EP1189187A2 - Method and system for monitoring a designated area - Google Patents

Abstract

The surveillance method evaluates images from at least 2 image recording devices (1,2) covering respective zones of the surveillance area, corresponding to critical and non-critical regions, separated from one another via an alarm boundary. The data relating to a detected position variation of an object in the zone covered by the first image recording device is supplied to the second image recording device. An Independent claim for a surveillance system is also included.

Description

The present invention relates to a method for monitoring a predetermined one Area that has at least two zones, one critical and one uncritical Represent the area and be separated from each other by an alarm limit, as well as a corresponding procedure.

For automated monitoring of sensitive areas or security areas As a rule, video surveillance cameras are used, by means of which the security area is visualized. For larger or more complex security areas used several video surveillance cameras with different viewing areas, because the field of view of a single video surveillance camera due to its size of the security area is not sufficient to completely capture it.

An exemplary security area is e.g. into a critical and an uncritical area divided, which are separated by an alarm limit. A variety of Video surveillance cameras are used to monitor this alarm limit. each Video surveillance camera is assigned a predetermined detection range, each a section of the security area visualized and part or all of it Field of view of the video surveillance camera includes an object that is in a certain detection area occurs, from the corresponding video surveillance camera is recorded. Furthermore, this video surveillance camera records the complete motion sequence of the object in its detection area, i.e. all changes of position of the Objects are perceived. In the event that the object is based on the uncritical Area exceeds the alarm limit in the direction of the critical area, triggers the Video surveillance camera alarm off.

Assuming, for example, that there is a security guard in the critical area can perform without triggering an alarm, the security guard also without triggering the alarm limit starting from the critical in Direction could exceed the non-critical area, an alarm would still be triggered if the security guard went back to the critical area. To do this Avoiding allows the security guard to be observed in full in the detection area of a video surveillance camera, i.e. a so-called Object tracking, to determine that the security guard is authorized to engage in the critical Area because he had started his inspection tour in the critical area and thus no alarm is triggered when the alarm limit is exceeded in this example becomes.

A major disadvantage of this method is that the alarm is triggered for the case that the security guard in the detection area of a first video surveillance camera exceeds the alarm limit from the critical towards the uncritical range, and in a detection range of a second video surveillance camera in returns the critical area beyond the alarm limit.

Based on the known prior art, the present invention Task based on creating a way when monitoring a predetermined Area with increased decision security to trigger alarm when an unauthorized Object enters a critical area.

This object is solved by the subject matter of claims 1 and 16.

Preferred embodiments of the present invention are the subject of the dependent claims.

In particular, the object of the present invention is achieved by a method for monitoring a predetermined area solved using images, the images at least are generated by a first and a second image capturing device and the predetermined area has at least two zones that are critical and non-critical Represent areas that are separated by an alarm limit. in this connection a predetermined detection area is assigned to each image capture device, and an object that enters the detection area of an image capture device is from the corresponding image capture device. From this image capture device data is recorded, the changes in the position of the object in the corresponding Describe the detection area. An object that is within the detection range of the the first image capture device occurs, is captured by the first image capture device, wherein data is recorded from the first image capture device that Describe changes in the position of the object in the corresponding detection area, and this data is sent from the first image capture device to the second Hand over image capture device.

An advantage of the transfer of the acquisition data to a first image acquisition device according to the invention to a second image capture device is that the second Image capture device has more data regarding the object being tracked, so that the decisive security when an alarm is triggered is increased significantly. Furthermore, this object transfer between the monitoring devices a complete monitoring of an object that is in the detection areas of several Image capture devices moved.

The detection areas of the first and second image detection devices are preferably formed such that they overlap in an overlap area or adjoin each other. The first image capturing device transfers those recorded by it Data unsolicited to the second image capture device in the event that the first image detection device determines that the object is in the detection range of the second image capture device will occur. According to another variant, the second image capture device in the event that it is in the detection area assigned to it Detects an object and determines that this object was previously in the detection area the first image capture device was, the first image capture device for transfer of the data recorded on the object.

