JP2004295798A - Security system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a low cost security system which can decide whether a photographed moving object is an intruder accurately and actuate a notifying means, only if the object is an intruder. <P>SOLUTION: The security system is composed of a monitoring camera 51 takes photographs of a moving object and outputs it as animation data; a frame stripping off means 54 inputs the animation data and divide it into frame images with a certain time interval; a conversion means 58 decides whether two frame images separated in turn have any change on the image by pixel and transforms the frame image into numerical string data, on the basis of determined results; a code-generating means 59 generates geometrical codes, corresponding to a shape profile of the moving object, on the basis of the numerical string data, a deciding means 63 decides whether the moving object is a human being, on the basis of the geometrical codes; and an notification control means. The notification control means actuates a notifying means, when the moving object is decided as being a human being. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a security system, and more particularly, to a security system capable of detecting an intruder by an imaging unit such as a camera.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, as a security system for preventing a suspicious person from invading, a system that incorporates a monitoring camera and detects a suspicious person (intruder) based on captured image data is known. Specifically, only the background is imaged and stored by the imaging means, and the difference between the stored background image data and the monitoring image data is acquired. Based on the difference image data, the presence or absence of an intruder is determined. Recognize. When the intruder is recognized, the informing means is activated to intimidate the intruder, and is reported to a base station of a security company or a management company through a telephone line.
[0003]
The above prior art is naturally performed by those skilled in the art, and the applicant does not know the document describing this prior art.
[0004]
[Problems to be solved by the invention]
However, in a conventional security system, even if an operable moving object is detected by a surveillance camera, it is difficult to determine whether it is an intruder (human) or an animal such as a dog or a cat. there were. In other words, humans and animals may be erroneously recognized because their contours change as needed due to their movements. In particular, since the distance of the moving object with respect to the surveillance camera always changes, the size of the moving object to be imaged becomes indefinite, making it more difficult to distinguish an intruder. For this reason, in a house where pets such as dogs and cats are kept indoors, when residents go out, do not go out with their pets or put pets in circles or crates and move around indoors And other measures were required. That is, since the pet cannot be left out of the room while being left indoors, the system is extremely inconvenient.
[0005]
In view of the above circumstances, the present invention provides a security system capable of accurately determining whether or not a captured moving object is an intruder, and operating the notification means only when the intruder is an intruder. To provide.
[0006]
[Means for Solving the Problems]
The security system according to the first invention includes an imaging unit that captures an image of a moving object and outputs moving image data thereof, and a shape data generating unit that generates shape data corresponding to a contour shape of the moving object based on the moving image data. Based on the generated shape data, determining means for determining whether or not the moving object is a human, and a notification control for operating a notifying means when the determining means determines that the moving object is a human. Means.
[0007]
According to the present invention, shape data corresponding to a contour shape of a moving object is generated based on moving image data captured by an imaging unit such as a monitoring camera. The determining means determines whether the moving object is a human or another moving object (for example, a pet) by comparing the generated shape data of the moving object with preset human shape data. When the determining means determines that the moving object is a human being, that is, an intruder, the notification control means activates the notification means. Examples of the notifying means include a sound generating means and a light generating means for intimidating an intruder, and a notifying means for notifying a base station of a security company or a management company through a communication network or the like. On the other hand, even when a moving object is detected, if it is determined that the moving object is not a human, the notification unit is not operated. For this reason, even if a pet or the like is left indoors and goes out, malfunction of the notification means is prevented.
[0008]
A security system according to a second aspect of the present invention includes: an imaging unit that captures an image of a moving object and outputs moving image data thereof; a frame separating unit that receives the moving image data and separates the image into frame images at predetermined time intervals; For two frame images, a conversion unit that determines the presence or absence of an image change for each pixel or for each small area divided in advance, and converts the frame image into numerical sequence data based on the determination result. Data generating means for generating shape data corresponding to the contour shape of the moving object, determining means for determining whether the moving object is a human based on the shape data, and the moving object by the determining means. And a notification control unit that activates the notification unit when it is determined that the user is a human.
