JP2003189295A - Monitor camera system and information-providing system using the same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To consolidate and deliver images observed by means of a monitor camera installed at a store to a processing center to execute centralized image processing and accumulation. <P>SOLUTION: The images observed by means of the monitor camera installed at the store are consolidated and delivered to the processing center. An image processing means at the processing center extracts black from a photographed image. Removing a portion corresponding to the black portion of a black- extracted background image extracts a person image. The coordinate of its top portion is stored as a head coordinate. The monitor camera is fixedly installed. Previous registration is applied to a corresponding relation to the head coordinate applied when a person with a prescribed height is present at the space coordinate of its monitor range. The space coordinate is then obtained from the detected head coordinate to determine the position of the person in the image. The position data of the person is stored on request. The data is then provided to the store. <P>COPYRIGHT: (C)2003,JPO

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 and an information providing system using the surveillance camera system, and more particularly to gathering images of surveillance cameras for fixed point observation in a center and detecting a person position by a simple process. The present invention relates to a system for delivering photographed image data from a center according to the requirements.

[0002]

2. Description of the Related Art Increasing customer turnover has become an important issue for improving sales in restaurants and coffee shops that provide light meals. Conventionally, the turnover ratio of a store is calculated by dividing the number of customers visiting the store by the number of sales slips and dividing by the number of seats in the store. In addition, at restaurants and other places where chain development is being carried out, a guard is patrolled at each store,
They also check the entry status of customers at each store.

On the other hand, conventionally, a surveillance camera is provided in a store for the purpose of crime prevention, and an employee monitors a camera image, for example, at a cash register. This is also used for grasping a customer's turnover ratio. be able to. Generally, an image from a camera is monitored in real time, or an image recorded on a video tape is reproduced at 2 to 3 times speed for monitoring.

Further, by sequentially applying the images obtained from the surveillance camera to the processing device, a person in the image is automatically detected. In this technology, the background image prepared in advance is compared with the image captured this time to obtain the brightness difference for each pixel, thereby detecting the variable pixels in the monitoring area, and further determining the image characteristics such as the area and the perimeter. It is determined whether or not it is a human body. Also,
When a histogram is created by projecting a human image horizontally in this image processing, the histogram from the top of the head to the base of the neck becomes a mountain shape in the head, so the center point of the head is determined from the position of the apex of the mountain. A technique for obtaining and detecting the head position is also used.

[0005]

However, in the method of grasping the customer arrival state from the number of visitors appearing on the sales slip, it is difficult to grasp for each unit time because it is judged from the total number of visitors stated on the slip. It is impossible to determine whether the customer is temporarily full and the other customer has returned because the customer has been present for a long time, or whether the number of customers who come to the store is small. Therefore, there is a problem that it is difficult to grasp sufficient data for constructing a business strategy.

On the other hand, the method of circling a watchman to a plurality of shops can objectively grasp the situation in the shop, but since a non-resident watchman monitors each shop only for a certain period, the time zone, the day, the day of the week, etc. There is a problem that it is not possible to accurately grasp changes in customers due to seasons and the like, and it is not possible to obtain sufficient data as in the above. That is, it is desirable to constantly monitor each store in order to obtain sufficient data, but for example, a method in which the image of the surveillance camera is constantly monitored by the surveillance staff causes an excessive labor of the surveillance staff, as well as oversight of monitoring and work efficiency. In terms of reality. Even with the method of checking images recorded on a video tape at double speed, the human ability is limited to about three times speed, and a long monitor is still required to check all the business hours of the store.

Further, there is already a technique for automatically detecting a customer by processing an image of an in-store surveillance camera. However, in order to detect a person image on the screen, all pixels of a photographed image are prepared in advance. It is necessary to perform a difference process for obtaining a brightness difference or a brightness ratio with the background image, which requires a relatively large amount of processing. Further, in order to use it as sales data, it is necessary to have information such as the travel route of the customer in the store and its seating position, and more complicated and enormous work is required to detect this in image processing.
For this purpose, it is necessary to prepare a large-scale and high-performance device having a sufficient processing capacity, which is not realistic considering, for example, installing an image processing device in each store.

