JP2007274656A - Video monitoring device and method therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a video monitoring device and a video monitoring method capable of monitoring the trespass of an animal body in a monitoring area set in a background image photographed by a monitoring camera simply and reliably. <P>SOLUTION: A device body 1 has a control unit 10 for processing information on the control of the entire device, and an image processor 11 for processing a photographed video image. A monitoring area setting section 10a sets the monitoring area. A foreign matter extractor 11a extracts a foreign matter related to the animal body based on the monitored image photographed by a photographing camera 2. A foreign matter area setting section 11b sets a foreign matter area including the entire foreign matter. A determination section 11c determines whether the monitoring area includes coordinates positions at a lower end in the set foreign matter area, and determines the presence or absence of foreign matters, in a region where the foreign matter and monitoring areas overlap each other, when it is determined that the coordinates positions at the lower end in the foreign matter area are included in the monitoring area. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a video monitoring apparatus and method for monitoring an abnormal state using a photographing unit such as a monitoring camera.

  In such a video monitoring apparatus, a video taken every predetermined time by a monitoring camera or the like is displayed on a monitor such as a CRT, and the monitor monitors the presence or absence of an intruder. If surveillance cameras are installed at a plurality of locations and the captured images are concentrated and displayed at a surveillance center or the like, it is possible to easily remotely monitor a plurality of locations simultaneously.

However, since it is very laborious for the monitor to constantly check the image displayed on the monitor, it automatically detects that an intruder or other moving object has entered the captured image. There has been proposed a monitoring device that informs a monitoring person of an abnormality. For example, in Patent Document 1, a difference image is generated by comparing an optical image captured by an imaging unit and a reference image, a difference value between a distance to an object measured by a laser ranging unit and a reference distance is calculated, It describes that the intruder is determined in consideration of the correlation between the position of the optical image change area and the distance measurement point where the distance change has occurred. Further, Patent Document 2 describes that a warning sound is generated when a change area on an acquired video frame or image is detected, and the warning sound is changed based on the position and degree of the change area. ing. Further, in Patent Document 3, a three-dimensional scene model of a scene to be monitored and a three-dimensional object model of a monitoring target object are constructed, a three-dimensional monitoring area is generated by computer graphics, and an installation parameter of the photographing apparatus is used. The point that the monitoring area is cut out from the image captured by setting the monitoring area on the screen is described. In Patent Document 4, the number of pixels w between lines for each scanning line is counted from an image in which parallel lines having a width W in the real space are displayed as indices, and each scanning line is based on the ratio of W and w. The point which calculates the distance corresponding to is described.
JP 2002-208073 A JP 2005-328236 A JP-A-6-35443 JP 2002-42142 A

  When image processing is performed based on video captured by the surveillance camera to automatically recognize moving objects such as intruders, moving objects other than the monitoring area may be recognized. For example, since a person walking in front of the monitoring area is also a moving object, if it is automatically recognized and notified, unnecessary notification is performed. Further, when a plurality of persons are crowded, the images of the persons photographed by the surveillance camera are overlapped, so that the recognition is difficult, and there is a disadvantage that it is likely to lead to a false notification.

  SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a video monitoring apparatus and method capable of easily and reliably monitoring the moving object that has entered the monitoring area set in the background image captured by the monitoring camera. It is.

  The video monitoring apparatus according to the present invention is based on a photographing unit for photographing a monitoring area, a monitoring area setting unit for setting a monitoring area based on a background image photographed by the photographing unit, and a monitoring image photographed by the photographing unit. Whether or not the monitoring area includes the extraction means for extracting the foreign matter related to the moving object, the foreign matter area setting means for setting the foreign matter area that includes the entire extracted foreign matter, and the coordinate position of the lower end of the set foreign matter area Area determining means for determining whether or not the coordinate position of the lower end of the foreign object area is included in the monitoring area, and foreign object determining means for determining the presence or absence of the foreign object in a region where the foreign object area and the monitoring area overlap. It is characterized by being. Further, the foreign matter area setting means sets a circumscribed rectangle including the entire extracted foreign matter as the foreign matter area.

The video monitoring method according to the present invention sets a monitoring area based on a background image photographed by a photographing means, extracts foreign matter related to a moving object based on the monitoring image photographed by the photographing means, and extracts the entire extracted foreign matter A foreign object area is included, and it is determined whether the coordinate position of the lower end of the set foreign object area is included in the monitoring area, and it is determined that the coordinate position of the lower end of the foreign object area is included in the monitoring area. It is characterized by determining the presence or absence of foreign matter in a region where the foreign matter area and the monitoring area overlap.
In the present invention, “animal body” refers to an object that moves within the monitoring area, and “foreign object” refers to “animal body” data extracted from image data in the monitoring area.

