JP2003101999A - Monitoring camera system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a monitoring camera system capable of improving monitoring accuracy and reducing monitoring labor by automatically detecting/ tracking a moving object of a monitoring object, computing movement information and storing the monitored information. SOLUTION: The monitoring camera system is provided with a camera 1 photographing a monitoring area, a moving object detecting/tracking means 2 for detecting the moving object of the monitoring object from a monitoring image based on photographing of the camera 1 and tracking it, a movement information computing means 3 for computing the movement information of the moving object, a monitoring information storage means 4 for storing the monitoring information such as the monitoring image, moving object detected/ tracked results, the movement information, and a result of moving object moving line prediction described later, a moving object moving line prediction means 5 for predicting a moving object moving line, and an image display means 6 for selectively displaying a part or all of the monitoring information. For the camera 1, coordinates in the monitoring area are made to correspond to a plurality of photographed monitoring images.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a surveillance camera system for assisting surveillance by detecting and tracking a moving object to be monitored such as a person or a vehicle by image processing.

[0002]

2. Description of the Related Art Surveillance camera devices are used in financial institutions, commercial facilities, parking lots, etc. in order to detect intruders and grasp the usage status of users. In many conventional surveillance camera devices of this type, a monitoring person monitors a moving object to be monitored, such as a person or a vehicle, in a monitoring area while looking at a captured monitoring image. Therefore, the monitoring area is photographed by using a plurality of monitoring cameras, and the monitoring images by the individual monitoring cameras are switched through the image selecting means to display or record.

On the other hand, in a store or the like, the flow line of a person, that is, the movement locus is one of the factors that influence sales. Therefore, in order to increase sales, the flow lines are investigated to improve the store layout. However, the conventional flow line survey is based on a method in which a surveyor follows a visitor and writes his / her behavior on a survey form each time.

[0004]

In the conventional surveillance camera apparatus, there is a problem that the surveillance operation is often performed by the observer while watching the surveillance image, and accurate surveillance cannot be performed when the surveillance area is wide.

On the other hand, the conventional flow line survey has a problem that it takes much time, labor and cost. Moreover, the flow line survey results were difficult to understand just by looking at non-specialists such as store managers. Therefore, there is also a problem that it is difficult for the store side to understand. In addition, it is easier to understand the current situation by looking at the current flow line while comparing it with the ideal flow line and the flow line when good results were obtained in the past (for example, when high sales were made). The above surveillance camera device cannot satisfy such requirements.

Further, if the movement of the moving object to be monitored can be predicted, it can be linked to the simulation of the flow line and the improvement of the monitoring accuracy, but this has not been possible in the past.

The present invention provides a surveillance camera system that automatically detects and tracks a moving object to be monitored, calculates movement information, and stores the monitoring information, thereby improving the monitoring accuracy and reducing the monitoring labor. The purpose is to provide.

It is another object of the present invention to provide a surveillance camera system that simulates a flow line and improves the monitoring accuracy by predicting the motion of a moving object to be monitored.

A further object of the present invention is to provide a surveillance camera system which facilitates the search of past surveillance information to facilitate the grasp of the current state of the surveillance area.

[0010]

According to another aspect of the present invention, there is provided a surveillance camera system, comprising: a camera for photographing a surveillance area; and a moving object detection for detecting and tracking a moving object to be monitored from a surveillance image based on photographing by the camera. Tracking means; movement information calculation means for calculating movement information of a moving object; monitoring information storage for storing monitoring information such as monitoring images, moving object detection / tracking results, movement information, and moving object flow line prediction results described later Means;
A moving object flow line prediction means for predicting a moving object flow line; and a display means for selectively displaying a part or all of monitoring information are provided.

In the present invention and the following inventions, the definitions and technical meanings of terms are as follows unless otherwise specified.

<Regarding the camera> As the camera, it is preferable to use a camera such as a video camera capable of capturing a monitoring image composed of moving images. Further, one or more cameras can be appropriately used as required depending on the size of the monitoring area. Further, the processing of the monitoring image based on the photographing by the camera may be performed by either digital processing or analog processing, but the digital processing is easier to process the image capturing such as clipping of the image. Furthermore, the surveillance image may be either color or monochrome.