In view of such a problem, the present invention can detect the customer position in the store and the movement route thereof by a simple process, and the centralized process can be performed for each store. It is an object of the present invention to provide a surveillance camera system that reduces equipment load and an information providing system using the same.

[0009]

[Means for Solving the Problems] To achieve this purpose,
The present invention comprises a surveillance camera fixedly mounted and image processing means for processing images continuously captured at a predetermined interval from the camera, and detects a person image in the image to detect the reality of the person. In a surveillance camera system for determining a position in space, the image processing means detects a head of a person in the captured image, and coordinates of the head on the image (first coordinates). And a conversion table that associates the coordinates (second coordinates) of the floor portion in the real space of the shooting range of the camera with each other, and obtains the corresponding second coordinates from the first coordinates by referring to the conversion table. The conversion table sets in advance the second coordinates for the floor portion of the physical space in the photographing range of the camera, and the head of a person of a predetermined height is included in the image within the image. At the coordinate of 1 Of correspondence between feet of the person in case is located where the second coordinate it is characterized in that it is registered.

As described above, if the person's head is extracted from the image obtained from the surveillance camera so that the coordinates of the floor portion where the person is actually present can be obtained from the coordinates of the head on the screen, it becomes complicated. It is not necessary to accurately extract the whole-body image of a person by enormous image processing, and the processing can be simplified. Further, if the position of the person on the screen in the store is grasped by such processing, the customer's entry status can be accurately obtained without the surveillance staff constantly monitoring the image of the surveillance camera. .

In this surveillance camera system, the head detecting section extracts black from the photographed image, and removes the portion of the photographed image corresponding to the black portion in the background image from which the black is also extracted, and leaves the remaining portion. The person image in the image is grasped, and the top of the person image is detected as the head in the Y-axis direction of the photographed image. In this way, by extracting the person by simply excluding the black portion in the background image, the brightness difference or brightness ratio is calculated for all pixels in the captured image as in the conventional case, and this is binarized to change the brightness. It is not necessary to extract a part, and the processing load can be reduced.

On the other hand, the information providing system according to the present application detects a surveillance camera fixedly mounted and a person image in images continuously photographed from the camera at a predetermined interval to detect the person in the real space. The image processing means for determining the position, the first storage area for storing the captured image data in association with the control data including at least the shooting date and time and the person position, and the person in the image by reading the control data Personal data creating means for creating personal data, a second storage area for accumulating the personal data,
In an information providing system including a display unit capable of displaying the person data in an appropriate format, the image processing unit includes a head detection unit that detects a person's head in the captured image, and the head detection unit. The coordinates on the image (first coordinates) and the coordinates of the floor part in the real space of the photographing range of the camera (second coordinates)
And a person position determination unit that acquires the corresponding second coordinate from the first coordinate by referring to the conversion table, and the conversion table is stored in advance in the camera. Second coordinates are set for the floor portion of the physical space in the shooting range, and when the head of a person with a predetermined height is at the first coordinates in the image, the feet of the person are at the second coordinates. It is characterized in that the correspondence relation of where it is located is registered.

In this information providing system, the head detecting unit extracts black from the photographed image and excludes a portion of the photographed image corresponding to a black portion in the background image in which the black is extracted, and leaves a remaining portion. It is characterized in that it is grasped as a person image in the image, and the top of the person image is detected as a head in the Y-axis direction of the photographed image.

As described above, if the presence or absence of a person and the position thereof are acquired from the image of the surveillance camera by a simple process and the person data is displayed on the display means so that the data can be provided, for example, the restaurant manager can It is possible to easily understand the customer's stay time, turnover rate, etc. Therefore, it is not necessary to prepare a monitor stationed at all times, and labor and cost can be reduced.

Further, in this information providing system, the person data creating means continuously reads the control data and continuously obtains the position information of the person in the image, thereby moving the person in the image. It is desirable to create a history as the person data. Furthermore, the system
It is also possible to include a locus diagram creation unit that reads the person data and displays the movement route of the person in the image as a locus diagram on the display unit. In this way, if the movement history of the person in the screen is acquired and it is possible to display it as a locus map, for example, the store manager can grasp the movement route of the customer in the store, and the sheet of the store can be displayed. It can be useful for changing the layout and table / counter ratio.