According to a further preferred embodiment, the first image capturing device transfers the data recorded by it to an evaluation device, which via a Network is connected to the first and the second image capture device and which in turn transfers the data to the second image capturing device. According to a variant the evaluation device can send its data to the second image acquisition device without being asked passed in case it is determined that the object is in the detection area the second image capture device will occur. According to another The second image capturing device can be a variant if it detects an object, that enters the assigned detection area and that previously in the detection area of the first image capture device was the evaluation device for transferring the Prompt recorded data.

According to a particularly preferred embodiment of the present invention Alarm triggered when the object starts from the non-critical area towards the critical area crosses the alarm limit. However, no alarm is triggered if the object in the detection area of the second image detection device the alarm limit crossing from the non-critical area towards the critical area and previously the alarm limit in the detection area of the first image capture device has crossed from the critical area towards the uncritical area.

Preferably, the data indicate the change in the position of the object in the detection area describe an image capture device, at least information on, which have a motion vector, an average speed and motion direction components represents. Area data can thus be transmitted on the basis of this data, a section of the detection area of the second image capture device represent, in which the object based on the detection area of the first image detection device will occur. Here, the data preferably have information which represents the section of the detection area of the second image detection device, will enter the object.

According to a further particularly preferred embodiment of the present invention one of the image capture devices must be in order to capture an object in the capture area a so-called detection threshold value is exceeded, wherein in the section of the detection area of the second image capture device into which the Object will occur, the detection threshold is lowered after experiencing the data, that were handed over by the first image capture device.

An advantage of lowering the detection threshold is that the detection security of objects in the detection area of image capture devices, the Data passed by other image capture devices is increased. This is particularly advantageous in the event that an object e.g. due to different Visibility in the detection area of an image capture device can be detected very well while it is in the detection area of another, adjacent image detection device is difficult to see.

In particular, those from the first image capture device to the second image capture device transferred data are used to identify the Object to perform, which is significantly simplified based on the data passed.

Fig. 1

eine Seitenansicht einer Anordnung von Überwachungseinrichtungen gemäß einer ersten Ausführungsform der vorliegenden Erfindung;

Fig. 2

eine drei-dimensionale Illustration von zu überwachenden Sichtbereichen in der Anordnung gemäß Fig. 1;

Fig. 3

eine Draufsicht der Anordnung gemäß Fig. 1 in einem ersten Anwendungsbeispiel;

Fig. 4

eine Illustration einer Anordnung von Überwachungseinrichtungen gemäß einer zweiten Ausführungsform der vorliegenden Erfindung;

Fig. 5

ein Blockschaltbild eines Systems zur Bildauswertung gemäß einem Ausführungsbeispiel;

Fig. 6 bis 9

Blockdiagramme, die jeweils den detaillierten Aufbau einer Einzelkomponente des Systems zur Bildauswertung gemäß Fig. 5 darstellen;

Fig. 10

ein Blockdiagramm einer weiteren Ausführungsvariante des Systems zur Bildauswertung gemäß Fig. 5;

Fig. 11

eine Illustration eines beispielhaften Binärbilds in einem zwei-dimensionalen Koordinatensystem sowie eine Objektliste; und

Fig. 12

eine Illustration einer erweiterten Objektliste.

Further preferred embodiments of the present invention are explained in more detail with reference to the following figures. The figures contain:

Fig. 1

a side view of an arrangement of monitoring devices according to a first embodiment of the present invention;

Fig. 2

a three-dimensional illustration of viewing areas to be monitored in the arrangement according to FIG. 1;

Fig. 3

a plan view of the arrangement of Figure 1 in a first application example.

Fig. 4

an illustration of an arrangement of monitoring devices according to a second embodiment of the present invention;

Fig. 5

a block diagram of a system for image evaluation according to an embodiment;

6 to 9

Block diagrams each representing the detailed structure of an individual component of the system for image evaluation according to FIG. 5;

Fig. 10

a block diagram of a further embodiment of the system for image evaluation according to FIG. 5;

Fig. 11

an illustration of an exemplary binary image in a two-dimensional coordinate system and an object list; and

Fig. 12

an illustration of an expanded object list.