<About Moving Object Detecting / Tracking Means> The moving object detecting / tracking means is a means for automatically detecting a moving object in a monitoring image based on the image picked up by a camera and for tracking the detected moving object. . The moving object is detected by performing image processing on the moving image. For example, when trying to detect a person as a moving object, a stationary object and a moving object are identified by difference processing between a plurality of image frames, and it is further determined whether the moving object is a person to be monitored. In order to distinguish the moving object to be monitored from other moving objects, the characteristic amount of the moving object to be monitored is stored in advance, and the characteristic amount is read out and compared with the characteristic data in the detection data. Good. Further, when a moving object to be monitored is detected, it is possible to further determine the direction of the moving object and what kind of operation the moving object is performing from the change in the operation to obtain the operation information of the moving object.

Further, how the moving object to be monitored which has been detected as described above has moved, that is, tracking of the moving object is obtained in time series by obtaining position information such as the center of gravity of the moving object. This can be done by comparing the movement of the location information from the surveillance image. It should be noted that the detection and tracking of the moving object may be performed so that the moving object may be performed individually or as a set, or may be configured to be switchable so as to be performed each time. . In order to detect and track at least a set of moving objects, the moving object detecting / tracking means comprises means for counting the number of moving objects.

<About the moving information calculating means> The moving information calculating means is a means for calculating the moving information regarding the detected moving object. That is, in the present invention,
The “movement information” includes at least information about the movement trajectory, movement distance, movement time, and movement speed of the moving object to be monitored. Furthermore, if necessary, information such as acceleration can be added for calculation. Of the above various information, the movement trajectory information can be obtained by tracking a moving object. Further, the movement distance information can be calculated from the movement locus in a certain time based on the movement locus information. Furthermore, the travel time information can be calculated from the time required to travel a certain distance based on the travel trajectory information. Furthermore, the moving speed information can be calculated based on the moving distance and the moving time. The acceleration can also be calculated based on the moving distance and the moving time.

Next, when monitoring a set of a plurality of moving objects, the movement information calculating means can calculate the density, the average velocity, the average movement vector, etc. of the moving objects as desired. Here, the “moving object density” indicates the number of moving objects per unit area in a specific partial area in the monitoring area, and means the congestion degree of the moving objects in the specific space. Therefore, the density of the moving object is calculated based on the area of the specific partial region and the number of moving objects existing therein. The “moving object average movement vector” can be calculated by the average movement distance and movement direction.

<Regarding Monitoring Information Storage Means> In the present invention, “monitoring information” refers to information related to monitoring such as monitoring images, moving object detection / tracking results, moving information, and moving object flow line prediction results described later. . The monitoring information storage means selectively stores some or all of the monitoring information. Further, it is also allowed to store information related to the monitoring information, if desired. When the monitoring information is stored, the attribute information of the moving object to be monitored, for example, when the moving object is a person, the sex, the age, and the like can be stored in association with each other. Various known storage means can be used as the recording means. For example, hard disk, DV
A storage means having a large storage capacity such as a D, a memory card, an MO disk, a video tape, etc. is suitable.

<About Moving Object Flow Line Prediction Unit> The moving object flow line prediction unit is a unit for predicting the movement of the moving object as a flow line based on the movement information and obtaining the prediction result. For this reason, the moving object flow line prediction means may be provided with a learning function so as to learn past movement information and movement information based on assumed conditions stored in advance for learning. The flow line can be obtained for both a single moving body and a set of moving bodies. Therefore, it is possible to switch between a single unit and a set. In this case, you may make it interlock with the same switching of the movement information calculation means.

Further, in order to predict the flow line of the moving objects of the set, the moving objects to be monitored are grasped as a fluid, and the position information of the obstacles in the monitored area is introduced into the operation to perform the fluid dynamic operation. By doing so, it is possible to accurately predict the flow line of the moving object to be monitored.

<Regarding Display Means> The display means is a means for displaying a part or all of the monitoring information and related information, and is configured to display either one or both of the current data and the past data. You can As the display means, various known display means can be appropriately selected and adopted.