Further, the system extracts requesting means for requesting image data by designating a shooting date and a shooting place condition, and image data matching the condition from the first storage area and extracting the image data. It is desirable to include image extraction means to be displayed on the display means. By configuring the system in this way, it is possible to confirm the actual image as necessary, and it is possible to perform a more detailed analysis of the management policy and also use it for purposes such as crime prevention.

Further, in this information providing system, the surveillance camera, the display means and the request means are the first.
The image processing means, the person data creating means, and the first and second storage areas are installed at a second point, and the first and second points are used for communication. It may be connected by a network. If the system is configured in this way, the images of the surveillance cameras of a plurality of stores are transmitted to a processing center including image processing means, person data creating means, and a storage area at any time, and the image processing is performed in the processing center. It can be done centrally. Therefore, it is not necessary to install a high-performance processing device for each store, and the information can be centrally managed.

Furthermore, the image processing method according to the present invention is an image processing for detecting the presence or absence of a person from photographed images obtained at fixed intervals from a surveillance camera fixedly installed and for determining the position of the person in the real space. In the method
A step of determining the presence / absence of a person in the image by comparing a background image photographed in a state where there is no person in the photographing range of the camera in advance, and the coordinates of the head of the person in the photographed image. It is characterized by including a step of detecting, and a step of determining at which position in the real space the person is from the coordinates of the detected head.

Here, the step of determining the presence / absence of a person in the image includes the step of extracting a black portion from the photographed image and the step of extracting the black portion from the photographed image corresponding to the black portion in the background image. It is characterized by including a step of excluding and a step of determining that there is a person if a significant black portion remains in the captured image after that.

Further, the step of detecting the coordinates of the head of the person is performed by detecting the uppermost coordinates in the Y-axis direction of the black portion remaining in the photographed image.

In the step of determining the position of the person, the step of previously setting the coordinates of the floor portion of the photographing range of the surveillance camera, and the step of associating the coordinates in the photographed image with the coordinates of the floor portion of the photographing range. And a step of determining the coordinates in the image of the feet of the person when the head of the person having a predetermined height is at the coordinates of the detected head, and the floor portion of the photographing range from the coordinates of the feet determined here. And deriving the coordinates of.

[0022]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below in detail with reference to the accompanying drawings. FIG. 1 is a diagram showing an overview of the information providing system according to the present invention. Referring to FIG. 1, stores A, B and C are connected to a processing center 20 via a high speed network 10. Each of the stores A to C is a restaurant or a coffee shop that provides light meals. For example, the store A has cameras A1 and A2 that are aimed at the seats in the store, and a processing center 2.
It comprises a request means 31 for making a data request to 0 and a display means 32 for displaying the data sent from the processing center 20. Stores B and C also have the same equipment as store A. In the following description, only store A will be described as a representative example of these stores, but stores B and C have the same configuration and operate in the same manner. In-store cameras A1, A
Reference numerals 2 are fixedly mounted toward the passenger seats, respectively, and pick up images every predetermined period (for example, 2 seconds) and sequentially transmit the image data to the processing center 20. Further, the image of the in-store camera may be displayed on the display device 32 in the store at the same time.

The high speed network 10 connecting the shops A to C and the processing center 20 is a communication network using, for example, an optical fiber cable, and is suitable for transferring relatively large data such as image data. However, the network 10 is not limited to this example as long as it is a communication network, and it does not matter whether it is a public network such as the Internet or a dedicated network.

FIG. 2 is a block diagram showing the configuration of the processing center 20. The processing center 20 includes a processing server 21.
And a large-capacity data storage 22. The processing server 21 includes a communication unit 23 that communicates with the stores A to C,
The operation of the entire processing center 20 is controlled, customer data such as person's movement record and stay time is created from the image data, a locus map of person's movement is created from the customer data, and in response to a request from request means. It is provided with a processing control means 24 for carrying out processing for delivering actual image data by means of an image processing means 25 and presence / absence of a person from the images sent from the stores A to C. On the other hand, the data storage 22 stores an image data storage area 26 in which image data sent from each store is stored together with control data to be described later, and a customer data recording area 2 in which data regarding a customer's stay in each store is stored.
7 and a screen / space coordinate comparison table 28 in which the correlation between the coordinates in the image sent from each store and the position coordinates in the actual store is registered.