[0009]
According to the present invention, the moving image data is separated into frames by the frame separating means, and the subsequent recognition processing is performed based on the frame image. The time interval of the frame separation at this time is appropriately set according to the speed of the operation to be recognized, the accuracy of the recognition, and the processing capability.
[0010]
In the changing means, a change in the image between the two frame images is determined for each pixel or for each small region divided in advance, and a numerical value based on the determination result is given. For example, when it is determined that there is a change, “1” is output, and when it is determined that there is no change, “0” is output. In this way, the frame image is changed to the numerical sequence data. After that, the data generating means generates shape data corresponding to the contour shape of the moving object based on the numerical value sequence data. The determining means determines whether the moving object is a human or another moving object (for example, a pet) by comparing the generated shape data of the moving object with preset human shape data.
[0011]
When the determining means determines that the moving object is a human being, that is, an intruder, the notification control means activates the notification means. On the other hand, even when a moving object is detected, if it is determined that the moving object is not a human, the notification unit is not operated. For this reason, even if a pet or the like is left indoors and goes out, malfunction of the notification means is prevented.
[0012]
By the way, in the first invention or the second invention, "the determination means determines whether the contour shape of the entire moving object is vertically long or horizontally long. In this case, there is provided an aspect ratio determining means for determining that the moving object is a non-human moving object. "
[0013]
According to this configuration, it is determined whether the outline shape of the entire moving object is vertically long or horizontally long, and if it is vertically long, it is determined that the moving object moves in an upright posture, that is, a human. On the other hand, when the contour shape is horizontally long, it is determined that the moving object moves in the prone posture, that is, an animal such as a dog or a cat.
[0014]
Also, in the first invention and the second invention, "the determining means is a part specifying means for specifying a body part included in the subject based on the generated shape data, and a shape of the specified part And a part determining means for determining whether the moving object is a human or not in accordance with the moving object.
[0015]
According to this configuration, the body part included in the subject is specified based on the shape data generated by the shape data generating unit. In other words, the shape data representing the contour shape of each part such as the head, the torso, and the foot is stored in advance, and the shape data generated by comparing the generated shape data with the stored shape data. It is specified which part the shape data represents. Then, it is determined whether the detected moving object is a human or another moving object in accordance with the detailed contour shape of the specified part and the relation with other parts.
[0016]
Here, the following determination unit can be exemplified as a specific determination unit.
(1) A joint discriminating unit that discriminates based on “the formation of the joint of the foot” when the specified part corresponds to the vicinity of the “foot”.
(2) A head determining unit that determines based on “the position of the head with respect to the torso” when the specified part corresponds to the vicinity of the “head”.
(3) A shoulder width determining unit that determines based on “the width of the shoulder width relative to the head” when the specified part corresponds to the vicinity of the “head”.
(4) A tail discriminating unit that discriminates based on “the presence of a tail” when the specified part corresponds to the vicinity of the “tail”.
[0017]
Here, (1) is a means that is effective when the side of the moving object is imaged. Since the joints are different between the feet of a dog or the like and the feet of a human, the shape near the joint is changed. By making the determination, it is determined whether the object is a human or another moving object. The means (2) is effective when an image of the side of a moving object is taken. For a human whose head is located above the torso, an animal such as a dog has a head in front of the torso (or (Obliquely above), the position of the head relative to the torso is determined to determine whether the object is a human or other moving object. (3) is a means that is effective when the front or back of the moving object is imaged. Since the width of the shoulder width (torso width) differs between a human and other moving objects, the width of the shoulder width relative to the head is large. Then, it is determined whether the object is a human or a moving object other than the human. Note that, by making a determination based on the head, regardless of the distance between the imaging means and the moving object, that is, regardless of the size of the detected moving object, the width of the shoulder width (body width) is relatively recognized. It becomes possible to do. (4) is a means that is effective when an image of the side of a moving object is taken. Since a human does not have a tail like a dog or the like, the presence or absence of the tail is determined by determining whether or not the human has a tail. Is a moving object.