  By having the above configuration, it is possible to reliably determine that the moving object has entered the set monitoring area. That is, by setting a foreign object area that includes the entire foreign object related to the moving object and determining whether the coordinate position of the lower end is included in the monitoring area, the foot position that is estimated to be grounded is detected in the monitoring area. It is possible to check whether or not an intrusion has occurred, and if it is determined that the coordinate position of the lower end of the foreign object area is included in the monitoring area, the presence / absence of foreign objects is determined in the overlapping area of the foreign object area and the monitoring area Thus, it is possible to reliably check the invasion of the moving object into the monitoring area only by the limited area.

  In particular, in the case of a foreign object in which a plurality of moving objects overlap, conventionally, it is necessary to perform image processing with a heavy load such as determining the presence or absence of infiltration by individually separating the foreign object. Thus, accurate determination can be made by a simple process such as setting a foreign matter area including the presence of foreign matter in a region overlapping the coordinate position of the lower end and the monitoring area.

  Accordingly, it is possible to quickly and accurately determine the intrusion of the moving object into the monitoring area, and it is possible to minimize erroneous notification.

  Hereinafter, embodiments according to the present invention will be described in detail. The embodiments described below are preferable specific examples for carrying out the present invention, and thus various technical limitations are made. However, the present invention is particularly limited in the following description. Unless otherwise specified, the present invention is not limited to these forms.

  FIG. 1 is a schematic block diagram showing an embodiment according to the present invention. The apparatus main body 1 includes a monitoring camera 2 that is a photographing means for a monitoring area, an information input device 3 for inputting information necessary for operation, an alarm device 4 that notifies when a monitoring target object is determined, a monitoring video, and the like Is connected.

  The apparatus main body 1 includes a control unit 10 that performs information processing related to control of the entire apparatus, an image processing unit 11 that performs image processing of a captured video, and noises such as lighting fluctuations from the video captured by the surveillance camera 2. An image input unit 12 for acquiring an image of a monitoring area, an image memory 13 for storing an input image 13a output from the image processing unit 11, a processed image 13b, a background image 13c, and the like, a program necessary for control processing, and monitoring to be described later A storage unit 14 that stores area setting data 14a and foreign object area setting data 14b, and an image output unit 15 that displays an image on the monitor 5 are provided.

  The control unit 10 includes a monitoring area setting unit 10a that performs a setting process such as a coordinate position that defines the monitoring area based on the monitoring area setting information input from the information input device 3.

  The image processing unit 11 includes a foreign matter extraction unit 11a, a foreign matter area setting unit 11b, and a determination unit 11c.

  The foreign matter extraction unit 11a creates a differential image by comparing a specific captured image with another captured image in a series of accumulated captured images, and determines a change area of the specific captured image based on the differential image. Let it be a foreign object. Such a method is used to identify an intruder from a video in a video monitoring device or the like, and is a known technique. Then, the image of the area specified as the foreign object is cut out and extracted. In the present embodiment, the foreign object is specified based on the difference image between the background image 13c and the captured image. The background image 13c stores, as a background image, an image captured by the monitoring camera 2 in a state where there is no moving object in the monitoring area when the monitoring device is installed.

  The foreign matter area setting unit 11b demarcates the foreign matter area so as to include the entire extracted foreign matter and performs setting processing of data such as the coordinate position. If the foreign object area is set to a circumscribed rectangle that circumscribes the entire foreign object, the entire foreign object can be reliably included, and the process of setting the coordinate position, etc. can be simplified. Also good.

  The determination unit 11c determines whether or not the set coordinate position of the lower end of the foreign object area is included in the monitoring area, and if the lower end coordinate position is included, the presence or absence of the foreign object in the overlapping area of the foreign object area and the monitoring area is determined. Determination is made, and if there is a foreign object in the overlapping area, a warning process is performed.

  FIG. 2 is a flow relating to the foreign object determination process. First, a background image obtained by capturing a monitoring area in advance when the monitoring camera 2 is installed is acquired (S100). For example, as shown in FIG. 3, a background image may be generated by shooting in a state where the moving object does not exist in the monitoring area. Then, the background image is displayed on the monitor 5, and the coordinate position of the monitoring area is set by demarcating the outer periphery of the image area corresponding to the monitoring area by the information input device 3 such as a mouse (S101). As shown in FIG. 4, a hatched area P at the bottom of the background image is set as the monitoring area.