<Regarding Operation of the Present Invention> In the present invention, based on the configuration described above, a moving object to be monitored, which is composed of a single object or a group, is automatically detected from the monitoring images captured by the camera, Moreover, it is possible to track and calculate movement information including a movement distance, a movement time and a movement speed of the moving object, store necessary monitoring information, and display a part or all of the monitoring information on the display means. . Therefore, even if the monitoring area is wide, monitoring can be performed easily and accurately. Therefore, it is possible to reduce the monitoring labor.

In addition, in the present invention, the movement prediction of the moving object to be monitored can be calculated as a flow line prediction and can be displayed. Therefore, by simulating the flow line of the monitoring area, the moving object can be simulated. It is possible to effectively plan the layout while considering the flow lines of the. In addition, it is possible to improve the monitoring accuracy by using the flow line prediction result.

The surveillance camera system according to the invention of claim 2 is
A camera for photographing the monitoring area; a moving object detecting / tracking means for detecting and tracking a moving object to be monitored from a monitoring image created by the camera based on the photographing; and a movement information calculating means for calculating movement information of the moving object. Monitoring information storage means for storing monitoring information such as monitoring images, moving object detection / tracking results, movement information; monitoring information searching means for searching the monitoring information stored in the monitoring information storage means; current monitoring information And display means for selectively displaying the retrieved monitoring information;

The present invention defines the configuration so that the stored monitoring information can be searched and displayed.

The monitoring information retrieving means is a means for retrieving past monitoring information stored in the monitoring information storage means and reading out desired monitoring information. The monitoring information to be searched is
Although not particularly limited, it is convenient to be able to search for a monitoring image, a moving object trajectory tracking result, moving information of a moving object, and the like. In addition, the search can be performed individually or in combination with time, such as date and time, items of monitoring information, attribute data of a moving object to be monitored, monitoring information stored with a specific mark, patterns of contents, etc. Can be configured to do so.

The display means operates so as to selectively display the past monitoring information read as a result of the search of the monitoring information and the present monitoring information. In this case, the display means may display only the read monitoring information, but it may be configured to display another display, for example, in parallel with the current display. Further, the display means may be either single or plural. For example, the image display unit of the display means may be divided into a plurality of pieces so as to be able to be displayed, or a plurality of display means may be arranged side by side so that one display is provided on one side and the other display is provided on the other side. Good.

When the present invention is implemented by adding the invention of claim 1, a more convenient surveillance camera system can be obtained.

Thus, according to the present invention, desired information is retrieved from past monitoring information, selectively displayed as the current monitoring information, and used as a reference to grasp the current status of the monitoring area. Can be performed easily and accurately. Therefore, when examining the layout of the monitoring area, it can be performed easily and accurately.

The surveillance camera system according to the invention of claim 3 is
The surveillance camera system according to claim 2 is characterized in that the display means is configured to display at least the current surveillance information and the past surveillance information in a comparable manner.

A moving body tracking technique using moving image processing is
In the field of TS (Intelligent Transport System) and the like, research is actively conducted, and traffic flow monitoring, road monitoring, traffic volume measurement, and road information provision for abnormal traveling using moving images are being performed. In addition, moving object tracking technology is being researched in a wide range of fields, such as measuring the trajectory of soccer players and measuring crowd flow at station ticket gates.

Measuring the flow of a moving object means
It can be said that the current situation is being measured in order to bring that flow closer to a certain goal (state, grade, etc.). However, even if the tracking result of the moving object is simply displayed, there is a problem that it is difficult to determine whether the state is good or bad.

In the present invention, a visitor, which is a moving object to be monitored and has entered a monitoring area, for example, a store, is detected on the basis of an image picked up by a camera, and its flow line is automatically traced and recorded. , While displaying the current monitoring information, search the desired flow line from the past monitoring information,
The current flow line and the past flow line can be displayed at the same time. At this time, the attribute information of the visitor, such as gender,
The age, etc. can be displayed at the same time. This allows
It is possible to support the flow line evaluation.