[0018]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, a security system according to an embodiment of the present invention will be described with reference to FIGS. 1 is an explanatory diagram showing the configuration of the entire security system, FIG. 2 is a block diagram showing the functional configuration of a security device in the security system, and FIG. 3 is a function of the server and the first information terminal device in the security system. FIG. 2 is a block diagram showing a typical configuration. FIG. 4 is a block diagram showing a functional configuration of the image recognizing means. FIGS. 5 and 6 are explanatory diagrams for explaining an image recognizing method. FIG. 7 shows a flow of processing in the image recognizing means. It is a flowchart.
[0019]
The security system of the present embodiment is a system that prevents crimes such as theft by suspicious persons (intruders) and improves the safety of residents in daily life. As shown in FIG. 1, the security system 1 includes a server 2 composed of a computer, a plurality of security devices 4 installed in a resident's house, a first information terminal device 6 a owned by the resident, and possessed by the resident. It is provided with a second information terminal device 6b and a third information terminal device 6c possessed by a friend, immediate family, etc. who is a notifier of emergency information. The server 2 and the security device 4 are connected by a wireless communication line NL via a network 3 using a packet communication method, and the server 2 and the first information terminal device 6a, the second information terminal device 6b, and The third information terminal device 6c is connected by a communication line L via a wide area network 5 such as the Internet.
[0020]
Here, the packet communication network 3 is used between the server 2 and the security device 4 to transmit and receive communication information TD such as status information and emergency information. The packet communication system is a communication system in which data is divided into small units and transmitted and received one by one. In the packet communication, in the communication between the two points, the line on the way is not occupied by other communication data, so that the communication information TD can be reliably transmitted and received between the server 2 and the security device 4.
[0021]
In addition, between the server 2 and the first information terminal device 6a, the second information terminal device 6b, and the third information terminal device 6c, in consideration of the development of communication network and the spread of information terminal devices (for example, mobile phones). Therefore, a network 5 such as the Internet is used. As a result, information can be distributed over a wide area, so that the resident or the emergency information notifier can be reliably notified of the communication information TD.
[0022]
The security device 4 is installed at a resident's house to detect indoor abnormalities, and also to provide state information on the indoor state when the abnormalities are detected and emergency information to notify an emergency state when the resident's physical condition deteriorates. The communication information TD is transmitted to the server 2 as shown in FIG. 2. As shown in FIG. 2, a device main body 7 which forms the core of the security device 4, a remote controller 8 for occupants to operate, a doorway, a window, And a plurality of external sensors 9 installed in a room or the like.
[0023]
The apparatus main body 7 has, as a functional configuration, a communication control unit 12 for transmitting and receiving to and from the server 2 by the receiving unit 10 and the transmitting unit 11, a signal receiving unit 13 for receiving various wireless signals from the remote controller 8 and the external sensor 9, Detection signal recognizing means 15 for recognizing a detection signal transmitted when the external sensor 9 or the internal sensor 14 incorporated in the apparatus main body 7 detects an abnormality, and generating state information based on the detection signal; And status information output means 16 for outputting the information via the transmission means 11. Further, the apparatus main body 7 has a built-in monitoring camera 51 and an image recognition means 52 for recognizing an intruder based on moving image data output from the monitoring camera 51. The details of the image recognition means 52 will be described later.
[0024]
Further, the apparatus main body 7 utters a warning message by the speaker 19 and sounds the siren 20 based on the sound storage means 18 in which the sound data of the warning message is stored and the state information generated by the detection signal recognition means 15. And an operating means 22 for recognizing a generation instruction KD, which will be described later, and operating the voice control means 21. Accordingly, when the external sensor 9 or the internal sensor 14 detects an abnormality, or when an intruder is recognized based on moving image data output from the monitoring camera 51, a warning message is issued from the speaker 19. At the same time, since the siren 20 rings, the intruder who has entered the room is intimidated and promptly evacuated, and crimes such as theft can be prevented. Here, the speaker 19 and the siren 20 correspond to the notification means of the present invention, and the voice control means 21 corresponds to the notification control means of the present invention.