FIG. 3 shows the image processing means 2 of the processing server 21.
6 is a flowchart for explaining a person position detecting process according to No. 5; In this step, whether there are people in the image,
If so, the purpose is to detect the position within the store. Here, the inventor of the present application pays attention to the fact that Japanese hair is black, and detects the presence or absence of a person and its position in the captured image by the black hair portion so as to achieve simplification of processing. There is.

The images taken by the in-store cameras continuously transmitted from the stores A to C are sent to the image processing means 25 via the communication means 23 of the processing server 21. Referring to the flow of FIG. 3, the image processing means 25 reads the image data for each frame (step S11) and extracts black from the image (step S12). This processing is performed by measuring the brightness of each pixel of the captured image and extracting only the pixels having a preset threshold value or less. Here, the purpose of this step is achieved if the hair portion can be detected, so if the threshold value is set low enough to detect only black or a color close to it, the processing load due to extraction of unnecessary portions can be avoided. it can. FIG. 4A shows an example of an image captured by the camera, and FIG. 4B shows a state in which black is extracted from the captured image.
Shown in.

Next, the image processing means 25 extracts the person image in the image by performing the difference processing with the background image prepared in advance (step S13). As this background image, a black image extracted in advance by the same process as described above is used from an image captured in a state where there are no persons in the photographing range of the camera. By excluding the part of the captured image corresponding to the black part in this background image, only the human image is extracted as shown in FIG. If there is a significant black portion in this image, it can be determined that there is a person image, and if there is no significant image portion (step S14). In this way, by extracting the person by simply excluding the black portion in the background image, the brightness difference or brightness ratio is calculated for all pixels in the captured image as in the conventional case, and this is binarized to change the brightness. It is not necessary to extract a part, and the processing load can be reduced.

Next, if there is a person in the image, the coordinates of the crown of the person are detected (step S15). This processing is performed by detecting the coordinates of the uppermost part of the black portion in the image shown in FIG. 4C. For example, scanning is performed from the upper end of the screen in the X-axis direction and the coordinates at which the first black pixel is hit are stored. To do so. By grasping the hit coordinates here as the top of the person's head, it is possible to perform complicated processing such as detailed area survey and feature extraction of the brightness fluctuation part that was conventionally performed to extract the person image. It becomes possible to grasp the position.

Next, the image processing means 25 refers to the coordinate comparison table 28 in the data storage 22, derives the actual position coordinates in the store from the coordinates of the person's head on the screen, and determines the position of the person. It is stored (step S16). This coordinate comparison table 28 has a standard height (for example, 140 to 180) at arbitrary coordinates on the screen.
cm) has the head of the person, the in-store coordinates where the person is located in the actual store are registered. That is, when a person with a standard height is within the imaging range, the correspondence between the coordinates of the head appearing on the screen and the coordinates in the store where the person is actually located is registered in advance in the comparison table. The image processing unit 25 can easily recognize the position of the person by referring to the image processing unit 25.

This will be described conceptually with reference to FIG. Since the surveillance camera in the store is fixedly installed toward the passenger seat portion, as shown in FIG. 5A, in-store coordinates are set in advance for the floor portion of the store in the photographing range. After that, when the head of the virtual person set to the height H (for example, 160 cm) is at arbitrary coordinates on the screen, the table 28 shows the correspondence relationship at which coordinate in the store the person's feet are located. register. In the example shown in FIG. 5A, when the head coordinates on the screen are (x ₁ , y ₁ ), the corresponding in-store coordinates are (b, 4) and the head coordinates are (x
The corresponding in-store coordinates when ( ₂ , y ₂ ) are (f, 2)
Is. All of these correspondences are registered in the table 28. FIG. 5B shows an example of the comparison table 28. In this way, the image processing means 25 can obtain the in-store coordinates of the person on the screen by referring to the comparison table 28.

