EP1079350B1 - Space surveillance device - Google Patents

Abstract

A device has an image sensor (5), one or more presence or movement sensors (6) and an electronic controller-analyzer coupled to these sensors. Devices for detecting sabotage to any sensor store and check stable features for images picked up by the image sensor. Checking stable features is performed by testing an image of a room being monitored for stable features. Any stable features found are compared with stored images by using image-processing methods.

Description

The present invention relates to a device for room surveillance, with at least an image sensor and at least one presence or motion sensor and with one Control and evaluation electronics to which the sensors mentioned are connected.

For such facilities, also known as intrusion detectors, it is very important that they Attempts to sabotage can be detected, with sabotage affecting the entire detector or just one of the two sensors or sensor types. With motion sensors than today almost exclusively passive infrared sensors, ultrasonic or microwave sensors or off Dual sensors composed of these two sensor types are used Devices for sabotage monitoring, generally referred to as anti-mask devices known. In this connection, reference is made to EP-A-0 186 226, EP-A-0 499 177, the EP-A-0 556 898 and European patent application No. 99110848.1 by the applicant of the referenced this patent application.

The known anti-mask devices of passive infrared sensors have an infrared transmitter and an infrared receiver and are used to detect the two types of coverage of the detector, that is the cover of the detector in a certain, possibly only small, distance from the detector window, and the immediate coverage of the detector window by, for example, covering with a film or spraying with an infrared-opaque Spray, such as paint spray. The first type of cover is subsequently called the fem cover and the second is referred to as a spray cover, with fem cover a cover a few millimeters away up to a maximum of about 15 cm from the detector window is meant.

Operations or optical changes immediately in front of the detector, such as the remote cover in most cases a reflection of that from the infrared transmitter of the anti-mask device emitted radiation on the infrared receiver, which is due to a change in that from the infrared receiver received radiation expresses. To detect changes in the optical Properties of the detector window, this is exposed to infrared radiation and it the radiation passing through the detector window or reflected by it is measured. The signals from the infrared receiver are used to evaluate the signals of the anti-mask device compared with threshold or reference or general voltage values which are above or below and must be kept for a certain period of time.

In the case of ultrasonic or microwave sensors, the sabotage is monitored by: the ultrasonic or microwave transmitter by briefly switching on / off or off / on emits a short pulse, which creates a wide frequency spectrum, which then evaluated in a certain frequency range with regard to amplitude and time course becomes. The parameters mentioned are used for changes in the room in front of the detector typical deviations from mean values or previous measurement results are examined, in particular to such deviations that are necessary for the attachment of a shield or cover are characteristic of the detector.

Image sensors or video detectors, however, are not protected against sabotage, although it goes without saying There is also a risk of sabotage with these sensors. By the invention a device of the type mentioned at the beginning, the at least an image sensor is protected against sabotage.

This object is achieved according to the invention in that means for detecting sabotage of the at least one image sensor is provided, and that these means for storage and Check stable features of the image recorded by the image sensor are formed.

A first preferred embodiment of the device according to the invention is characterized in that that the stable features are checked by the fact that the image of the monitored space is examined for stable features, and the stable found thereby Features with methods of image processing can be compared with the saved ones.

A second preferred embodiment of the device according to the invention is characterized in that that means for measuring the brightness in the monitored room are provided, and that an alarm is triggered if there is a difference between the stored and the found stable characteristics.

The storage and checking of stable features according to the invention enables detection partial coverage of the detector or the pretense of wrong scenes by holding a photo in front of the image sensor or by changing the field of view of the detector. The stable features are saved immediately after installation of the facility; while The operation of the picture is then periodically examined for stable ones Features and a comparison of the found with the stored stable features.

A third preferred embodiment of the device according to the invention is characterized in that that the stable features by for the space to be monitored and / or the equipment of which characteristic edges and / or curves are formed.

A further preferred embodiment of the device according to the invention is thereby characterized in that the storage and verification of a plurality of stable characteristics and that an alarm is triggered when the number of saved with the stable features matching found stable features a threshold below.

As long as this threshold is not fallen below and a minimum number of already saved stable features is found, newly found stable features become the added saved. In this way it is possible to change the spatial model such as. Moving furniture and the like, constantly updating.