  Thus, when the acquisition of the background image and the setting of the monitoring area are completed, the image captured by the monitoring camera 2 is captured (S102), and foreign matter extraction processing is performed (S103). The captured image and the background image that have been captured are compared to generate a difference image to extract foreign matter. As shown in FIG. 5, when a plurality of persons are walking, the captured images of each person overlap each other, and therefore foreign objects are extracted in a state where the images of each person overlap.

  Then, it is determined whether the extracted foreign matter is a foreign matter corresponding to the monitoring target object (S104). For example, in the case of an extremely small size image or the like, it is determined that the image is not an image of the monitoring target object, and the process returns to step S102 to capture the next image.

  If it is determined that the object is a foreign object of the monitoring target object, a foreign object area including the entire foreign object is set (S105). For example, as shown in FIG. 5, a circumscribing rectangle R including all the foreign objects of a plurality of persons is defined, and the coordinate position and the like are set as a foreign object area. By setting such a foreign substance area, it is possible to perform subsequent determination processing without separating the individual images constituting the foreign substance.

  Next, it is determined whether the coordinate position of the lower end of the set foreign object area is within the monitoring area (S106). As shown in FIG. 6, in the case of a foreign object area defined by a circumscribed rectangle R, the lower end side (line segment specified by the coordinate position (x1, y1) and coordinate position (x2, y1) of the image area) ) Is included in the monitoring area P, and in this example, it is determined that it is included.

  By determining whether or not the coordinate position of the lower end of the foreign object area is included in the monitoring area, it is estimated that the coordinate position at the lowermost end is a grounded step even in the case of a foreign object consisting of a plurality of persons. Whether or not the foot position has entered the monitoring area can be determined without omission.

  If it is determined in step S106 that the coordinate position of the lower end of the foreign matter area is included, the presence / absence of foreign matter is determined in the overlapping region of the foreign matter area and the monitoring area (S107). As shown in FIG. 7, in this example, there is an overlapping area A between the circumscribed rectangle R and the monitoring area P, and the coordinate position of the area A is calculated based on the set coordinate positions of both. can do. If the presence / absence of the foreign matter extracted in step S103 is determined in the calculated region A, the presence / absence of the foreign matter in the limited region is determined. Therefore, the monitoring target object has entered the monitoring area with a simple process. It can be determined whether or not.

  When it is determined that the coordinate position of the lower end of the foreign object area is included, as shown in FIG. 7, the foreign object itself may include a case where it does not enter the monitoring area. However, as shown in FIG. By checking the presence or absence of foreign matter in A, it is possible to accurately determine whether or not the foreign matter has entered the monitoring area, excluding such cases.

  As described above, even when a foreign object is extracted in a state where a plurality of moving objects overlap, it is possible to reliably determine whether or not the object has entered the monitoring area with simple processing without being separated into individual images. Thus, it is possible to quickly and accurately determine the foreign matter.

It is a schematic block diagram regarding the embodiment concerning the present invention. It is a flow related to a foreign matter determination process. It is an example of an image regarding a background image. It is an example of the background image which set the monitoring area. It is explanatory drawing regarding a determination process. It is explanatory drawing regarding a determination process. It is explanatory drawing regarding a determination process. It is explanatory drawing regarding a determination process.

Explanation of symbols

S: moving object, P: monitoring area, R: circumscribed rectangle, 1 ... device body, 2 ... monitoring camera, 3 ... monitor.

Claims (3)

  An imaging unit for imaging the monitoring area, a monitoring area setting unit for setting the monitoring area based on the background image captured by the imaging unit, and a foreign object related to the moving object are extracted based on the monitoring image captured by the imaging unit. An extraction unit, a foreign object area setting unit that sets a foreign object area that includes the entire extracted foreign object, an area determination unit that determines whether the coordinate position of the lower end of the set foreign object area is included in the monitoring area, and a foreign object An image monitoring apparatus comprising: a foreign substance determination unit that determines whether or not a foreign object area and a monitoring area overlap when it is determined that the coordinate position of the lower end of the area is included in the monitoring area .   The video monitoring apparatus according to claim 1, wherein the foreign matter area setting unit sets a circumscribed rectangle including the entire extracted foreign matter as a foreign matter area.   Set a monitoring area based on the background image photographed by the photographing means, extract foreign matter related to the moving body based on the monitoring image photographed by the photographing means, set a foreign matter area that encompasses the entire extracted foreign matter, It is determined whether the coordinate position of the lower end of the set foreign object area is included in the monitoring area, and the foreign object area and the monitoring area overlap when it is determined that the coordinate position of the lower end of the foreign object area is included in the monitoring area. A video monitoring method characterized by determining the presence or absence of foreign matter.

Images