KR20130111867A - System for monitoring image and thereof method - Google Patents

Abstract

PURPOSE: An image monitoring system and an operating method thereof are provided to rapidly control dangerous situations based on a generated event. CONSTITUTION: An image monitoring system comprises an image monitoring device (100), an operating device (200), and a designated organization (300). The image monitoring device captures images within a monitoring area and includes a digital signal processing unit (130). The digital signal processing unit determines an event from the captured image, uses event information, and calculates the occurrence probability of the determined event. When the occurrence probability is under a reference value, an alarm signal is transmitted to the operating device. The operating device transmits the image to the outside by monitoring the captured image. The designated organization responds to a dangerous situation by reading the alarm signal transmitted by the operating device. [Reference numerals] (100) Image monitoring device; (120) Timing circuit; (140) Microphone; (150) Driving unit; (160) Image signal conversion unit; (170) Communication interface; (200) Operating device; (210) Display unit; (220) Storage unit; (230) Communication unit; (240) Control unit; (300) Designated organization; (310) Police office; (320) Fire station; (330) Hospital

Description

Image surveillance system and its operation method

The present invention relates to a video surveillance system and a method of operating the video surveillance system that efficiently monitors an image according to an event probability analysis and quickly copes with a risk situation according to an event generated.

In general, a video surveillance system installs a plurality of cameras around various monitoring areas such as buildings, airports, roads, railways, and military units, stores video information obtained from them, and divides them on display devices at remote locations. It is a system that displays and recognizes the situation immediately when an intrusion or accident occurs.

Since the video information acquired by such a video surveillance system has a large amount of information, the user may not be able to control all surveillance videos, and may overlook the case where a dangerous situation occurs.

The technical problem to be solved by the present invention is to provide an image surveillance system and its operation method to quickly cope with the risk situation according to the generated event by generating an alarm for the surveillance image having a low event probability by analyzing the event probability of the surveillance image. It is.

According to an aspect of the present invention, a video surveillance system includes a video surveillance apparatus for photographing an image in a surveillance region through a camera; An operating device for storing and monitoring the photographed image and transmitting the photographed image to the outside; And a designated agency corresponding to a dangerous situation by reading an alarm signal transmitted by the operating device, wherein the video surveillance apparatus determines an event from the captured image and uses the determined event information to store the event. And a digital signal processor configured to calculate an occurrence probability of an event and transmit an alarm signal indicating the dangerous situation to the operating apparatus when the event occurrence probability is equal to or less than a reference value.

The digital signal processor may include: an image analyzer extracting feature information related to an event from the captured image and determining a type of event based on the extracted feature information; An event probability analysis unit for determining a risk situation by calculating an event occurrence probability of the image based on previously stored event information; And an alarm generator that generates an alarm signal and transmits the alarm signal and the dangerous event to the operating device when the event is a dangerous situation.

In the present invention, the event probability calculator, it is characterized in that it is a risk situation when the event occurrence probability is less than the reference value.

In the present invention, the database for storing the event information including the event type and the number of event occurrences analyzed by the image analysis unit for any of the images; characterized in that it further comprises.

In the present invention, the event search unit for searching the event information stored in the database; characterized in that it further comprises.

According to an aspect of the present invention, there is provided an operating method of an image surveillance system, including an image surveillance apparatus for photographing an image in a surveillance region through a camera, storing and monitoring the photographed image, and externally displaying the image. A method of operating a video system comprising an operating device for transmitting to a video signal and a designated engine corresponding to a dangerous situation by reading an alarm signal transmitted by the operating device, wherein the characteristic information related to an event is obtained from an image captured by the video surveillance device. Extracting and determining a type of event based on the extracted feature information; Determining, by the video surveillance apparatus, a risk situation by calculating an event occurrence probability of the determined video based on previously stored event information; If the event is a dangerous situation, the image monitoring device generates an alarm signal and transmits the alarm signal to the operating device together with the dangerous event image; And reading, by the designated authority, the alarm signal and the dangerous event image transmitted from the operating device, and corresponding to the dangerous situation.