The stable features are preferably checked when the detector is not armed, or if there is no activity in the monitored room because the processor is underutilized during this time. The decision whether im monitored Room activities take place or not, preferably takes place on the basis of the signal of the presence or motion sensor.

The device according to the invention with at least one image sensor and at least one Presence or motion sensor points towards known dual detectors as well significant advantages over pure image sensors. Compared to the dual detectors, at where no or only a very rough spatial resolution is possible, so that a distinction Often it cannot take place between humans and animals Detectors much more robust. In addition, the image sensor offers the possibility of classification the objects based on their geometry and movement and thus the intelligent monitoring as well as the verification and storage of events and later accessibility of these.

Compared to a pure image sensor, the detector according to the invention has the advantage that it even in poor lighting conditions the performance of a presence or Provides motion detector and is therefore fully functional. In addition, the presence or Motion detector the image processing algorithms when interpreting difficult situations support.

In the following the invention with reference to an embodiment and the single drawing explained in more detail, the drawing being a block diagram of a device according to the invention for room monitoring shows.

The device for room monitoring shown in Fig. 1 consists essentially of a multi-criteria motion detector 1, hereinafter referred to as a detector, and one hereinafter referred to as electronics control and evaluation electronics 2 with a control stage 3 and a processing stage 4 for the local evaluation of the signals of the detector 1. Of course, this representation only shows the individual function blocks and not the specific ones apparatus construction of the facility again. For example, certain are usually Parts of the electronics are present in detector 1. The latter applies in particular if the detector signals are processed or pre-evaluated in detector 1.

The detector 1 consists of at least one image sensor 5 and at least one following presence or motion sensor 6, referred to as P / B sensor. In addition, the detector points Means 7 for measuring the brightness in the monitored room, which is preferably a component form the image sensor 5. Both the image sensor 5 and the P / B sensor 6 are one Preprocessing stage 8 or 9 downstream, but also in detector 1 or if necessary can be included in processing level 4. From preprocessing stages 8 and 9 the signals arrive in processing stage 4, which is also the brightness signal of the means 7 is supplied for brightness measurement.

Processing level 4 is autonomous and enables local decisions and / or display the images recorded by the image sensor 5; preferably it is also for transmission of the images to a spatially distant center 10, where, for example, an additional one Verification can take place.

The P / B sensor 6 is a motion or presence detector based on one of the known detection principles Passive infrared, active infrared, microwaves, ultrasound or any Combination of them. The image sensor 5 is in the range of visible light, in the near infrared or sensitive to long-wave infrared (heat radiation); he can on a usual imaging Process (CCD [CCD: charge-coupled device], CID [CID: charge injection device] or CMOS [CMOS: complementary metal oxide semiconductor = complementary metal oxide semiconductor structure]) based.

Preferably, a special CMOS image sensor, a so-called APS [APS: active pixel Sensor] used, which is characterized by a very low power consumption and by the possibility of access to individual pixels. In addition, in such APS additional application-specific analog or digital functions, for example simple Image processing algorithms such as filters or exposure control can be easily integrated. Regarding APS, the article "A 128 x 128 CMOS Active Pixel Image Sensor for Highly Integrated Imaging Systems "by Sunetra K. Mendis, Sabrina E. Kennedy and Eric R. Fossum, IEDM 93-538 and "128X128 CMOS Photodiode-Type Active Pixel Sensor With On-Chip Timing, Control and Signal Chain Electronics "by R.H. Nixon, S.E. Kemeny, C.O. Staller and E. R. Fossum in SPIE Vol. 2415/117.

The image sensor 5 is directed towards the space to be monitored, detects it in terms of image technology, digitizes the image and stores it as a reference image in a memory. If the the image sensor 5 forming APS consists of 128 by 128 pixels, for example, would then be used a wide-angle lens at a distance of 15 m in front of the image sensor 5 one pixel of approximately 12 by 12 cm. Such a grid is suitable, human and distinguish animal shapes relatively reliably from each other.