[0025]
The main unit 7 is operated using a household power supply as a main power supply. However, since a backup power supply (not shown) such as a battery is built in, the intruder can output the power while the warning message is being issued. Even if it is removed, it is possible to intimidate the intruder by issuing a warning message without stopping.
[0026]
Further, in the apparatus main body 7, the emergency switch 23 is pressed, the predetermined switch provided on the remote controller 8 is continuously pressed for a certain period of time, or the emergency switch of the waterproof remote control (not shown) is pressed. An emergency signal recognizing means 24 for recognizing at least one of the operations and generating emergency information based on the emergency signal, and an emergency information output means 25 for outputting the emergency information via the transmitting means 11. ing. Since the emergency information is notified to the third information terminal device 6c of a friend or immediate family member (emergency information notifier) of the resident via the server 2, the emergency information is suitable for living alone or living in an elderly household.
[0027]
The remote controller 8 is operated by the resident to input the operation of the apparatus main body 7 and the setting of the mode, and the like. The remote controller 8 further includes a warning unit (not shown) for generating an alarm sound as a functional configuration. ing.
[0028]
Next, the server 2 in the security system 1 will be described. As shown in FIG. 3, the server 2 receives various types of information via the networks 3 and 5, and performs processing in accordance with the information, and is installed in a state where the management company can use it. Although not shown, the hardware configuration is similar to that of a general-purpose computer, but is used to directly input information such as a central processing unit (CPU) including a main storage device, an arithmetic device, and a control device, and a keyboard and a mouse. , An output device such as a display for taking out information processed in the computer, and a communication means such as a modem for transmitting / receiving data.
[0029]
The server 2 has, as a functional configuration, a first information control device 28a that performs transmission and reception with a plurality of security devices 4 by a receiving unit 26 and a transmitting unit 27, and a first information terminal device 6a by a receiving unit 29 and a transmitting unit 30. , A second communication control means 31 for transmitting and receiving to and from the second information terminal device 6b and the third information terminal device 6c, and a storage means 32 for storing resident data JD. The resident data JD stores personal information about the resident, and stores therein the e-mail address M1 of the resident's information terminal device, the e-mail address M2 of the emergency information notifier of the resident, and the like in association with each other. ing.
[0030]
Further, the server 2 includes a state information recognizing unit 33 that recognizes the state information output from the state information output unit 16 of the security device 4, and the state information recognized by the state information recognizing unit 33 and the residence stored in the storage unit 32. State information specifying means 34 for specifying the second information terminal device 6b for notifying the state information based on the user data JD, emergency information recognizing means 35 for recognizing the emergency information output from the emergency information output means 25, Based on the emergency information and the resident data JD recognized by the information recognizing means 35, the emergency information specifying means 36 for specifying the third information terminal device 6c for notifying the emergency information, the state information specifying means 34 and the emergency information specifying means 36 Sending means for sending status information and emergency information as email to the second information terminal device 6b and the third information terminal device 6c specified by 7, generation instruction recognition means 38 for recognizing the generation instruction KD (details will be described later) output from the first information terminal device 6a, and the generation instruction KD recognized by the generation instruction recognition means 38 and the resident data JD. And a generation instruction notifying unit 39 for notifying the operation unit 22 of the security device 4 of the generation instruction KD.
[0031]
When the server 2 recognizes the state information, the management company that manages the server 2 first calls the resident's house where the security device 4 that has output the state information is installed, and checks the state of the resident's house. Then, if necessary, a security guard or the like is rushed to the resident's house. Further, when the server 2 recognizes the emergency information, the third information terminal device 6c thereafter detects whether or not the e-mail is opened, and the e-mail is not opened even after a predetermined time (for example, 10 minutes) elapses. In this case, a contact is made with the immediate family or the like who is the owner of the third information terminal device 6c by telephone, or a caretaker or the like is rushed to support the resident. If the condition is severe, an ambulance is arranged. As a result, a resident whose physical condition has deteriorated can be immediately rescued even if he / she cannot contact his or her immediate family.
