JPS62222397A - Emergency monitor - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

Detailed Description of the Invention (Technical Field) The present invention relates to an abnormality monitoring device that uses a plurality of sensors to detect the presence or absence of an abnormality within a monitored area, and is mainly used for crime prevention purposes such as intrusion and theft, and for fire prevention. It is used for detection, etc.

(Background Art) Conventionally, in this type of abnormality monitoring device, it has been determined whether or not an abnormality has occurred for each individual sensor. Therefore, there is a problem in that malfunction of one sensor causes a false alarm from the abnormality monitoring device. Furthermore, since each sensor is independent and does not mutually use information, there is a problem in that high detection reliability cannot be obtained.

On the other hand, in an image recognition type abnormality monitoring device, as shown in FIG. Based on the knowledge of
An apparatus has been proposed (Japanese Patent Application No. 60-227398) in which an abnormality determination means 2 is provided for analyzing an abnormality, and the determination result is outputted by an output means 3. Since the information is analyzed by the inference unit 21 based on the knowledge for abnormality determination stored in the knowledge base 22 in advance, the accuracy of abnormality determination is extremely high. 5 is relatively expensive and cannot monitor a very wide area.

(Object of the Invention) The present invention has been made to solve the above-mentioned problems, and its purpose is to organically use information from a plurality of sensors distributed within a monitoring area. An object of the present invention is to provide an abnormality monitoring device that dramatically improves detection reliability by determining the presence or absence of an abnormality.

(Disclosure of the Invention) In the abnormality monitoring device according to the present invention, as shown in FIG. 1, a plurality of sensors 1.
．． 12. . . , In and the previously stored knowledge for abnormality determination, each of the above-mentioned sensors 11.12.・
..., 1n, and includes an abnormality determining means 2 for determining the presence or absence of an abnormality from the information obtained by 1n, and an output means 3 for outputting the determination result. The abnormality determination means 2 includes a plurality of sensors 1. ．． 12. ..., has a function of determining the presence or absence of an abnormality in the inference unit 21 based on the knowledge for abnormality determination stored in the knowledge base 22 in advance from the information obtained by In. This allows individual sensors 1. ．． 12. ...
, 1n alone, which is difficult to detect, can significantly improve detection reliability.

Embodiments of the present invention will be described below with reference to the accompanying drawings. Second
The illustrated embodiment is the simplest example in which the abnormality monitoring device of the present invention is used as an intrusion monitoring device. In this embodiment, there are a plurality of sensors ζ, a facing infrared sensor 1a,
A tail sensor 1b and a glass breakage sensor 1c are used. The facing infrared sensor 1a is placed on the wall,
This device detects people climbing over the fence.The infrared emitter is placed at one end of the buried earth, the infrared receiver is placed at the other end of the earth, and an infrared warning line is created along the top edge of the fence. is posted. When an intruder blocks this infrared warning line, the infrared receiver detects the infrared rays being interrupted and sends an abnormality detection signal to the abnormality determining means 2. An ultrasonic reflection type object detection sensor, an electric field detection type human body detection sensor, etc. are arranged under the eaves of a house, and this is used as a tail side sensor 1b that detects approach to the side of the house. Tail sensor 1
When approaching the house is detected by b, a detection signal is sent to the abnormality determining means 2. A glass breakage sensor 1c is attached to the window glass of a house.

The glass breakage sensor 1c detects whether or not the glass is broken and inputs a detection signal to the abnormality determining means 2. The abnormality determination means 2 determines whether the target (object to be monitored) is abnormal (that is, an intruder) based on the temporal characteristics of how the target (object to be monitored) moves within the warning area set in this way. The knowledge base 22 stores rules for determining whether the sensor is abnormal or not abnormal (household member, dog, cat, etc.) as knowledge for abnormality determination, and each sensor la.

The information of 1b and 1c is analyzed by the inference unit 21 based on the above-mentioned rules, and the presence or absence of an abnormality can be determined with high accuracy. For example, if an abnormality is detected only by sensor 1c (glass breakage sensor), it is assumed that this is a false alarm from the glass breakage sensor, or that a household member accidentally broke the glass, and no alarm is issued. If an abnormality is detected in the order from sensor la (facing infrared sensor) to sensor lb (tail sensor), and then sensor lc (glass breakage sensor) is also detected, it is determined that this is an intruder. . On the other hand, if sensor 1a detects an abnormality and then sensor 1b does not operate within a predetermined period of time, it is determined that a cat or crow is on the fence, and no alarm is issued. Not working, sensor 1b
When activated, it is determined that a householder is under the eaves of the house, and no alarm is issued.

In addition, an illumination meter that measures the ambient illuminance is added as a fourth sensor, and an alarm is issued only when sensors 1 a, 1 b, and 1 c operate in sequence during the day, and at night, sensor l
When a and lb operate in sequence, or sensor lb.

It is also possible to change the warning rules at night and during the day, such as issuing an alarm when 1c operates in sequence.

In the above description of the embodiments, the case where the abnormality monitoring device of the present invention is used as an intrusion monitoring device to a house has been explained, but the application of the present invention is not limited to this, and it can be used as a fire detection device or a factory intrusion monitoring device. Needless to say, it can be widely applied to various abnormality detection applications such as safety monitoring devices.

(Effects of the Invention) As described above, in the present invention, information from a plurality of sensors distributed in a monitoring area is organically used, and pre-stored knowledge for abnormality determination is obtained. Since the presence or absence of an abnormality is determined based on this, it is possible to accurately determine an abnormality, and the detection reliability is dramatically improved compared to conventional devices.

[Brief explanation of drawings]

Figure 1 is a claim correspondence diagram showing the basic configuration of the present invention, Figure 2 is a claim correspondence diagram showing the basic configuration of the present invention.
The figure is a block diagram of one embodiment of the present invention, and FIG. 3 is a block diagram showing the configuration of a conventional example. 11.1□, . . . , 1n are sensors, 2 is an abnormality determination means, and 3 is an output means.

Claims (1)

[Claims] (1) an abnormality determination means that determines the presence or absence of an abnormality from information obtained by each of the sensors, based on a plurality of sensors arranged within a monitoring area and pre-stored knowledge for abnormality determination; An abnormality monitoring device comprising: output means for outputting the determination result.