The possibility of recognizing a person at a distance of 15 m is very advantageous, and the area of the monitored room at this detection distance of about 15 by 15 m quite realistic. In the active state of the device, the image sensor 5 then makes intervals a picture of the monitored room from fractions of a second is saved Images for a certain time and compare them with the reference image and / or with each other. The storage of the images is preferably controlled in such a way that the images sent by the detector 1 immediately preceding and / or immediately following the detected event until saved further and that the remaining images automatically after the specified time to be deleted.

In order to make a usable picture even in poor lighting conditions can, the image sensor is 5-on high light sensitivity and a large dynamic range (sufficient recognizability of details with strong light / dark contrast) optimized. The functions integrated on the APS chip allow an automatic electronic Integrate closure with a dynamic of 1: 1000.

The P / B sensor 6 essentially serves to identify the potential weaknesses of the image sensor 5 compensate. This includes in particular that the image sensor 5 is below a critical one Illumination provides no image information, and that also a strong change in the image information is often not caused by an intruder compared to the reference image. you think, for example, of abrupt changes in lighting that by switching the street lighting on / off, passing vehicles with the lights on Headlights, thunderstorms or the like can be caused. In these and the like Cases by taking into account the signal of the P / B sensor 6, the robustness of the detector 1 significantly increased. This is taken into account by a combined evaluation the signals of the image sensor 5 and the P / B sensor 6 in the processing stage 4 realized.

It has been shown that it is advantageous to use the signals from the image sensor 5 and the P / B sensor 6 to undergo a separate pre-evaluation before the combined evaluation, which in the preprocessing stages 8 and 9 respectively. As already mentioned, the preprocessing stages 8 and 9 in the respective sensor 5 or 6 or in processing stage 4 be integrated. During the pre-evaluation, the signals of the P / B sensor 6 are combined into one Evaluation converted with the signal of the image sensor 5 suitable format and classified according to their strength. If detector 1 contains a distance meter (not shown), then this becomes corresponding in the presence of a signal from the P / B sensor 6 Starch from processing level 4 activated via control level 3 and delivers to the processing level information about the distance of the event just detected or Object from detector 1. With the help of this distance information, the signal from the image sensor can be used 5 clear conclusions on the size of a detected object and thus on its size Nature, such as humans or animals.

With the image sensor 5, the pre-evaluation takes the form of hardware and / or in the form of a processor core integrated on the APS chip. When pre-evaluating the signals, the number of compared the modified image of the reference image, its clustering and characteristics of the pixel cluster certainly. The reference image is constantly updated, whereby Changes are only adopted in the reference image after checking their stability. The reference image tracking can be more stable by including the signals of the P / B sensor 6 be carried out.

At the input of processing stage 4 there is a signal of the P / B classified according to strength Sensor 6, an image signal of the image sensor 5 with information about the number of changes Pixels and the characteristics of the pixel clusters and possibly a signal from the distance meter, the distance of the event triggering the signal of the P / B detector 6 indicates. In addition, the processing stage 4 receives from the means 6 for lighting measurement continuous information about the average lighting in the monitored room and weighted the combined evaluation of the signals the signals of the lighting-independent P / B Sensor 6, the weaker the lighting, the more so.

The combined evaluation of the signals gives a decision at the output of processing stage 4 Alarm or non-alarm, this decision essentially the image content, the overall lighting, the information from the P / B sensor 6 and the change and / or history of these parameters, hereinafter referred to as global criteria, are taken into account. Plausibility links are very helpful here: if, for example, lighting and change the image content quickly and strongly, but the signal of the P / B sensor 6 is weak, then no alarm is given, but the stability of the new image is checked and in it searched for movements. If the P / B sensor 6 reports no movement and only one Lighting and / or image change took place, then lighting became pretty certain switched on or off so that there is no alarm.

The facility for room surveillance shown largely corresponds to that in the European one Applicant's patent application no. 99103260.8 of the present patent application described two or multi-criteria detectors with an image sensor. For this reason here the signal processing is not described in detail, but it is based on the European Patent application referenced.

As already explained in the introduction to the description, the detector 1 is equipped with one device equipped for sabotage monitoring, namely for sabotage of both the P / B sensor 6 as well as the image sensor 5. The device for monitoring sabotage of the P / B sensor is an antimask device of the known type, the specific training of which detection principle implemented in the P / B sensor 6. For a detailed description of known ones Antimask devices are based on the patent applications cited in the introduction to the description directed. The following is the device for monitoring sabotage of the image sensor 5 are described.