1 shows a side view of an arrangement of monitoring devices 1, 2 according to a preferred embodiment of the present invention. The monitoring facilities 1, 2 can be designed as common video surveillance cameras or as infrared or thermal imaging cameras. The monitoring devices 1, 2 are preferred each mounted on masts 3, 4, which are fixed in a site to be monitored 8 are anchored. Furthermore, the monitoring devices 1, 2 can be connected to any rigid or moving objects, for example on parts of a building.

For the exemplary case that the monitoring devices 1, 2 as monitoring cameras are executed, both surveillance cameras each have a so-called Viewing area 6, 7 of a length 11. The length 11 of the viewing area 5, 6, 7 depends on an orientation angle α of the monitoring devices 1, 2, and the detection properties the corresponding monitoring devices 1, 2. In the case of Surveillance cameras correspond to the detection properties, for example the optical ones Properties of the camera optics used.

The viewing areas 5, 6, 7 of different monitoring devices are preferably located 1, 2 such that they overlap each other by predetermined lengths 9, 10, so that a complete monitoring of the area to be monitored is made possible.

2 shows a three-dimensional illustration of the viewing areas 6, 7 of the monitoring devices 1, 2 from FIG. 1. The viewing areas 6, 7 are marked with a rectangular base with a base of length 11 shown, although in reality these viewing areas 6, 7 will generally be designed as so-called "viewing cones".

The viewing areas 6, 7 preferably overlap one another in such a way that likewise larger objects, for example, starting from the viewing area 6 into the viewing area 7 occur, also in the overlap area of the viewing areas 6, 7 of the length 10 can be fully captured.

3 shows a top view of the arrangement of the monitoring devices 1, 2 according to FIG Fig. 1 in a first embodiment. The monitoring devices 1, 2 serve in the illustrated embodiment for this purpose, for example an unauthorized approach to prevent objects on a runway 12 on an airport site. This will by means of the monitoring devices 1, 2 a control line KL1 is monitored and if a Object starting from a permitted area EB this control line KL1 in the direction of If the taxiway exceeds 12, the alarm is triggered.

In a first variant, if for example a person or a vehicle along a the control line from the permitted area EB indicated by an arrow 13 KL1 in the direction of the taxiway 12 is exceeded when crossing the control line KL1 in point 16 alarm triggered. The corresponding object first enters the Viewing area 6 of the monitoring device 1 and then crosses this viewing area 6 and the overlap area that this viewing area 6 with the viewing area 7 of the monitoring device 2 forms. The object is registered at the time of its entry Field of view 6 captured by the monitoring device 1 and its movement is determined by means of Object tracking tracks to the point where the object is in the overlap area entry. Object tracking means that the entire movement of the object is recorded in the viewing area 6, 7 of the monitoring device 1, 2. Preferably when entering the overlap area and thus into the view area 7, the object becomes from the monitoring device 1 to the monitoring device 2 by means of so-called "Visual Handover "or object handover and then from the monitoring device 2 continues to point 16 where the alarm is triggered. "Visual Handover "or object transfer means that the monitoring device 1 recorded data relating to the object of the monitoring device 2 become.

A second variant is indicated by means of an arrow 14, which illustrates that again any object such as a person or a vehicle along the direction of the arrow of the arrow 14 moves and the control line KL1 starting from the permitted area EB in the direction of the runway 12. This is when the control line is exceeded KL1 in point 17 alarm triggered. The corresponding object enters the viewing area 6 of FIG Monitoring device 1 and leaves this field of view 6 again before entering into the viewing area 7 of the monitoring device 2 and then crossing over the control line 1 in point 17. When the object enters the viewing area 7 of the monitoring device 2 it is determined that this object has previously covered the viewing area 6 crossed the monitoring device 1, whereupon the object from the monitoring device 1 is transferred to the monitoring device 2.