The image processing means 25 obtains the in-store coordinates of the person from the head coordinates on the screen, and then stores the store code, camera code, shooting date and time in the image data read in step S11.
Control data such as the presence / absence of a person and the coordinates of the person in the store are added (step S17) and stored in the image data storage area 26 of the data storage 22 (step S18). An example of this data structure is shown in FIG. Information such as store A, camera A1, person position (b, 4), date and time is added as control data to the first half of the stored data. In this way, the image data continuously sent from the stores A to C are sequentially processed and stored in the data storage 22.

FIG. 7 is a flow chart for explaining the customer data creating process in the processing control means 24. When the control data is added to the image data by the image processing means 25, the processing control means 24 reads the control data (step S21). The processing control unit 24 refers to the presence / absence of a person in the image, and if there is no human image in the image, ends the processing as it is (step S22). Further, in this case, since it is considered that the image data itself is unnecessary, the entire data record may be deleted from the data storage 22. On the other hand, when there is a person in the image, the person code is given to the person, the time and the in-store coordinates of the person are read, and registered in the customer data recording area 27 of the data storage 22 (step S2).
3). FIG. 8 shows a configuration example of customer data registered in the customer data storage area 27. As shown in FIG. 8, for each record, an area for recording a customer code, a cell from coordinate 1 to coordinate n in which the travel route of the customer is registered, a staying time of the customer, a sitting seat, and the like is prepared. . By the process of step S23, when a new person is detected, the person code is added in descending order from 0001, and the time of the first detection and its in-store coordinates are registered in the column of "coordinate 1".

After that, the processing control means 24 reads the next data (step S24) and judges whether or not the person is out of the screen based on the presence / absence of the person image (step S25). If there is no person image on the screen, it is determined that the person has left the store, so the data recording is ended, and the person code is not recorded thereafter (step S26). On the other hand, if there is a person also in this data, it is determined whether or not the person position has changed from the previous data (step S27). This is performed by comparing the in-store coordinates of the current data and the previous data. If the in-store coordinates match, it is determined that there is no movement and recording is not performed (step S28). If the in-store coordinates do not match, it is determined that the person has moved, and the time and new in-store coordinates are recorded in the cells of coordinate 2 and later in this customer 0001 record (see FIG. 8). After that, the process returns to step S24, the next data is read, and the same process is performed. In this way, the movement record from when the customer frame-in the screen until frame-out is obtained.

After that, the processing control means 24 subtracts the first recorded time from the last recorded time for the person to obtain the staying time of the person, and records it in the staying time column shown in FIG. Further, of the data recorded for the person, the coordinates that have not moved for a predetermined period of time or the coordinates that have not moved for the longest time are determined to be the sitting position of the person, and the in-store coordinates are recorded. In this case, the seat number at the in-store coordinates may be registered in advance, and the seating seat of the person may be recorded by comparing with the coordinates. In the example shown in FIG. 8, the time of the coordinate 5 detected last for the person code 0001 is 11: 40: 2.
4, the time of the first detected coordinate 1 is 10:25:10
Therefore, by subtracting, it can be determined that the staying time of this person is about 1 hour and 15 minutes. Further, since the time points of coordinates 3 and 4 are the farthest apart, it is determined that the position of coordinate 3 is the seating location, and the coordinates are recorded as the seating seat of the customer. In this way, it is possible to accumulate the staying time and the seating seat information for each customer.

The image data and the customer data thus accumulated are delivered to an appropriate store as needed. In this case, the processing center 20 may, for example, deliver the customer data accumulated on the day after the store is closed to each store, or, for example, regarding the store A in response to a request from the request means 31 of the store A. The customer data may be distributed. The delivered customer data can be displayed and confirmed on the display means 32 of the store A. As a result, it is possible to grasp the number of customers visiting the store, the staying time, the seating seat, the moving route, and the like at each store. Therefore, the store side decides the product type and the table /
Can make improvement plans such as counter ratio.