In the present invention, before the step of determining the type of the event, the step of extracting the feature information associated with the event for any image; Determining a type of event based on the extracted feature information; And storing event information including the type of the event and the number of occurrences of the event in a database.

As described above, according to the present invention, an alarm is generated for a surveillance image having a low event occurrence probability through an event probability analysis on the surveillance image, thereby quickly coping with a risk situation according to the generated event.

1 is a block diagram of a video surveillance system according to an embodiment of the present invention.
FIG. 2 is a detailed block diagram of a digital signal processor of the video surveillance apparatus of FIG. 1.
3 is a flowchart illustrating a method of operating a video surveillance system according to the present invention.
4 is a flowchart illustrating a preprocessing process of FIG. 3.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "comprise" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

The invention can be represented by functional block configurations and various processing steps. Such functional blocks may be implemented in various numbers of hardware or / and software configurations that perform particular functions. For example, the present invention relates to integrated circuit configurations such as memory, processing, logic, look-up table, etc., which may execute various functions by the control of one or more microprocessors or other control devices. It can be adopted. Similar to how the components of the present invention may be implemented in software programming or software elements, the present invention includes various algorithms implemented in combinations of data structures, processes, routines or other programming constructs, including C, C ++ It may be implemented in a programming or scripting language such as Java, an assembler, or the like. The functional aspects may be implemented with an algorithm running on one or more processors. In addition, the present invention may employ the prior art for electronic environment setting, signal processing, and / or data processing. Terms such as mechanism, element, means, configuration can be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in conjunction with a processor or the like.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Referring to the accompanying drawings, the same or corresponding components are denoted by the same reference numerals, do.

1 is a block diagram of a video surveillance system according to an embodiment of the present invention.

The video surveillance system shown in FIG. 1 includes an image surveillance apparatus 100, an operation apparatus 200, and a designation institution 300.

The video monitoring apparatus 100 includes an optical system OPS, a photoelectric conversion unit OEC, a correlation double sampler and an analog-to-digital converter 110, a timing circuit 120, a digital signal processor 130, _A zoom motor M _Z , a focus motor M _F , a filter motor M _D , a driving unit 150, a video signal conversion unit 160, and a communication interface 170 ). The zoom motor M _Z , the focus motor M _F , the filter motor M _D , and the drive unit 150 in the present invention are described in the description of the optical system OPS, the photoelectric conversion unit OEC, the diaphragm motor M _A , For convenience, it is represented by camera.

An optical system (OPS) including a lens unit and a filter unit optically processes light from a subject.

The lens section of the optical system OPS includes a zoom lens ZL and a focus lens FL. In the filter unit of the optical system OPS, an optical low pass filter (OLPF) used in a night mode of operation removes optical noise having a high frequency content. Infra-Red cut filter (IRF) used in daytime operation mode cuts off the infrared component of incident light.

A photoelectric conversion unit OEC of a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide-Semiconductor) converts light from the optical system OPS into an electrical analog signal. The digital signal processing unit 130 controls the timing circuit 120 to control the operation of the photoelectric conversion unit OEC and the CDS-ADC (Correlation Double Sampler and Analog-to-Digital Converter) 110.

The CDS-ADC 110 processes an analog video signal from the photoelectric conversion unit OEC, removes the high-frequency noise, adjusts the amplitude, and converts the digital video data. The digital image data is input to the digital signal processor 130.

The digital signal processing unit 130 performing the overall control processes the digital signal from the CDS-ADC device 110 to generate digital image data classified into luminance and chrominance signals.

The microphone 140 receives a voice signal from the photographed image and outputs the voice signal to the digital signal processor 130. [

The digital signal processor 130 determines an event from the captured image and calculates an occurrence probability of the determined event using previously stored event information, and operates an alarm signal informing that the event is a dangerous situation when the event occurrence probability is lower than the reference value. Send to 200. The detailed operation of the digital image processor 130 will be described with reference to FIG.