As is clear from these two variants, there is an advantage of the invention Object transfer in that the alarm triggering monitoring device 1, 2 over has more data regarding the tracked object than in the case of object tracking by a single monitoring device 1, 2, so that the decision security at the alarm trigger is increased significantly. For example, there are about 75% the movement of the object, which moves along the arrow 13, in the viewing area 6 of the Monitoring device 1 and only 25% in the viewing area 7 of the monitoring device 2, which triggers the alarm.

A third variant is shown by means of an arrow 15. An object that shows the path that described by the arrow 15, for example, an employee of the Be control personnel who walk the area between control line KL1 and runway 12, to eliminate any interfering objects. Here, the space between the Control line KL1 and taxiway 12 defined as a restricted area EEB by allowing certain objects to stay.

In the event that the control personnel remove the control line KL1 from this Interspace EEB in the direction of the permitted range EB exceeds z. B. since him in permitted area EB in the vicinity of the monitoring device 2 is something that he check no alarm is triggered. The inspection employee then leaves enters the viewing area 6 of the first monitoring device 1 along the arrow 15 after crossing the overlap area, the viewing area 7 of the monitoring device 2 and crosses the control line KL1 starting from the permitted range EB towards the runway 12 to its surveillance activity in the space EEB continue. The control employee is both in the viewing area 6 of the monitoring device 1, as well as in the viewing area 7 of the monitoring device 2 in each case along the path covered by the corresponding monitoring device 1, 2 tracked.

An object tracking that is only in the viewing area 7 and exclusively by the monitoring device 2 would lead to the result that the Control staff, starting from the permitted area EB, the control line KL1 in the direction the runway 12 has exceeded. So when crossing the control line KL1 triggered by the monitoring device 2 alarm. Because the control employee however is entitled to stay in the intermediate space EEB and the control line KL 1 first exceeded, starting from the space EEB in the direction of the permitted range EB this alarm would be a false alarm.

In order to prevent such a false alarm from being triggered, the monitoring device must 2 the "history" of the control employee is known, i.e. in the present example the path taken by the control personnel along arrow 15 in the field of vision 6 has covered the monitoring device 1. Accordingly, object tracking of the control employee in both viewing areas 6, 7, and the monitoring device 1 and the monitoring device 2, when making a decision is taken into account, it can be determined that the control employee leaves the Intermediate space has crossed the control line KL1 and then again by crossing the control line KL1 has returned to this space. That means it can it is found that in the present example no alarm is triggered because the exceeding the control line KL1 is a justified crossing.

As is clear from this third variant, there is a significant advantage of present invention in that in one area to be monitored, which in several Visible areas 6, 7 of several monitoring devices 1, 2 is divided, any Object monitored by means of object transfer between the monitoring devices 1, 2 without gaps can be, if necessary with a very high level of decision certainty the triggering of an alarm can be determined.

Another major advantage of handing over the property is that the security of detection of objects in the viewing areas 6, 7 of the monitoring devices 1, 2 increased is what is explained in more detail below.

For example, an object enters the viewing area 6, where it is from the monitoring device 1 is detected and where changes in position of the object are tracked and corresponding Data is recorded. In the event that an analysis of the data reveals that the object has the viewing area 6 in the direction of the viewing area 7 of the monitoring device 2 leaves, according to a variant, a notification from the monitoring device 1 sent to the monitoring device 2. The notification preferably includes information regarding the direction in which the object is moving and the recorded data so that the monitoring device 2 can determine which location the object will enter into the viewing area 7. The monitoring device can thus 2 recognize the object more easily when entering the viewing area 7 and to capture.

This is particularly advantageous in the event that the object z. B. due to different Visibility in the viewing area 6 is very easy to detect, while it is in the viewing area 7 is very difficult to recognize.