Further, by using the customer data 27, it is possible to represent the travel route for each customer as a locus diagram as shown in FIG. 9, for example. FIG. 9 shows the locus of movement of the customer 0001 in the store shown in FIG. 8, and the position coordinates 1 to 1 of the customer are shown on the diagram in which the spatial coordinates in the store are shown as the X axis and the Y axis.
It can be obtained by marking 5 and connecting with lines in order. This data conversion processing may be performed by the processing control means 24 of the processing server 20 and then distributed to each store.
It may be performed at the store after receiving the customer data shown in FIG.

Since the image data sent from each store is also stored in the data storage 22 of the processing center 20, the image data can be distributed in response to the store's request. That is, for example, when the store side wants to confirm an actual image during analysis using customer data, the request means 31 transmits a request for image data to the processing center 20 by designating the store code, camera code, date, time, and the like. To do so. When the processing center 20 receives this request, the processing control means 24 extracts the image data matching the request information from the image data storage area 25 of the data storage 22,
Try to deliver to the requesting store. As a result, the actual image required can be confirmed on the store side, which enables more detailed analysis and can also be used for purposes such as crime prevention.

[0038]

As described in detail above, according to the present invention, since the person detection and the position determination in the image captured by the surveillance camera are performed by simple processing, it is relatively complicated and huge. It is possible to speed up the processing without the need for the conventional image processing. Thereby, for example, even when the processing center 20 receives a plurality of camera images from a plurality of stores, it is possible to operate the system without causing a processing delay.

Moreover, since the store side can accurately grasp the staying time and the moving route of the customer without preparing a monitor stationed at all times, the monitoring labor and the cost thereof can be reduced.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of an embodiment of an information providing system according to the present invention.

FIG. 2 is a diagram showing a configuration of a processing center 20 shown in FIG.

FIG. 3 is a flowchart illustrating a person position determination process of image processing means 25 shown in FIG.

FIG. 4 is a diagram illustrating an example of an image in a processing process of an image processing unit 25.

5A is a diagram for explaining spatial coordinates in the person position determination of the image processing means 25, and FIG. 5B is a diagram showing an example of a screen / spatial coordinate comparison table.

6 is a diagram showing a data structure stored in an image data storage area 26. FIG.

FIG. 7 is a flowchart illustrating a movement route determination process of the process control unit 24.

8 is a diagram showing a data structure registered in a customer data storage area 27. FIG.

FIG. 9 is a diagram showing a state in which a travel route of a customer is represented in a locus diagram.

[Explanation of symbols]

A to C stores A1, A2 surveillance camera 10 high-speed network 20 processing center 21 Processing server 22 Large capacity data storage 23 Communication means 24 Processing control means 25 Image processing means 26 Image data storage area 27 Customer data storage area 28 screen / space coordinate comparison table 31 Request Means 32 display means

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G06T 7/60 150 G06T 7/60 150B G08B 25/00 510 G08B 25/00 510F 510M H04N 5/915 H04N 5 / 91 K F term (reference) 5B057 AA19 CH01 DA07 DC22 DC32 5C053 FA11 GB06 GB40 JA16 JA22 JA24 KA24 LA01 LA14 5C054 CA04 CC05 CE14 CH02 DA06 EA05 FC03 FC15 FE00 FE02 FE09 GA00 GB02 GB05 GB15 GD01 A24 A05A03 A02 A05A0A02 A02 A05A0A02 DD20 EE01 EE02 GG02 GG06 GG19 GG21 5L096 BA02 CA02 FA14 FA69 GA08 JA11

Claims (12)