The video signal conversion unit 160 converts the digital video data from the digital signal processing unit 130 into an analog video signal.

The digital signal processor 130 transmits the converted analog video signal from the video signal converter 160 to the operating device 200 while communicating with the operating device 200 through the communication interface 170. [

The digital signal processor 130 controls the driving unit 150 to drive the diaphragm motor M _A , the zoom motor M _Z , the focus motor M _F , and the filter motor M _D. The diaphragm motor M _A drives a diaphragm (not shown), the zoom motor M _Z drives a zoom lens ZL, and the focus motor M _F drives a focus lens FL. The filter motor M _D drives the optical low-pass filter OLPF and the infrared cut filter IRF in the filter unit.

The operating device 200 includes a display unit 210, a storage unit 220, a communication unit 230, and a control unit 240.

The display unit 210 displays a video signal transmitted from the video surveillance apparatus 100.

The storage unit 220 stores video signals transmitted from the video surveillance apparatus 100, and may be various storage media.

The communication unit 230 transmits and receives data to and from the designated organ 300, and transmits an alarm signal and an event image, which are a result of the risk analysis, transmitted from the video surveillance apparatus 100, to the designated organ 300.

The designation authority 300 may be a police station 310, a fire station 320, a hospital 330, or the like so as to cope with a dangerous situation. When receiving the alarm signal and the event image from the designated institution 300, the risk situation handling personnel are put into the field to solve the risk situation.

FIG. 2 is a detailed block diagram of a digital signal processor of the video surveillance apparatus of FIG. 1. The operation of the digital signal processing unit 130 of the video surveillance apparatus 100 shown in FIG. 2 will be described in connection with the operating apparatus 200 and the designated authority 300.

Referring to FIG. 2, the digital signal processor 130 includes an image analyzer 131, a database 132, an event probability analyzer 133, and an alarm generator 134.

Before performing the present invention, a preprocessing process must be preceded, and the preprocessing process is performed by the image analyzer 131 and the database 132. Next, the pretreatment process will be described in detail.

In a typical computer-based classification system, statistical characteristics of a given data are analyzed to determine the type of new data judged to have the same statistical characteristics. In this case, in order to improve the classification performance, it is necessary to process the given data to select the data having high reliability. This process is called a preprocessing process. This process is a preliminary operation to select the partial data that is currently focused on or to form unnecessary data to separate unnecessary information in order to easily extract essential information from a given input data. This preprocessing includes processing such as data normalization, data selection, noise data removal, and the like. After the preprocessing, it is necessary to convert the original data into new data at a lower level in order to reduce the computational amount to an appropriate level and improve the quality of the data. The new data obtained for this dimension reduction is called the feature of the original data, and the process of extracting such feature is called feature extraction. Once features are extracted from the data, the type information of the given data is finally determined using a classifier.

Among the feature extraction methods, there is a subspace method which is widely used. The subspace method includes a preprocessing step of processing raw data so as to extract essential information for classification, a step of finding a transformation matrix which is a set of axes for projecting data using the processed data, Projecting and extracting features, and classifying the data using the projected features instead of the raw data.

A typical example of a subspace technique is linear discriminant analysis. The linear discriminant analysis comprises the steps of: finding an axis maximizing defined scatter to enhance classification performance; Projecting data onto the found axes; And using the projected value as a feature instead of the original image.

This linear discriminant analysis finds the axis that maximizes the defined scatter to enhance the classification performance and finds the feature using the axis included in it. A scatter matrix representing scattering is a scattering matrix defined by data belonging to the same class. It is defined as a matrix (between-class scatter matrix), which can be used to find the axis that minimizes the scattering between data that should be classified into the same type while maximizing the scattering between the data to be classified differently.

The image analyzer 131 extracts feature information related to an event with respect to arbitrary images through the preprocessing process as described above, and determines the type of event based on the extracted feature information.