In the event that the detection and detection of the object by the monitoring devices 1, 2 in each of the viewing areas 6, 7 depends on a predetermined threshold value, which must be exceeded in order to record object data, for example trigger this threshold value in the monitoring device 2 is preferred based on the data sent by the monitoring device 1, so that the detection threshold is lowered accordingly. Lowering the Threshold value can take place for a sub-zone of the viewing area 7, into which the monitoring device 1 detected object is likely to occur, or for the complete Viewing area 7.

According to a further variant, a monitoring device 1, 2 that detects an occurrence of an object in their field of view 6, 7 is detected and changes in position of this object captures, record and analyze data to determine if the object may be from the Field of view 6, 7 of another monitoring device 1, 2 has occurred. At a the corresponding monitoring device 1, 2 can be positively analyzed by the other monitoring device 1, 2 data on the movement of the Request objects in the viewing area 6, 7 of this other monitoring device 1, 2.

This is particularly advantageous if an interfering object such as a spider is located moved over a section of a monitoring device 1, 2 and recognized as an object because this object takes into account its determined direction of movement the viewing area 6, 7 of another monitoring device 1, 2 should come. For the case that the requesting monitoring device 1, 2 has no data relating to the detected Object received from another monitoring device 1, 2 can be assumed that the detected object is not alarm relevant.

FIG. 4 shows an illustration of an arrangement of monitoring devices 19, 20 according to a further preferred embodiment of the present invention. The monitoring facilities 19, 20 can in turn be used as video surveillance cameras be executed or as infrared or thermal imaging cameras. The monitoring facilities 19, 20 are preferably each mounted on masts that are firmly in the ground are anchored. Furthermore, the monitoring devices 19, 20 can be connected to any rigid or moving objects, for example on parts of a building.

In the example shown, the monitoring devices 19, 20 are used, for example, for Supervision of a prison building. For the exemplary case that the monitoring devices 19, 20 are designed as surveillance cameras, both have surveillance cameras each have a viewing area 21, 22. The size of the monitorable Viewing area 21, 22 depends on the orientation of the monitoring devices 19, 20, as well as the detection properties of the corresponding monitoring devices 19, 20. In the case of surveillance cameras, the detection properties correspond for example the optical properties of the camera optics used. Furthermore are detected in both viewing areas 21, 22 of the monitoring devices 19, 20 Objects tracked.

In the present example, the assumption is that an object, such as a security guard, from the roof 18 of the building via a fire escape 25 into an allowed area EB can arrive without triggering an alarm. However, an alarm should be triggered when a Object, such as a breakaway, out of a window 24 into the permitted area EB arrives.

In the event that no object transfer between the monitoring devices 19, 20 takes place, a breakaway could thus open along an arrow 23 from a window 24 get the roof 18 and over the roof 18 and the fire escape 25 in the permitted range EB without triggering an alarm. If the property is handed over, it can be determined that the same object or the breakaway that is in the viewing area 22 of the monitoring device 20 from the roof 18 through the fire escape 25 in the permitted area EB, previously from a window 24 in the viewing area 21 of the monitoring device 19 from the Roof 18 has reached, which leads directly to the triggering of an alarm.

Fig. 5 shows an illustrative block diagram of an embodiment of an inventive Systems for image evaluation. In this system, a variety preferably delivers of surveillance cameras 1, 2 video signals, each for monitoring one of the corresponding camera 1, 2 are used for the field of view. The video signals from the cameras 1, 2 are each connected to an analog / digital converter 29 and digitized. The camera 1, 2 can be a common video surveillance camera or an infrared or Be a thermal imaging camera.

The digitized pixel data of the video signals of the corresponding cameras 1, 2 are each stored in a storage device 30, a storage device 30 preferably two different image memories or one image memory with two different ones Has storage areas, and wherein in the first image memory or first Memory area the digitized pixel data, which represent a respective current image, be stored and in the second image memory or second memory area digitized pixel data representing a reference image are stored.