[0032]
The status information notified from the server 2 to the second information terminal device 6b and the emergency information notified from the server 2 to the third information terminal device 6c are distributed by e-mail, and require a specific terminal device. Instead, it is possible to receive status information and emergency information using an information terminal device that is widely used, such as a mobile phone. In addition, once an e-mail is sent, it will not be erased unless it is operated on the information terminal device side. It is possible to recognize.
[0033]
Next, the first information terminal device 6a, the second information terminal device 6b, and the third information terminal device 6c in the security system 1 will be described. The first information terminal device 6a, the second information terminal device 6b, and the third information terminal device 6c are the same type of information terminal device such as a mobile phone, and the one that outputs a generation instruction KD when operated by a resident is described. One that functions as one information terminal device 6a, and that the status information output from the security device 4 is notified from the server 2 functions as the second information terminal device 6b, and that the emergency information output from the security device 4 is transmitted from the server 2 What is notified functions as the third information terminal device 6c.
[0034]
In this embodiment, since the first information terminal device 6a, the second information terminal device 6b, and the third information terminal device 6c have substantially the same functional configuration, the configuration of the first information terminal device 6a is representative. Will be explained. The first information terminal device 6a includes a communication control unit 42 for transmitting and receiving to and from the server 2 by the receiving unit 40 and the transmitting unit 41; a storage unit 43 for storing the e-mail transmitted from the server 2; A display control means 45 for displaying the received e-mail on a display means 44 such as a liquid crystal screen, an operation means 46 including ten keys and function instruction switches, and a voice control means 21 of the apparatus main body 7 to activate a warning message. And a generation instruction output means 47 for outputting a generation instruction KD for producing an utterance.
[0035]
Meanwhile, the security system 1 of the present embodiment includes an image recognition unit 52 as a characteristic configuration. The image recognition means 52 detects a moving object based on moving image data output from a surveillance camera 51 such as a CDD camera (corresponding to the imaging means of the present invention), and determines whether the moving object is a human (intruder). It has a function of determining whether it is a non-human moving object (for example, a pet). More specifically, as shown in FIG. 4, a functional configuration includes a frame separating unit 54, a converting unit 58, a code generating unit 59, and a determining unit 63. The frame separating unit 54 receives moving image data from the monitoring camera 51 and generates frame images (still images) separated at predetermined time intervals (for example, every 0.1 second). The separated frame image is stored in the image storage unit 56 of the storage device 55. Here, the reason why the image is stored in the image storage unit 56 is to compare with the previous frame image when the latest frame image is separated.
[0036]
The conversion unit 58 has a change determination unit 60 that reads the latest frame image and the previous frame image separated at a predetermined time interval from the image storage unit 56 and determines whether or not there is a change in the image for each pixel. The frame image is converted into numerical sequence data based on the determination result. More specifically, the change determination unit 60 compares the amount of change detected for each pixel with a predetermined threshold value, and determines a pixel whose change amount is larger than the threshold value as a moving pixel (moving pixel). Pixel). As a result, only a moving part can be extracted from the subject. That is, it is possible to separate the background with no movement and the moving object with movement from the subject. Therefore, the conversion means 58 outputs, for example, “1” for a moving pixel and “0” for a still pixel, and then arranges the numerical values in a predetermined order to obtain a numerical value sequence for a moving object. Create data.
[0037]
The code generation means 59 generates a shape code corresponding to the contour shape of the moving object based on the numerical sequence data generated by the conversion means 58, and has a coordinate detection means 61 and a line segment calculation means 62. are doing. The coordinate detecting means 61 obtains a plurality of characteristic points for a curve constituting the contour shape of the moving object, and detects the coordinates. For example, as shown in FIG. 5A, when the shape of the extracted moving object is a human upper body, vertices T1, T2, T3,... Tn of a plurality of curves constituting the contour shape are set as feature points. Set. By connecting these feature points, a polygon having a simplified outline shape, that is, a figure consisting of only straight lines as shown in FIG. 5B is formed. The line segment calculating means 62 calculates the lengths B, C, D,... Of the line segments connecting the feature points, and the interior angles b, c, d,. , And a shape code (for example, BbCcDd...) Composed of a combination of an inner angle and an inner angle. Here, the shape code corresponds to the shape data of the present invention, and the code generating means 59 corresponds to the data generating means of the present invention.