Further, not only the flow line of the moving object to be monitored but also other monitoring information such as a monitoring image can be displayed side by side with the current state and the past monitoring information extracted by the search. This makes it easier to understand the current situation.

The surveillance camera system according to the invention of claim 4 is
The surveillance camera system according to any one of claims 1 to 3, wherein a plurality of cameras are used to cover a predetermined surveillance area, and a coordinate in the surveillance area is set for a captured image of each camera. The feature is that they are associated.

The present invention defines a camera arrangement suitable for monitoring a predetermined monitoring area using a plurality of cameras. In other words, when the surveillance area is large, it is difficult for one camera to clearly capture the entire surveillance area. Therefore, different cameras share different locations in the surveillance area. In that case, it is difficult to grasp which part of the monitoring area is the monitoring image by simply displaying the monitoring images taken by the individual cameras in parallel as individual images. The coordinates in the entire monitoring area are associated with the captured image for each device.

Thus, in the present invention, since the coordinates in the surveillance area are respectively assigned to the surveillance images of a plurality of cameras, the image taken by the camera indicates which part of the surveillance area. You can know exactly what.

According to the surveillance camera system of the invention of claim 5,
The surveillance camera system according to any one of claims 1 to 4, wherein the moving object detection / tracking means determines whether the detected moving object is a monitoring target, and the determined monitoring target moving object is a moving object. And a motion judging means for judging what kind of motion has been performed.

The present invention defines a preferable configuration for moving object detection in the moving object detection / tracking means. That is, in the present invention, the detection of the moving object is performed separately by determining whether the moving object is a monitoring target and determining how the moving object is operating. The former determination is performed by comparing the feature amount of the moving object, which is stored in advance, with the detected feature data of the moving object. The latter determination is based on a change in the feature amount or the like in the detection data of the moving object.

Thus, in the present invention, it becomes easy to detect the moving object to be monitored and what kind of operation the moving object is performing, that is, the operation information.

The surveillance camera system according to the invention of claim 6 is
The surveillance camera system according to any one of claims 1 to 5, wherein the movement information computing means computes movement information including at least a movement trajectory, a movement distance, a movement time, and a movement speed of the moving object to be monitored. I am trying.

The present invention defines items of movement information to be calculated. That is, the above calculation items are useful for monitoring the monitoring area and planning the layout of the monitoring area. Of course, if necessary, it is possible to calculate other items such as the acceleration of the moving object.

The surveillance camera system according to the invention of claim 7 is
The surveillance camera system according to any one of claims 1 to 6, wherein a set of moving objects is detected, tracked, calculated, and displayed.

In the field of construction, in places where people are crowded such as blame passages and ticket gates at stations, conducting line planning is performed in consideration of the flow of people. Also in the transportation field, traffic flow plans are being carried out for the purpose of alleviating traffic congestion.

However, when there is no suitable technique for measuring the congestion of a moving object consisting of a set of people, vehicles, etc., and when obtaining a lead wire for a set of people, the measuring person enters the crowd and mixes with the flow line. Is being measured. In such a measuring method, there is a problem that time and labor are spent and labor cost increases.

Conventionally, some of these facilities are equipped with surveillance cameras, but they are mainly used only for surveillance and not for flow line measurement.

The present invention defines a configuration in which a set of people, vehicles, etc. is treated as a moving object. That is, the set of moving objects is detected, the movement of the set is tracked, the movement information of the set is calculated, the monitoring information of the set is stored, and further, based on the movement information, the layout of the space, the action parameters of the set, etc. To predict the flow line of the set or retrieve the stored monitoring information and use the past monitoring information.

The movement information of the set includes the density of the set, the average velocity of the set, the average movement vector of the set, and the like. As the layout condition of the space, for example, the size of the space and the number, size and position of obstacles such as furniture are set. As the condition of the action parameter,
For example, age, gender, weather, congestion degree, passage width, attention information (display, broadcast, etc.) are set.

Thus, in the present invention, a group of people and vehicles is used as a moving object, so that it can be widely used for monitoring and examination of layout in many fields such as the construction field, the traffic field, and commercial fields such as shops. A surveillance camera system effective for

[0049]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.

