPU reads the program from the ROM 117 and executes the processing shown in FIG. Each step in FIG. 7 shows a procedure that the program causes the CPU to execute. 7, steps common to FIG. 2 are denoted by step numbers common to FIG.

  In step S111, the travel time is acquired from the acquired flow line, and recorded in the storage unit 112c as shown in FIG. In FIG. 8, the flow line of the flow line ID indicates that it takes 3 seconds from passing through the start line to passing through the end line.

  In step S112, the average moving time is calculated, and the average moving time is recorded in the storage unit 112d in correspondence with the monitoring range ID, the monitoring target ID, and the region ID. The storage unit 112d stores the average travel time (7 seconds) in addition to the monitoring range ID, the monitoring target ID, and the region ID (30, 31, 32,..., 124) stored in step S308. . The average movement time may be the average movement time in the flow line that satisfies the condition of S306, or may be the average movement time in the flow line within the monitoring range set in S308. The flow line analyzing unit 115c acquires the moving time of the monitoring target for each flow line, and the monitoring range setting unit 115d records the average moving time of the monitoring target in the monitoring range.

  With the above processing, the average moving time when the monitor moves in the monitoring range can be set. The set average moving time is used when an alarm is issued as an abnormal situation when the monitoring target stays within the monitoring range even if the monitoring range exceeds the average moving time by a threshold or more. Moreover, you may display average moving time.

  FIG. 9 is a schematic diagram illustrating an example of a schematic configuration of the monitoring apparatus according to the third embodiment of the present invention.

  As shown in FIG. 9, the monitoring apparatus according to the present embodiment includes a terminal 141. The terminal 141 includes a control unit 1411, a storage unit 1412, a display unit 1413, an input unit 1414, a monitoring range setting unit 1415, a RAM 1416 and a ROM 1417, and a bus 1418 for connecting these elements.

  The storage unit 1412 has the same function as the storage unit 112 in the first embodiment, the display unit 1413 has the same function as the display unit 113, and the input unit 1414 has the same function as the input unit 114. The condition setting unit 1415a has the same function as the condition setting unit 115a and the flow line acquisition unit 1415b in the first embodiment. The feature amount calculating unit 1415c is a unit that calculates the feature amount of the monitoring target, and records the feature amount in the monitoring target information storage unit 1412b. The feature quantity calculating unit 1415c calculates the feature quantity of the monitoring target, and records the calculated feature quantity in the identification information of the monitoring target. The flow line analyzing unit 1415d has a function equivalent to that of the flow line analyzing unit 115c in the first embodiment.

  The monitoring range setting unit 1415e records the set of regions obtained as a result of the flow line analysis unit 1415d in the storage unit 1412d in association with the region identifier and the feature amount as the monitoring range.

  In addition, the RAM 1416 has the same function as the RAM 116 in the first embodiment, the ROM 1417 has the same function as the control unit 111, and the control unit 1411 has the same function as the control unit 111.

  Next, a procedure for setting a monitoring range in the present embodiment will be described with reference to FIG. Here, in the present embodiment, a monitoring system for monitoring a site in a factory or company will be described as an example, and people A and B passing through the site will be described as monitoring targets. FIG. 10 is a flowchart showing the operation when the control unit 1411 is configured by a CPU and a program executed thereon. The ROM 1417 is a storage medium that stores the program so that the CPU can read it out. This CPU reads the program from the ROM 1417 and executes the processing shown in FIG. Each step in FIG. 10 shows a procedure that the program causes the CPU to execute.

  Step S1501 is processing of the condition setting unit 1415a, and sets a start line and an end line for acquiring a flow line as shown in FIG. 11 using the input unit 1414.

  The subsequent step S1502 is processing of the flow line acquisition unit 1415b, acquires a flow line that matches the condition set in S1501 as shown in FIG. 12A, and uses the acquired flow line information as monitoring target identification information. Correlate and record in the storage unit 112c. In the storage unit 112c, for each of the flow line IDs 1, 2,..., 7, 8, 9,.・ ・ 2 is recorded. The flow line ID1 is the monitoring target flow line of the monitoring target ID1, the flow line ID7 is the monitoring target flow line of the monitoring target ID1, and the flow line ID14 is the monitoring target flow line of the monitoring target ID2.

  Step S1503 is a process of the feature quantity extraction unit 1415c, which extracts a feature quantity for each monitoring target and records it in the monitoring target identification information storage unit 1412c. In the monitoring target identification information storage unit 1412c, it is recorded that the name of the monitoring target of the monitoring target ID 1 is A, the telephone number of the contact is 111-2222, and the feature amount is the feature amount of the helmet. Further, in the monitoring target identification information storage unit 1412c, it is recorded that the name of the monitoring target of the monitoring target ID 2 is B, the telephone number of the contact is 222-3333, and the feature amount is the feature amount of the work clothes. Is done.

  The next steps S1504 to S1508 are processing of the flow line analyzing means 1415d. In S1504, the video is divided into arbitrary division numbers as shown in FIG. 12B, and an identifier is given for each area. Steps S1505, S1506, S1507, and S1508 are steps for analyzing the number of flow lines that appear for each of the divided areas. If there are more than a predetermined number of flow lines that appear, they are associated with the region identifier in FIG. Is recorded in the storage unit 1412c.