[0038]
The determination means 63 shown in FIG. 4 determines whether the moving object is a human (intruder) or a pet such as a dog based on the shape code generated by the code generation means 59. Here, an aspect ratio determining means 64, a part specifying means 65, and a part determining means 66 are provided. First, the aspect ratio determining means 64 determines whether the contour shape of the entire moving object is vertically long or horizontally long. If the object is vertically long, the moving object is a human, and if it is horizontally long, the moving object is a non-human moving object. Is determined. This is because, as shown in FIG. 6, the human H often moves in a standing posture, and the animal A such as a dog or a cat often moves in a prone posture. Is determined.
[0039]
On the other hand, the part specifying means 66 specifies a body part included in the subject based on the shape code generated by the code generating means 59. In the code storage unit 57 of the storage device 55, a shape code representing the contour shape of each part of the body such as the head, the torso, and the foot is stored in advance, and the generated shape code and the code storage unit 57 are stored. By comparing the generated shape code with a shape code stored in the form code, the generated shape code is identified as a shape code representing a portion. For example, when a shape code that is elongated and extends in the vertical direction is generated, the shape code is identified as a shape code indicating a foot.
[0040]
The part determining means 66 determines whether or not the detected moving object is a human according to the part specified by the part specifying means 65. Specific examples of the discrimination include a joint discrimination unit 67 for the foot, a head discrimination unit 68 for the head, a shoulder width discrimination unit 69 for the shoulder, and a tail discrimination unit 70 for the buttocks.
[0041]
When the part specified by the part specifying unit 65 corresponds to the vicinity of the “foot”, the joint determining unit 67 determines based on “the formation of the joint of the foot”. This is because, as shown in FIG. 6, the leg of the human H has the “U” shape due to the bending operation of the femur 71 and the tibia 72 extending up and down around the knee, whereas the dog H Since the foot of the animal A has an inverted "C" shape in which the tibia 73 and the metatarsal 74 extend in the vertical direction from the front, the difference between these shapes is considered. It is determined by using the information. In other words, if the generated shape data is in the shape of a “ku” in the traveling direction (moving direction), it is determined that the person is a human H (intruder). If so, it is determined that the animal is an animal A such as a dog. This determination is effective when the moving object crosses the monitoring camera 51 in the left-right direction, that is, when the side surface of the moving object is imaged.
[0042]
When the part specified by the part specifying unit 65 corresponds to the vicinity of the “head”, the head determination unit 68 determines based on “the position of the head with respect to the trunk”. As shown in FIG. 6, when the moving object is viewed from the side, the head of the human H is located above the torso, whereas the head of the animal A such as a dog is located obliquely above the torso. Therefore, the determination is made using the difference between these relative positions. That is, when the size of the moving object hardly changes, that is, when the moving object crosses the surveillance camera 51 in the left-right direction and the head is positioned above the trunk, the human H (invading On the other hand, if the head is positioned diagonally above or in front of the torso, it is determined to be an animal A such as a dog.
[0043]
When the part specified by the part specifying means 65 corresponds to the vicinity of the “shoulder and head”, the shoulder width determination unit 69 determines based on “the width of the shoulder width relative to the head”. This is because when looking at the front or back of the moving object, the human H has a wide shoulder width (width of the torso), whereas the animal A such as a dog has a narrow width of the torso. It is determined by using the information. In other words, when the size of the moving object changes, that is, when the moving object moves in the distance direction with respect to the monitoring camera 51, and the shoulder width with respect to the head is larger than the predetermined ratio, the moving object is a human H (intruder). On the other hand, when the ratio is smaller than the predetermined ratio, it is determined that the animal is an animal A such as a dog.
[0044]
When the part specified by the part specifying unit 65 corresponds to the vicinity of the “tail”, the tail determination unit 70 determines based on “the presence of the tail”. Since the human H does not have a tail like a dog, it is determined using this difference. That is, when an elongated cord-like shape is recognized near the buttocks, the animal is determined to be an animal A such as a dog.