1 to 6 show a first embodiment of a surveillance camera system of the present invention, FIG. 1 is a system block diagram, FIGS. 2 and 3 are flow charts for detecting a moving object,
FIG. 4 is a flowchart for tracking a moving object, FIG. 5 is a flowchart for moving object information used for predicting a moving object in the case of a single moving object, and FIG. 6 is a flowchart for predicting a moving object when a trajectory of a moving object disappears. In the system block diagram of FIG. 1, 1 is a camera, 2 is a moving object detection / tracking means, 3 is movement information calculation means, 4 is monitoring information storage means, 5
Is a moving object flow line prediction means, and 6 is a display means. In addition,
The present embodiment corresponds to the invention described in claim 1.

<Camera 1> The camera 1 is composed of a plurality of video cameras 1-1, 1-2, 1-3, ... 1-n, and is installed so that almost the entire monitoring area can be shared and photographed. To be done. Then, the plurality of video cameras 1-1, 1-
Coordinates are designated for each of 2, 1-3, ... 1-n, and those images are combined based on the designated coordinates to generate one or a plurality of monitoring images so as to cover almost the entire monitoring area. Form.

<About Moving Object Detecting / Tracking Means 2> The moving object detecting / tracking means 2 includes moving object detecting means 2a, target moving object determining means 2b, target moving object motion determining means 2
c and target moving object tracking means 2d. The moving object detecting means 2a is means for identifying a moving object from the monitoring image created based on the input from the camera 1. The target moving object determination means 2b is means for detecting a moving object to be monitored from the identified moving objects. The target moving object motion determination unit 2c is a unit that determines the motion of the moving object to be monitored. Target moving object tracking means 2d
Is a means for tracking a moving object to be monitored.

Next, a flow chart for detecting the moving object to be monitored by the moving object detecting / tracking means 2 will be described with reference to FIGS. First, in FIG. 2, the background image (0) is superimposed on the input image (t) to create a difference image by the difference method, and a binarized image is created based on the difference image. Subsequently, a labeling process is performed and then a person is determined. In this case, a person is detected as the moving body. If yes, it is stored as detection information, and the process for the next input image is continued. Also,
If the determination is no, the process for the next input image is continued as it is. The previous input image is used as the background image each time the input image is switched. FIG. 3 is a flowchart when the background image is (t−T), but the other parts are the same as those in FIG. 2.

Further, a flow chart of the moving object tracking in the moving object detecting / tracking means 2 will be described with reference to FIG. That is, when a moving object to be monitored is detected, the number N of moving objects is calculated and three-dimensional reconstruction is performed. Note that “three-dimensional reconstruction” refers to conversion of coordinates on an image into coordinates in real space. Next, the motion information is calculated, and subsequently the motion compatibility is calculated. The above-described series of processing is performed N times for the moving object, and then the presence or absence of conformity is determined. If there is a match, the operation information is recorded / added, and the process returns to the beginning and the processes after the moving object detection are repeated. If there is no match, it is determined whether or not there is a match with reference to the information of another camera image. If there is a match, the above operation information is recorded / added. If there is no match, the previous information is retained, and the process returns to the beginning and the processes after the moving object detection are repeated to perform the tracking process.

<Regarding the movement information calculation means 3> The movement information calculation means 3 comprises a single piece movement information calculation means 3a and a set movement information calculation means 3b. Single unit movement information calculation means 3
Reference numeral a is a means for calculating movement information when the moving object to be monitored is a single unit, and is provided with a movement locus calculation means 3a1, a movement distance calculation means 3a2, a movement time calculation means 3a3 and a movement speed / acceleration calculation means 3a4. There is. The movement locus calculation means 3a1 calculates the movement locus of a single moving object. The moving distance calculation means 3a2 calculates the moving distance of the single moving object. The moving time calculating means 3a3 calculates the moving time of a single moving object. Moving speed / acceleration calculating means 3a4
Calculates the moving speed and acceleration of a single moving object.