The digitized pixel data of the current image compared to that of the reference image of each video signal to see differences between the two images, each generated by one and the same camera 1, 2 will determine. Thus, based on the digitized pixel data A binary image of a current image is generated in the pixels with the binary value "0" represent pixels whose data are related to the pixel data of the respective Reference images are unchanged, while pixels marked with the binary value "1" Represent pixels, i.e. Pixels of the current image, with their data related to the image data of the reference image a change in image was determined.

The binary images generated are in an object determination device 32 in each case related marked pixels examined, all connected pixels be assigned to an object, d. H. Objects are extracted from the binary images. Accordingly, an object corresponds to a coherent image area that is within a certain one of the storage cycle of the second memory or second Storage area dependent period has changed. Object data is stored in an object list of the extracted objects, the objects being stored, for example, as a die maximum horizontal and vertical extent of the marked pixel area circumscribing Rectangle or the like can be defined. The current object list is with a stored object list of the previous image compared and updated. there the objects extracted from the current binary image become those in the previous one Objects found by plausibility check, such as Check for minimal Distance, similar shape or the like are assigned and objects to which a certain one If no object has been assigned for a period of time, they are deleted again.

The object data thus generated are evaluated in an evaluation device 33 Detection of alarm-relevant objects and for triggering an alarm. In the evaluation device 33 data are preferably calculated, which result from the difference of a detection point, for example, the center of a new object and a saved one Center of an assigned object of the previous image results. Based The current object list can be updated with this data.

In particular, any object can be calculated by computing data, preferably a distance traveled, a horizontal and vertical directional component and one include the average speed of the object based on the previous duration, be used to over a certain object in the field of view of a camera 1, 2 to track the entire period of collection. For alarm-relevant object rectangles each of the first memory and the first memory area become the object corresponding digitized pixel data is read out, using known image processing methods in the image section read out image content features for the object be extracted. To determine the object size, the size of the extracted Rectangle and the number of marked pixels found within the rectangle are used. All features of the extracted and tracked objects are required with Feature criteria that are stored in a storage device 34 are compared and preferably an alarm is triggered if all criteria are met at the same time. in this connection the camera 1, 2 is selected by means of a selection device 28, in its field of vision the corresponding object is detected, and the corresponding video signal of the Current image of the selected camera 1, 2 is switched to one by means of a switch 48 Monitor 35 switched, with the alarm objects showing the associated vectors become.

FIG. 6 shows a detailed view of the memory device 30 from FIG. 5. The memory device 30 preferably comprises two image memories 36, 37, the digitized ones Pixel data of the current image are stored in the image memory 36. Furthermore periodically, the digitized pixel data in the second Image memory 37 stored in each case until image data is stored again the image memory 37 to be used as a reference image. The digitized pixel data the image memories 36, 37 become 31 in the image difference determination device compared with each other. Furthermore, the digitized pixel data from memory 36 are read out by the evaluation device 33 for feature extraction in relation on alarm-relevant objects.

FIG. 7 shows a detailed view of the image difference determination device 31 from FIG. 5. The image difference determination device 31 preferably comprises a subtraction device 38, an amount formation device 39 and a threshold value comparison device 40th

In the subtraction device 38, the digitized pixel data of the current Image compared with the digitized pixel data of the reference image and for each Differences in corresponding pixels are determined. From these differences amounts are formed for the individual pixels in the amount formation device 39, that are compared in the threshold value comparison device 40 with a predetermined threshold value which represents a decision threshold for a pixel change. By for example, this decision threshold will be changes caused by signal noise are eliminated. If the threshold is exceeded, a binary value is generated "1" generated for the corresponding pixel, i.e. for the pixel was one Image change detected and therefore this pixel is noted or marked. at If the threshold value is undershot, a binary value "0" is assigned to the pixel.

A binary image, the image changes, can be formed by means of the binary values generated in this way represented in the current image with respect to the reference image.

FIG. 8 shows a detailed view of the object determination device 32 from FIG. 5 Object determination device 32 preferably comprises a binary image memory 41, an object extractor 42 and an object correlator 43.

In the binary image memory 41, the binary image stored in the image difference determining means 31 is generated, stored. This binary image is generated by the object extractor 42 examined for contiguous and marked pixels in order to extract objects and corresponding object data are stored in an object list.