It has already been mentioned that the image sensor 5 contains a memory in which the digitized Image of the monitored room is stored as a reference image. This memory is preferred integrated on the APS chip. Storage is now also carried out for sabotage monitoring of stable features in the reference image, a periodic examination of the Image sensor 5 recorded image for stable features and a check of the found stable characteristics based on a check with the stored. Under stable Features are to be understood as those features of the image that have a certain probability do not change, in particular boundary lines and edges of the room and of doors and windows, straight edges and general curves of larger pieces of furniture, and the same.

There are a number of such stable features according to known methods of image processing digitized and stored in memory. The features are considered symbolic-geometric Data written in a list. For example, a straight edge can pass through its Start and end point or a segment of a circle through its start and end point and additionally the radius or the center of the circle can be defined.

Periodically, preferably when there is no activity in the monitored room is present or even in the blurred state of the detector, the picture taken are examined for stable characteristics and the stable characteristics found are included compared the saved. For example, the distance between the Reference edge and a newly found edge can be determined. If this distance one does not exceed the previously defined value, then the edges are evaluated as matching.

The presence or absence of activity in the monitored space is checked with the. P / B sensor detected. If there is sufficient brightness (signal from means 7 for brightness measurement) no stable features are found or the stable features found tamper alarm will not be triggered. The former is a Indications that the image sensor 5 or the detector 1 was not completely covered (for example with a cloth or the like), the latter may indicate that the image sensor 5, for example by taking a photo in front of the lens, a wrong scene is faked.

When checking the stable features, you can also proceed in such a way that you get a larger one Number of for example ten stable characteristics stores and for the number of necessary Matches between stored and found stable characteristics sets a threshold. If the brightness falls below this threshold with sufficient brightness sabotage alarm is triggered and if the minimum number corresponding to the threshold value of matches, newly found stable features in the amount of stable characteristics stored was added. So it becomes possible that Spatial model for changes such as constantly updated when moving furniture.

• Teilweises Abdecken des Bildsensors,
• Vortäuschung einer falschen Szene z.B. durch ein Foto,
• Verdrehen des Melders in seiner Halterung (Veränderung des Blickfelds des Melders),
• Abreissen des Melders von der Wand.

The following types of sabotage can be detected with a device of the type described:

• Partially covering the image sensor,
• Feigning a wrong scene, for example with a photo,
• Rotating the detector in its holder (changing the field of view of the detector),
• Tear the detector off the wall.

Claims (10)

1. Space monitoring device, comprising at least one image sensor (5) and at least one presence or movement sensor (6), and comprising a control and evaluation electronics system (2) to which the said sensors (5, 6) are connected, characterized in that means are provided for detecting sabotage of the at least one image sensor (5) and in that these means are designed to store and check stable features of the image recorded by the image sensor (5).
2. Device according to claim 1, characterized in that the stable features are checked in that the image of the monitored space is investigated for stable features and the stable features found in this process are compared with the stored stable features using image-processing methods.
3. Device according to claim 2, characterized in that means (7) are provided for measuring the brightness in the monitored space and in that an alarm is triggered if, given adequate brightness, there is a difference between the stored stable features and the stable features found.
4. Device according to claim 3, characterized in that the said brightness measuring means (7) are integrated into the image sensor (5).
5. Device according to claim 3, characterized in that a sabotage alarm is triggered if no stable features are found.
6. Device according to one of claims 1 to 5, characterized in that the stable features are formed by edges and/or curves characteristic of the monitored space and/or its equipment.
7. Device according to claim 6, characterized in that a multiplicity of stable features are stored and checked and in that an alarm is triggered if the number of stable features found corresponding to the stored stable features under-runs a threshold value.
8. Device according to claim 7, characterized in that, if the said threshold value is not under-run and new stable features are found, an additional storage and addition of the latter to the stable features already stored is effected.
9. Device according to one of claims 1 to 8, characterized in that the stable features are checked when no activities are present in the monitored space.
10. Device according to claim 9, characterized in that the decision about the presence of activities in the monitored space is effected on the basis of the signal of the presence or movement sensor (6).

Images