The set movement information calculation means 3b is means for calculating movement information when the moving object to be monitored is composed of a plurality of moving objects, that is, set movement information. The moving object counting means 3b1 and the moving object density calculation. Means 3b2, average movement speed calculation means 3b3 and average movement vector calculation means 3b4 are provided. The moving object counting means 3b1 is a means for counting the number of single moving objects existing in a specific area of the monitoring area and calculating the size of the collective moving objects. The moving object density calculating means 3b2 is a moving object counting means 3b1.
It is a means for calculating the density of the collective moving object by dividing the calculated value of by the area of the specific region. Average moving speed calculation means 3b3
Is a means for calculating the average value of the moving speeds of the collective moving objects. The average movement vector calculation means 3b4 is a means for calculating the average movement vector of the collective moving object.

Next, a flow chart of the aggregate movement information calculation centering on the movement information used in the moving object flow line predicting means 5 will be described with reference to FIG. That is, the current position of the moving object, the speed of the moving object, and the maximum speed (moving speed, moving maximum speed) are obtained based on the motion information of the moving object, and the moving range is calculated based on these. Similarly, the size, area / circumscribing rectangle of the moving object, the color of the moving object, and the RGB component are obtained, and the appearance information of the object is calculated based on these.

<Regarding Monitoring Information Storage Means 4> The monitoring information storage means 4 is means for storing monitoring information consisting of a monitoring image, moving object detection / tracking results, single movement information and collective movement information.

<Regarding Moving Object Flow Line Prediction Unit 5> The moving object flow line prediction unit 5 is a unit for predicting the flow line of the moving object to be monitored, and includes the single moving object flow line prediction unit 5a and the collective moving object motion. The line prediction means 5b is provided. The single moving object flow line prediction unit 5a is a unit that predicts the flow line of a single moving object. The collective moving object flow line prediction unit 5b is a unit that predicts a collective moving object flow line.

Next, a flow chart for predicting the moving object flow line when the trajectory of the moving object in the single moving object disappears will be described with reference to FIG. That is, the state of the trajectory is determined based on the tracking information of the moving object, and when the trajectory disappears, the movement information obtained in FIG. 5, that is, the movement range and the appearance information is referred to determine the presence or absence of a candidate. To do. As a result, when there is a candidate, the movement information is stored / added. When there is no candidate, the movement information is held.

<Regarding Display Means 6> The display means 6 is means for displaying current and / or past monitoring information.

7 and 8 show a second embodiment of the surveillance camera system of the present invention, FIG. 7 is a system block diagram, and FIG. 8 is a flow chart for explaining the outline of flow line prediction for a collective moving body. . In the figure, those parts that are the same as those corresponding parts in FIG. 1 are designated by the same reference numerals, and a description thereof will be omitted. The present embodiment is different in that the mobile body flow line prediction means 5 is configured by a movement information learning unit 5c, a spatial layout setting unit 5d, a behavior parameter setting unit 5e, and a flow line prediction unit 5f. The present embodiment corresponds to the invention described in claim 2.

The movement information learning section 5c is means for learning the monitoring information stored in the movement information storage means 4. The space layout setting unit 5e is means for setting space conditions such as space size, number of obstacles such as furniture, size and position. The action parameter setting unit 5f is means for setting action parameters of the moving object such as age group, sex, weather, congestion degree of the moving object, display objects and broadcasting. The flow line predicting unit 5f is a means for predicting the flow line of a moving object, and the learning result by the movement information learning unit 5c and the spatial layout setting unit 5
The flow line of the moving body is predicted in consideration of the spatial layout by d and the action parameter of the moving object by the action parameter setting unit 5e. This embodiment can be applied to the line prediction of a single moving object, but is suitable for the line prediction of a moving object of a set.

Next, the outline of the flow line prediction will be described with reference to FIG. That is, the number of people (number of people in a group), age, and sex as group information, the weather as environment information,
By referring to the congestion degree and the sign, and the space size, obstacles (pillars, shelves, etc.) and passage widths, and the length (area) as layout information, a set flow line prediction table is created and stored in advance. deep. The aggregate flow line prediction table is
As the set type, the environment (information) is assigned to each of A, B, C, ..., and the passage / stop positions are assigned to the passage 1, the passage 3, the passage 1, the passage 4 ,. I am creating it. Then, when a corresponding item is searched for the set type and the environment, the passage / stop position of the item becomes the flow line prediction.