Here, the event is an event indicating the occurrence of a dangerous situation, for example, a fire, a traffic accident, a personnel accident, etc. A fire or a traffic accident is a fire or a traffic accident from arbitrary images because event patterns have similar patterns. Feature information may be extracted, and the type of event may be determined from the extracted feature information. In addition, in case of personnel accidents, the weapons or group beatings used for the invasion of robbery are also different from the general ones, so feature information about the corresponding images can be extracted, and the type of event from the extracted feature information. Can be determined.

The database 132 stores event information including the type of the event and the number of occurrences of the type of the event, and then uses it as a reference when the event occurs. In database 132, (E _{0. ,} E _{x .,} E _n ) represents the type of event, such as a fire, traffic accident, personnel accident, etc., and (t _{0. ,} T _{x . ,,} t _n ) corresponds to The number of occurrences of the event type.

After the preprocessing process is completed, an image surveillance system for efficiently monitoring an image according to event probability analysis is operated. Hereinafter, the digital signal processor 130 will be described.

The image analyzer 131 extracts feature information related to the event from the captured image and determines the type of event based on the extracted feature information.

The image analyzer 131 includes a feature extractor 1311 and an event determiner 1312.

The feature extractor 1311 extracts an arbitrary feature from the captured image. The feature extractor 1311 extracts feature information of a fire, feature information of a traffic accident, and feature information of a personnel accident through feature extraction as disclosed above.

The event determiner 1312 determines the type of the corresponding event by comparing the extracted feature information with the event information stored in the database 132.

The event probability analysis unit 133 calculates an event occurrence probability based on the event information previously stored in the database 132 to determine a risk situation.

The event probability analyzer 133 includes an event probability calculator 1331 and an event probability searcher 1332.

The event probability calculator 1331 calculates an event probability using the updated number of event occurrences for the total sum of all event types stored in the database 132, as shown in Equation 1 below.

In Equation 1, the denominator represents the total sum of all events stored in the database 132, and the numerator represents the number of occurrences of an event plus a predetermined number of pre-stored arbitrary events and a number of occurrences of currently occurring events.

The event probability calculator 1331 determines whether the calculated event probability is lower than a reference value designated by the user, for example, 20%. If the calculated event probability is lower than the reference value specified by the user, the event probability calculation unit 1331 determines that a risk condition has occurred. If the calculated event probability is higher than the user-specified reference value, it is determined that it is a general situation, not a risk situation.

The event probability calculator 1331 updates the number of occurrences of the event type in the database 132 before calculating the event probability. If an event having the same property exists in the database 132, the event probability calculation unit 1331 increases the number of occurrences of the corresponding event. If the same event does not exist in the database 132, the event and the number of occurrences are registered in the database 132.

The event probability calculator 1331 searches for event information stored in the database 132 by a user request. Since the database 132 stores the event type and the number of event occurrences according to the event type, the event probability is sorted and displayed to the user in ascending or descending order according to the user's request. Alternatively, if a user inputs an event keyword requested by the user, the event occurrence probability is displayed. Therefore, the user can know which event occurred frequently in the surveillance video and which event occurred rarely.

The alarm generator 134 transmits the corresponding event image to the operating apparatus 200 together with the alarm signal when it is determined that the dangerous event occurs because the calculated event probability is lower than the reference value designated by the user.

The operating apparatus 200 transmits the alarm signal received from the alarm generator 134 and the corresponding event image to the designated authority 300 to request a rescue.

The designated authority 300 may view the alarm signal and the corresponding event image received from the operating device 200 to solve the risk situation.

3 is a flowchart illustrating a method of operating a video surveillance system according to the present invention. In the following description, the description of the parts that are the same as those in FIG. 1 and FIG. 2 will be omitted.

Referring to FIG. 3, the video surveillance apparatus 100 extracts feature information related to an event from a captured image and determines a type of event based on the extracted feature information (S11).

The video surveillance apparatus 100 performs a step S12 of determining a risk situation by calculating an event occurrence probability of an image determined based on event information stored in a database. The video surveillance apparatus 100 determines that a dangerous situation occurs when an event occurrence probability is lower than a reference value.