A major advantage of determining objects is that in the further Processing no longer individual pixels, only the extracted ones Objects are used, which increases the processing speed considerably.

The current object list with a stored object list is generated by means of the object correlator 43 compared and updated the previous image, using the one from the current one Binary image extracted objects from the objects found in the previous image be assigned by plausibility check.

FIG. 9 shows a detailed view of the evaluation device 33 from FIG. 5. The evaluation device 33 preferably comprises an object tracking device 44, a Feature extraction device 45 and an alarm object checking device 46.

The object tracking device 44 calculates data which are used to track an object in the Field of view of a corresponding camera 1, 2 can be used. Furthermore determined the object tracking device 44 in the event that an object covers the viewing area of a Camera 1, 2 leaves whether the object enters the field of view of another camera 1, 2. Thus, the object tracking device 44 can send a signal to the selection device 28 send to cause the video signal of the corresponding camera 1, 2 by means of the switch 48 is switched to the monitor 35,

The feature extraction device 45 reads the image data in the area of alarm-relevant object rectangles from the first image memory 36 in FIG. 6 and extracts in this image detail according to known image processing methods image content features for a corresponding Object. However, this feature extraction only happens for alarm-relevant objects, i.e. for objects that have a predetermined direction, size, speed, etc.

In the alarm object checking device 46, the features of the extracted and tracked Objects with the required feature criteria stored in storage device 34 compared.

FIG. 10 shows a block diagram of a further variant of the system according to FIG. 5, in which a reduction stage 47 between the analog / digital converter 29 and the memory device 30 is interposed. The reduction stage 47 serves to reduce the amount of data a video signal, for example by adding individual pixel data in groups to new pixel data that are stored in the storage device 30.

FIG. 11 shows a memory section of the binary image memory 41 from FIG. 8. The memory section is shown in the form of a 2-dimensional coordinate system 49 with an x-axis in the horizontal direction and y-axis in the vertical direction. Marked pixels are with crosses, i.e. Marked "X". In the present example there are two marked Pixel areas 50, 51 that have changed with respect to the reference image as objects 1 and 2 have been extracted. The extracted objects are rectangular, whereby object 1, that corresponds to the pixel area 50, has a height H1 and a width B1 and Object 2, which corresponds to the pixel region 51, has a height H2 and a width B2.

From the 2-dimensional coordinate system 49, data can be determined that the Coordinates x, y of the corresponding object center, the respective object height H, the represent the respective object width B and the number Px of the binary marked pixels. This data is entered in an object list 52.

In the present example, the center of object 1 is located, which is the pixel region 50 at x = 3.5 and y = 1.5. The object has a height of 2 pixels and one Width of 4 pixels and includes a total of 5 marked pixels.

12 shows an updated object list in which the data calculated by the object tracking device 44 has been supplemented. The current center of detection of an object is represented by the coordinates x _n and y _n and the last saved center of the object by the coordinates x _n-1 and y _n-1 . The values H _n-1 , B _n-1 and Px _n-1 indicate the last saved height, width or number of the marked pixels of the object. After evaluation of the new object data by the object tracking device 44, the updated object list is supplemented by the determined values for the amount of a movement vector s, an average speed v, a previous duration T and movement direction components R _H and R _V.

Object 1 has, for example, a current center of detection (2; 0). The last saved center has the coordinates (3.5, 1.5). According to the Pythagorean Theorem, this results in a distance to:

The values for the direction coordinates are: R H = x n - x n-1 = 2 - 3.5 = -1.5 R V = y n - y n-1 = 0 - 1.5 = -1.5

If a previous duration T = 2 of object 1 is assumed, the average speed of the object is: v = s / T = 2.1 / 2 = 1.05.