9 to 11 show a third embodiment of the camera system of the present invention. FIG. 9 is a system block diagram, FIG. 10 is a search screen, and FIG. 11 is a past flow diagram showing search results. It is a flow diagram showing the main search words and the current monitoring status, and similar attribute data. In the figure, those parts that are the same as those corresponding parts in FIG. 1 are designated by the same reference numerals, and a description will be omitted. The present embodiment is different in that the monitoring information search means 7 is provided.

That is, the monitoring information search means 7 is a means for searching the past monitoring information stored in the monitoring information storage means 4 while looking at the display means 6 and displaying the search result on the display means 6.

The search screen displayed on the display means 6 during the search is divided into search items and search words, as shown in FIG. Then, a desired search word is input for each search item to perform a search.

The search results are shown on the right side of FIG. 11, and the current situation is also shown on the left side. Therefore, the current status can be confirmed while comparing the past search screen with the current monitoring status. In addition, in FIG.
In addition to the flow chart, the main items to be searched, such as the store, the date and time, the customer, the staying time, the moving distance, the number of points purchased, and the amount purchased are displayed. Therefore, in FIG. 11, for example, it is possible to compare and examine the difference in the purchase behavior of the store visitor between the past layout and the current layout.

[0069]

According to the invention of claim 1, a camera, a moving object detecting / tracking means for detecting and tracking a moving object to be monitored from a monitoring image, and a moving information calculating means for calculating moving information, Monitoring information storage means for storing monitoring information such as monitoring image, moving object detection / tracking result, movement information, and result of moving object flow line prediction described later, moving object flow line prediction means, and display means for displaying monitoring information Even if the monitoring area is wide, monitoring can be performed easily and with high accuracy. Therefore, the monitoring labor can be reduced, and the movement of the target moving object can be predicted. Not only is it possible to simulate the flow line of the monitoring area by calculating and displaying it as a flow line prediction and effectively planning the layout while considering the flow line of the moving object. , It is possible to provide a monitoring camera system to improve the monitoring accuracy by utilizing the flow line prediction result.

According to the second aspect of the present invention, the camera, the moving object detecting / tracking means for detecting and tracking the moving object from the monitoring image, the moving information calculating means for calculating the moving information of the moving object, and the monitoring image. Monitoring information storage means for storing monitoring information such as moving object detection / tracking results and movement information, monitoring information searching means for searching monitoring information stored in the monitoring information storage means, current monitoring information and searched monitoring By having a display means for selectively displaying information,
By searching for desired information from past monitoring information, displaying it, and referring to it, it is possible to provide a monitoring camera system that easily and accurately grasps the current state of the monitoring area.

According to the invention of claim 3, in addition, the display means is configured to display at least the current monitoring information and the past monitoring information in a comparable manner.
To provide a surveillance camera system that facilitates grasping the current situation by supporting the flow line evaluation and displaying the current state and past surveillance information extracted by search for other surveillance information such as surveillance images side by side. You can

According to the fourth aspect of the present invention, in addition, a plurality of cameras are used to cover a predetermined surveillance area, and the image in each camera is associated with the coordinates in the surveillance area. As a result, it is possible to provide a surveillance camera system that accurately grasps which part of the surveillance area the mobile body is in.

According to the invention of claim 5, in addition, the moving object detecting / tracking means determines the judging means for judging whether the detected moving object is a monitoring target and how the judged moving object is a monitoring object. By providing an operation determination means for determining whether a different operation has been performed, it is possible to provide a surveillance camera system that can easily detect a moving object to be monitored and what kind of operation the moving object is performing. be able to.

According to the invention of claim 6, in addition, the movement information calculation means calculates movement information including at least a movement trajectory, a movement distance, a movement time and a movement speed of the moving object to be monitored to thereby obtain a monitoring area. It is possible to provide a surveillance camera system which is useful for surveillance of the robot and planning of the layout of the surveillance area.