  Steps S1509 and S1510 are processes of the monitoring range setting unit 1415e. In step S1509, an area where a flow line is detected at a predetermined frequency as shown in FIG. 14 is extracted from the result of the flow line analyzing unit 1415c, and the feature quantity of the monitoring target that has passed through the extracted area is recorded in the storage unit 1412d. . The monitoring range setting unit 1415e associates the monitoring range with the feature amount. In the storage unit 1412d, it is recorded that the area ID of the area where the monitoring target whose characteristic amount is a helmet or work clothes passes a plurality of times is 1, 2, 3,..., 40 as the monitoring range of the monitoring range ID1. Is done. In addition, in the storage unit 1412d, it is recorded that the area ID of the area where the monitoring target whose characteristic amount is a helmet passes a plurality of times is 9, 17, 18,..., 38 as the monitoring range of the monitoring range ID2. The Further, in the storage unit 1412d, it is recorded that the area ID of the area where the monitoring target whose feature quantity is work clothes passes a plurality of times is the monitoring range of the monitoring range ID3 of 4, 5, 6,. Is done.

  When the monitoring target of the monitoring target ID1 whose feature is a helmet is monitored (when a person wearing a helmet is monitored), the monitoring ranges of the monitoring ranges ID1 and 2 are set as the monitoring range. Also, when monitoring the monitoring target with the monitoring target ID 2 whose feature is work clothes (when monitoring a person wearing a work clothes), the monitoring ranges of the monitoring ranges ID 1 and 3 are set as the monitoring range. When monitoring the monitoring targets ID 1 and 2, the monitoring ranges with the monitoring range IDs 1, 2, and 3 are set as the monitoring range.

  Through the above processing, a region having a high appearance frequency can be acquired from the flow line to be monitored, and the set of acquired regions can be set as a monitoring range for each feature amount. The above processing is repeated for the monitoring target for which the monitoring range is set, and when there is a difference in the monitoring range, the monitoring range may be updated or a warning may be issued to the monitor. This embodiment can be applied to a facility such as a factory or a company where it is desired to switch a monitoring range for each monitoring target with a feature amount of an object worn by a worker.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

115, 1415 Monitoring range setting unit 115a, 1415a Condition setting means 115b, 1415b Flow line acquisition means 115c, 1415d Flow line analysis means 115d, 1415e Monitoring range setting means

Claims (14)

Setting means for setting at least one or more lines as flow line acquisition conditions;
An acquisition unit which based on the said flow line acquisition condition, acquires a flow line passing through the line,
Analyzing means for analyzing a flow line, and extracting an area where a flow line passing through the line is detected more than a predetermined number ;
A setting means for setting a set of areas extracted by the analysis means, in which more than a predetermined number of flow lines passing through the line are detected, to a monitoring range;
The setting means, the set monitoring range, if the flow line passing through the line there is change in the set of regions that are detected more than a predetermined number, the monitoring device characterized by generating an alarm.   The monitoring apparatus according to claim 1, wherein the setting unit sets a plurality of lines, and the acquisition unit acquires a flow line passing through the plurality of lines set by the setting unit. The monitoring apparatus according to claim 1, wherein the analysis unit divides an image into an arbitrary number of divisions, and analyzes whether or not more than a predetermined number of flow lines pass for each region. .   The monitoring apparatus according to claim 1, wherein the analysis unit acquires the moving time of the monitoring target for each flow line, and the setting unit records the average moving time of the monitoring target in the monitoring range.   The feature amount calculating means for calculating the feature amount of the monitoring target and recording the calculated feature amount in the identification information of the monitoring target, wherein the setting means associates the monitoring range with the feature amount. The monitoring apparatus according to 1. The setting means, when the flow line there was a change in the set of regions which are detected at a predetermined frequency, the monitoring device according to claim 1, characterized in that updating the monitoring range. And setting at least one or more lines as flow line acquisition conditions,
And based on the said flow line acquisition condition, and acquires the flow line passing through the line,
Analyzing the flow line, extracting a region where the flow line passing through the line is detected more than a predetermined number ,
A set of the extracted areas in which more than a predetermined number of flow lines passing through the line are detected is set as a monitoring range,
A method for setting a monitoring apparatus, characterized in that an alarm is issued when there is a change in a set of areas set in the monitoring range where more than a predetermined number of flow lines passing through the line are detected.   The monitoring apparatus setting method according to claim 7, wherein a plurality of lines are set as the flow line acquisition condition, and a flow line passing through the set plurality of lines is acquired.   The monitoring apparatus setting method according to claim 7, wherein the moving time of the monitoring target is acquired for each flow line, and the average moving time of the monitoring target in the monitoring range is recorded.   The monitoring apparatus setting method according to claim 7, wherein the monitoring target feature amount is calculated, the calculated feature amount is recorded in the monitoring target identification information, and the monitoring range is associated with the feature amount. A setting procedure for setting at least one line as a flow line acquisition condition;
An acquisition procedure which have groups on the flow line acquisition condition, acquires a flow line passing through the line,
An analysis procedure for analyzing a flow line and extracting an area where a flow line passing through the line is detected in a predetermined number or more ;
A program for causing a computer to execute a setting procedure for setting, in a monitoring range, a set of areas extracted in the analysis procedure and in which a flow line passing through the line is detected more than a predetermined number. the procedure, the set monitoring range, if the flow line passing through the line there is change in the set of many detection area than a predetermined number, program characterized by generating an alarm.   12. The program according to claim 11, wherein a plurality of lines are set in the setting procedure, and a flow line passing through the plurality of lines set in the setting procedure is acquired in the acquisition procedure.   The program according to claim 11, wherein the analysis procedure acquires the moving time of the monitoring target for each flow line, and the setting procedure records the average moving time of the monitoring target in the monitoring range.   A feature amount calculation procedure for calculating a feature amount of a monitoring target and recording the calculated feature amount in identification information of the monitoring target is executed by a computer, and the setting procedure associates the monitoring range with the feature amount. The program according to claim 11.

Images