[0045]
Note that the discrimination between the human H and the animal A is not limited to the above method. For example, any shape or posture that can distinguish the human H and the animal A, such as the position of the arm or the overall size, is used. It is possible to determine using the difference.
[0046]
By the way, in this embodiment, since the moving object is extracted based on the presence or absence of a change in the frame image, that is, the difference between the frame images separated at a predetermined time interval, a swinging curtain or laundry may be recognized as the moving object. There is. However, according to the present invention, since it is determined whether or not a person is a person according to a characteristic part of the person, the notification means is not activated even if the curtain or the laundry is blown by the wind.
[0047]
When the security device 4 or the monitoring camera 51 built in the security device 4 swings due to an earthquake, the entire frame image is determined to be a moving pixel, and the background itself may be recognized as a moving object. However, in this case, the outline shape of the moving object becomes the shape of the entire screen and is clearly different from the outline of a human, so that it is not discriminated as a human.
[0048]
Next, the flow of image processing in the security system 1 of the present embodiment will be described with reference to the flowchart shown in FIG. First, moving image data is separated into frame images in a frame separation step (step S1), and subsequent recognition processing is performed based on the frame images. The time interval of the frame separation at this time is appropriately set according to the speed of the operation to be recognized, the accuracy of the recognition, and the processing capability. The separated frame image is stored in the image storage unit 56 (Step S2).
[0049]
Subsequently, the presence / absence of a change is determined for each pixel of the sequentially separated frame images (step S3), and the presence / absence of the change is converted into numerical sequence data (step S4). Then, feature points in the contour shape of the moving object are extracted from the numerical value sequence data and their coordinates are detected (step S5), and the length and interior angle of the line connecting each feature point are detected (step S6). A shape code is generated based on the shape code (step S7).
[0050]
Thereafter, based on the shape code indicating the appearance shape of the moving object, it is determined whether or not the moving object is a human (intruder) by the above-described method (step S8). If it is determined by one of the determination means that the person is a human (YES in step S9), the notification means is activated (step S10). Specifically, the state information output means 16 notifies the server 2 and sounds the speaker 19 and the siren 20.
[0051]
As described above, in the security system 1 described above, it is possible to accurately determine whether the captured moving object is an intruder, and to activate the notification unit only when the intruder is an intruder. For this reason, it is not necessary to take any measures such as taking the pet out of the room or putting the pet in a circle or clay so as not to move around the room, and the usability can be greatly improved. Further, the conventional system in which security personnel and the like are rushed due to erroneous detection can be improved, and the burden on security companies can be reduced.
[0052]
In the security system 1, the reliability of monitoring an intruder is improved by combining a plurality of determination means. In particular, since it has a plurality of discriminating units corresponding to the characteristic portions of a human, even if, for example, an intruder wears a dog's costume and invades, it can be reliably identified as an intruder.
[0053]
Further, in the security system 1 described above, the amount of data to be subjected to recognition processing can be reduced by efficiently processing moving image data having a large amount of information. As a result, real-time processing can be performed by a general-purpose computer, and a relatively inexpensive security device 4 can be provided to many users.
[0054]
As described above, the present invention has been described with reference to the preferred embodiments. However, the present invention is not limited to these embodiments, and various improvements and modifications can be made without departing from the scope of the present invention as described below. Design changes are possible.
[0055]
That is, in the security system 1 described above, the presence / absence of a change in the frame image is determined for each pixel. However, the security system 1 includes an area dividing unit that divides the frame image into a plurality of small areas. May be determined for each divided small area. Since the number of divisions of the frame image is set to be much lower than the total number of pixels of the frame image, it is possible to simplify the processing by this region division.
[0056]
In the image recognizing means 52 in the security system 1 described above, as the shape data, the shape code generated by arranging the lengths of the line segments and the interior angles in a predetermined order is shown, but the numerical data calculated by the predetermined calculation is moved. It may be generated as shape data corresponding to the contour shape of an object.