According to the invention of claim 7, in addition, as a moving object to be monitored, a set of moving objects is detected and tracked,
By being configured so that it can be calculated and displayed, by using a group of people and vehicles as a moving object, it can be used in many fields such as the construction field, the traffic field, and the commercial field such as stores.
It is possible to provide a surveillance camera system that is effective for wide use such as surveillance and examination of layout.

[Brief description of drawings]

FIG. 1 is a system block diagram showing a first embodiment of a surveillance camera system of the present invention.

FIG. 2 is a flowchart of moving object detection as well.

FIG. 3 is a flowchart for detecting a moving object as well.

FIG. 4 is a flow chart of moving object tracking as well.

FIG. 5 is a flowchart of moving body information used for flow line prediction in the case of a single moving object.

FIG. 6 is a flowchart for predicting a flow line when the trajectory of a moving object disappears.

FIG. 7 is a system block diagram showing a second embodiment of the surveillance camera system of the present invention.

FIG. 8 is a flowchart illustrating an outline of flow line prediction for a collective moving object.

FIG. 9 is a system block diagram showing a third embodiment of the surveillance camera system of the present invention.

[Figure 10] Similar search screen

FIG. 11 is a flow diagram showing a search result in the past and main search words, and a flow diagram showing the current monitoring status and similar attribute data.

[Explanation of symbols]

1 ... Camera 2 ... Moving object detection / tracking means 3 ... Movement information calculation 4 ... Monitoring information storage 5 ... Moving object flow line prediction 6 ... Display means

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Takashi Ichijo             4-3-1, Higashishinagawa, Shinagawa-ku, Tokyo             Itec Co., Ltd. F term (reference) 5C054 AA01 AA05 CA04 CC02 CG05                       CH01 EA01 EA05 EA07 FA09                       FC13 FF02 GA01 GB02 GD01                       HA18 HA31                 5C087 AA03 AA24 AA25 BB03 BB74                       DD03 DD14 EE05 EE19 FF01                       FF04 FF19 FF20 GG02 GG09                       GG11 GG14                 5L096 AA06 BA02 CA05 EA43 FA52                       FA59 FA69 GA08 GA34 HA02                       JA11

Claims (7)

[Claims] 1. A camera for photographing a surveillance area; a moving object to be monitored is detected from a surveillance image based on photographing by the camera,
A moving object detecting / tracking means for tracking; a moving information calculating means for calculating moving information of a moving object; monitoring information such as a monitoring image, a moving object detection / tracking result, moving information, and a moving object flow line prediction result described later. Monitoring information storage means for storing; moving object flow line predicting means for predicting moving object flow lines; and display means for selectively displaying a part or all of the monitoring information. Surveillance camera system. 2. A camera for photographing a monitoring area; a moving object detecting / tracking means for detecting and tracking a moving object from a monitoring image based on photographing by the camera; and a movement information calculating means for calculating movement information of the moving object. Monitoring information, moving object detection / tracking results, monitoring information storage means for storing monitoring information such as movement information; monitoring information searching means for searching the monitoring information stored in the monitoring information storage means; A surveillance camera system comprising: a display unit for selectively displaying the retrieved surveillance information. 3. The surveillance camera system according to claim 2, wherein the display means is configured to display at least the current surveillance information and the past surveillance information in a comparable manner. 4. A plurality of cameras are used to cover a predetermined surveillance area, and the coordinates in the surveillance area are associated with the captured image of each camera. Item 5. The surveillance camera system according to any one of items 1 to 3. 5. A moving object detecting / tracking means, a judging means for judging whether or not the detected moving object is a monitoring target, and an operation for judging what kind of operation the judged moving object as a monitoring object has performed. The monitoring camera system according to claim 1, further comprising: a determination unit. 6. The movement information calculation means calculates movement information including at least a movement trajectory, a movement distance, a movement time and a movement speed of a moving object to be monitored. The surveillance camera system described. 7. The moving object to be monitored is configured so that a set of moving objects can be detected, tracked, calculated, and displayed. The surveillance camera system as described above.