Claims (17)

A method of monitoring a predetermined area based on images generated by at least a first and a second image capturing device, the predetermined area having at least two zones representing a critical and a non-critical area, which are separated from one another by an alarm limit, and wherein a predetermined detection area is assigned to each image capture device, an object that enters the detection area of an image detection device is detected by the corresponding image detection device, Data are recorded by this image capture device, which describe changes in the position of the object in the corresponding capture area, characterized in that
an object entering the detection area of the first image detection device is detected by the first image detection device, data being recorded by the first image detection device describing changes in the position of the object in the corresponding detection area, and this data from the first image detection device to the second Image acquisition device are handed over. A method for monitoring a predetermined area according to claim 1, characterized in that the detection areas of the first and second image capture device overlap or adjoin one another in an overlap area. A method for monitoring a predetermined area according to claim 1 or 2, characterized in that the first image capture device transfers the data to the second image capture device without being asked, in the event that the first image capture device determines that the object will enter the capture area of the second image capture device. A method for monitoring a predetermined area according to claim 1 or 2, characterized in that the second image detection device detects an object that enters the assigned detection area and, in the event that the second image detection device determines that the object was previously in the detection area of the first image detection device , the first image capture device requests the transfer of the recorded data. A method for monitoring a predetermined area according to claim 1 or 2, characterized in that the first image acquisition device transfers the data to an evaluation device which is connected to the first and second image acquisition device via a network, and this evaluation device transfers the data to the second image acquisition device passes. Method for monitoring a predetermined area according to claim 5, characterized in that the evaluation device transfers the data to the second image capture device without being asked, in the event that it is determined that the object will enter the capture area of the second image capture device. A method for monitoring a predetermined area according to claim 5, characterized in that the second image detection device detects an object that enters the assigned detection area and, in the event that the second image detection device determines that the object was previously in the detection area of the first image detection device, the Evaluation device requests the transfer of the recorded data. Method for monitoring a predetermined area according to one of Claims 1 to 7, characterized in that the alarm is triggered when the object crosses the alarm limit starting from the uncritical area in the direction of the critical area. Method for monitoring a predetermined area according to one of claims 1 to 8, characterized in that no alarm is triggered when the object in the detection area of the second image detection device crosses the alarm limit starting from the non-critical area in the direction of the critical area and previously in the detection area of the first image detection device has crossed the alarm limit from the critical area towards the uncritical area. Method for monitoring a predetermined area according to one of claims 1 to 9, characterized in that the image capture devices are designed as video surveillance, infrared or thermal imaging cameras. Method for monitoring a predetermined area according to one of Claims 1 to 10, characterized in that the data which describe the changes in the position of the object in the detection area of an image capture device comprise at least information which represents a motion vector, an average speed and motion direction components. Method for monitoring a predetermined area according to one of claims 1 to 11, characterized in that on the basis of the data which describe the changes in the position of the object in the detection area of the first image detection device, area data are determined which represent a section of the detection area of the second image detection device into which the object will enter. Method for monitoring a predetermined area according to one of Claims 1 to 12, characterized in that the data which are transferred from the first to the second image capture device comprise information which represents the section of the capture area of the second image capture device into which the object enters becomes. A method for monitoring a predetermined area according to claim 5 or 6, characterized in that in order to detect an object in the detection area of one of the image detection devices, a detection threshold must be exceeded and in the section of the detection area of the second image detection device into which the object will enter, the detection threshold is lowered. A method for monitoring a predetermined area according to claim 2, characterized in that the second image capturing device uses the data recorded by the first image capturing device, which describe the changes in the position of the object in the overlap area, to identify the object. System for monitoring a predetermined area by means of at least one first and second image capture device, the predetermined area having at least two zones, which represent a critical and a non-critical area and are separated from one another by an alarm limit, the first and second image capture devices each having: a device for assigning a predetermined detection area, a detection device for detecting an object that enters the assigned detection area, and a recording device for recording data describing changes in the position of the object in the assigned detection area, characterized in that
a device for transferring the data recorded by the first image capture device to the second image capture device is provided. System for monitoring a predetermined area according to claim 16, characterized in that the image capture devices are designed as video surveillance, infrared or thermal cameras.

Images