[0057]
In the security system 1 described above, the image recognition means 52 is provided in the security device 4 at the resident's house. However, the image recognition means 52 may be provided in the server 2. According to this, the moving image data is transmitted from the security device 4 to the server 2, and the server 2 determines whether or not the person is a person. When the person is determined to be a person, a signal for sounding the speaker 19 and the siren 20 is transmitted from the server 2 to the security device 4. Therefore, the image recognition means 52 is shared, the configuration of the security device 4 is simplified, and the entire system can be constructed at a lower cost.
[0058]
【The invention's effect】
According to the present invention, since the shape data corresponding to the contour shape of the moving object is generated, and the shape data is analyzed to determine whether the moving object is a human, whether the captured moving object is an intruder is determined. It can be accurately determined whether or not. For this reason, the reliability of the security system can be improved. Furthermore, by efficiently processing moving image data having a huge amount of information, the amount of target data for recognition processing can be reduced. As a result, real-time processing can be performed by a general-purpose computer, and a relatively inexpensive security system can be provided to many users.
[Brief description of the drawings]
FIG. 1 is an explanatory diagram showing a configuration of an entire security system according to an embodiment of the present invention.
FIG. 2 is a block diagram showing a functional configuration of a security device in the security system.
FIG. 3 is a block diagram showing a functional configuration of a server and a first information terminal device in the security system.
FIG. 4 is a block diagram illustrating a functional configuration of an image recognition unit in the security system.
FIG. 5 is an explanatory diagram for explaining an image recognition method.
FIG. 6 is an explanatory diagram for explaining a difference in contour between a human and an animal (dog).
FIG. 7 is a flowchart showing a flow of processing in an image recognition unit.
[Explanation of symbols]
1 Security system
19 Speaker (reporting means)
20 siren (reporting means)
21 sound control means (notification control means)
51 surveillance camera (imaging means)
54 Frame separation means
58 Conversion means
59 Code generation means (data generation means)
63 determination means
64 aspect ratio determination means
65 Site identification means
66 Part identification means

Claims (8)

Imaging means for imaging a moving object and outputting the moving image data,
Based on the video data, shape data generating means for generating shape data corresponding to the contour shape of the moving object,
A determination unit configured to determine whether the moving object is a human based on the generated shape data;
A security system comprising: a notification control unit that operates a notification unit when the moving object is determined to be a human by the determination unit. Imaging means for imaging a moving object and outputting the moving image data,
Frame separating means for inputting the moving image data and separating the moving image data into frame images at predetermined time intervals,
For two frame images separated in order, a conversion unit that determines the presence or absence of a change in the image for each pixel or for each small region divided in advance, and converts the frame image into numerical sequence data based on the determination result.
Data generation means for generating shape data corresponding to the contour shape of the moving object based on the numerical sequence data,
Determining means for determining whether the moving object is a human based on the shape data,
A security system comprising: a notification control unit that operates a notification unit when the moving object is determined to be a human by the determination unit. The determining means determines whether the outline shape of the entire moving object is vertically long or horizontally long.If the outline is vertically long, the moving object is a human, and if it is horizontally long, the moving object is a non-human moving object. 3. The security system according to claim 1, further comprising an aspect ratio determination unit configured to determine the security ratio. The determining means determines, based on the generated shape data, a part specifying means for specifying a body part included in the subject, and whether or not the moving object is a human according to the shape of the specified part. The security system according to any one of claims 1 to 3, further comprising a part determining unit. The said part discrimination means has a joint discrimination part which discriminate | determines based on "the formation of a joint of a foot", when the part specified by the said part specification means corresponds to the vicinity of "foot". 4. The security system according to 4. The site determining unit includes a head determining unit that determines based on the “position of the head with respect to the torso” when the site specified by the site specifying unit corresponds to the vicinity of the “head”. The security system according to claim 4 or claim 5, wherein The site determination unit includes a shoulder width determination unit configured to determine based on the “width of the shoulder width with respect to the head” when the region identified by the region identification unit corresponds to the vicinity of the “head”. The security system according to any one of claims 4 to 6. The said part discriminating means has a tail discriminating part which discriminates based on "the presence of a tail" when the part specified by the part specifying means corresponds to the vicinity of "tail". The security system according to claim 7.

Images