If it is determined that a dangerous condition has occurred from the event image, the video surveillance apparatus 100 generates an alarm signal and transmits the generated alarm signal to the operating apparatus 200 along with the event image (S13).

The designated organ 300 reads an alarm signal and an event image transmitted from the operating apparatus 200 and performs a step S14 corresponding to a dangerous situation.

4 is a flowchart illustrating a preprocessing process performed by the video surveillance apparatus 100 of FIG. 3. In the following description, the description of the parts which are the same as those in the description of Figs. 1 to 3 will be omitted.

Referring to FIG. 4, the video surveillance apparatus 100 performs step S21 of extracting feature information associated with an event with respect to arbitrary images.

When the feature information is extracted, the video surveillance apparatus 100 performs a step S22 of determining the type of event based on the extracted feature information.

When the determination of the type of event is completed, the video surveillance apparatus 100 performs step S23 of storing event information including the type of the event and the number of occurrence of the event type in a database.

The video surveillance apparatus 100 increases the number of occurrences of the corresponding event when an event having the same property exists in the database, and registers the corresponding event and the number of occurrences in the database when an event having the same property does not exist in the database.

The present invention has been described above with reference to preferred embodiments. It will be understood by those skilled in the art that the present invention may be embodied in various other forms without departing from the spirit or essential characteristics thereof. Therefore, the above-described embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is shown not in the above description but in the claims, and all differences within the scope should be construed as being included in the present invention.

All documents including publications, patent applications, patents, etc. cited in the present invention can be incorporated into the present invention in the same manner as each cited document individually and concretely, .

100: video monitoring device
130: Digital signal processor
131: an image analyzer
132: database
133: event probability analysis unit
134: alarm generator
200: operating system
300: designated institution

Claims (7)

An image surveillance apparatus for photographing an image in the surveillance region through a camera;
An operating device for storing and monitoring the photographed image and transmitting the photographed image to the outside; And
A designated authority corresponding to a dangerous situation by reading an alarm signal transmitted by the operating device,
The video surveillance device
Determining an event from the photographed image, using the pre-stored event information to calculate the probability of occurrence of the determined event, when the event occurrence probability is less than the reference value alarm signal indicating that a dangerous situation with the event image And a digital signal processor for transmitting to the operating device. The method of claim 1,
Wherein the digital signal processor comprises:
An image analyzer extracting feature information related to an event from the captured image and determining a type of event based on the extracted feature information;
An event probability analysis unit for determining a risk situation by calculating an event occurrence probability of the image based on previously stored event information; And
And an alarm generator configured to generate an alarm signal and transmit the alarm signal and the dangerous event to the operating device when the event is a dangerous situation. The method of claim 2,
The event probability calculation unit,
And if the event occurrence probability is equal to or less than a reference value, determining that the situation is dangerous. The method of claim 2,
And a database storing event information including an event type and a frequency of occurrence of an event analyzed by the image analyzer with respect to arbitrary images. 5. The method of claim 4,
And an event search unit for searching for event information stored in the database. Video surveillance device that captures the image in the surveillance area through the camera, an operating device that stores and monitors the captured image and transmits the image to the outside, and designates corresponding to a dangerous situation by reading an alarm signal transmitted by the operating device. An operating method of an imaging system including an organ,
Extracting feature information related to an event from an image captured by the video surveillance apparatus and determining a type of event based on the extracted feature information;
Determining, by the video surveillance apparatus, a risk situation by calculating an event occurrence probability of the determined video based on previously stored event information;
If the event is a dangerous situation, the image monitoring device generates an alarm signal and transmits the alarm signal to the operating device together with the dangerous event image; And
And a step in which the designated authority reads the alarm signal and the dangerous event image transmitted from the operating device and responds to the dangerous situation. The method according to claim 6,
Before the step of determining the type of the event,
Extracting feature information related to an event with respect to arbitrary images;
Determining a type of event based on the extracted feature information; And
And storing event information including the type of the event and the number of occurrences of the event in a database.

Images