[Claims] 1. A surveillance camera fixedly mounted,
An image processing means for processing images continuously captured at a predetermined interval from the camera, the monitoring camera system for detecting a person image in the image and determining the position of the person in the real space, the image processing A means detects a head of a person in the photographed image, a coordinate (first coordinate) on the image of the head, and a coordinate of a floor portion in a real space of a photographing range of the camera. A conversion table that associates the (second coordinates) with each other, and a person position determination unit that refers to the conversion table and acquires the corresponding second coordinates from the first coordinates. A second coordinate is set for the floor portion of the physical space in the shooting range of the camera, and when the head of a person with a predetermined height is at the first coordinate in the image, the person's feet are the second
The surveillance camera system is characterized in that the correspondence relation of where the coordinates are located is registered. 2. The surveillance camera system according to claim 1, wherein the head detecting unit extracts black from the captured image, and extracts a portion of the captured image corresponding to a black portion in the background image in which the black is also extracted. A surveillance camera system characterized in that the remaining portion after exclusion is grasped as a human figure in the image, and the top of the human figure is detected as a head in the Y-axis direction of the photographed image. 3. A surveillance camera fixedly mounted,
Image processing means for detecting a person image in images continuously shot at a predetermined interval from the camera to determine the position of the person in the real space, and at least the shooting date and time and the person position in the shot image data. A first storage area for associating and storing control data including the same; a person data creating means for reading the control data to create person data for a person in an image; and a second storage area for storing this person data. An information providing system including a display unit capable of displaying the person data in an appropriate format, wherein the image processing unit detects a head of a person in the captured image, and the head detecting unit. Coordinates on the image (first
Table) and a coordinate (second coordinate) of the floor portion in the real space of the shooting range of the camera, and a second coordinate corresponding to the first coordinate with reference to the conversion table. A person position determination unit that acquires a position of the person in the image in which the second coordinate is set in advance for the floor portion of the real space in the shooting range of the camera, The information providing system, wherein a correspondence relationship of where the person's feet are located in the second coordinate when the person is in the first coordinate is registered. 4. The information providing system according to claim 3, wherein the head detecting unit extracts black from the captured image, and extracts a portion of the captured image corresponding to a black portion in the background image in which the black is also extracted. An information providing system, characterized in that a remaining portion after exclusion is grasped as a human figure in the image, and the top of the human figure is detected as a head in the Y-axis direction of the photographed image. 5. The information providing system according to claim 3, wherein the person data creating unit continuously reads the control data and continuously obtains position information of the person in the image. An information providing system characterized in that a movement history of a person in an image is created as the person data. 6. The information providing system according to claim 5, wherein the system further comprises a locus diagram creating means for reading the person data and displaying a moving route of the person in the image as a locus diagram on the display means. An information providing system characterized by comprising. 7. The information providing system according to claim 3, wherein the system further complies with the requesting means for requesting image data by designating a shooting date and time and a shooting location condition. The image data is the first
And an image providing unit which is extracted from the storage area of the display unit and is displayed on the display unit. 8. The information providing system according to claim 3, wherein the surveillance camera, the display unit, and the request unit are installed at a first point, and the image processing unit and the person data are created. The means and the first and second storage areas are installed at a second point, and the first and second storage areas are provided.
Is an information providing system characterized by being connected by a communication network. 9. An image processing method for detecting the presence / absence of a person and determining the position of the person in the real space from captured images obtained at fixed intervals from a surveillance camera that is fixedly installed. A step of determining the presence or absence of a person in the image by comparing a background image photographed in the absence of a person with the photographed image; a step of detecting the coordinates of the head of the person in the photographed image; An image processing method, comprising the step of determining, in the physical space, the position of the person from the coordinates of the head detected in. 10. The image processing method according to claim 9, wherein the step of determining the presence / absence of a person in the image includes a step of extracting a black portion from the captured image and a step of extracting a black portion from the background image. An image processing method comprising: a step of excluding a portion of a captured image corresponding to a black portion; and a step of determining that there is a person if a significant black portion remains in the captured image thereafter. 11. The image processing method according to claim 10, wherein the step of detecting the coordinates of the head of the person includes detecting the uppermost coordinates in the Y-axis direction of the black portion remaining in the captured image. An image processing method comprising: 12. The image processing method according to claim 9, wherein the step of determining the position of the person includes the step of setting the coordinates of the floor portion of the shooting range of the surveillance camera in advance, A step of associating the coordinates with the coordinates of the floor portion of the photographing range; a step of determining the coordinates of the person's feet in the image when the head of the person with a predetermined height is at the coordinates of the detected head; Deriving the coordinates of the floor portion of the photographing range from the coordinates of the foot determined in step 1.