KR20120068150A - Obfect tracking system and method thereof - Google Patents

Abstract

PURPOSE: An object tracking system and a method thereof are provided to perform accurate scan by photographing an enlargement tracking image of a monitoring object through a PTZ(Pan, Tilt, Zoom) camera. CONSTITUTION: A face recognition is performed in a received image. A face range is extracted. A second object detection is performed for measuring comparing similarity rate of the extracted face range information and dangerous people database information. An image about a corresponding object is notified to a manager. A photographic direction of a monitoring camera is changed.

Description

Object tracking system and method

The present invention relates to an object tracking system and a method thereof, and more particularly, comprising a plurality of surveillance cameras in a network, and comparing face area information obtained through face recognition from a video captured by the surveillance camera with a crime suspect DB. The present invention relates to an object tracking system and a method for detecting a specific object having high similarity and enabling real-time tracking of the specific object.

Increasing importance of security has led to an increase in the location of surveillance systems using surveillance cameras.

However, the conventional surveillance system independently captures an area or part of each surveillance camera to store and analyze images in the system.

Therefore, even if a plurality of surveillance cameras monitor a specific area, there is a lack of networking capability between the surveillance cameras. Therefore, the correlation between images captured from the surveillance cameras and the movement of the same object are tracked or the movement path is determined by the manual operation of the administrator. I'm doing it.

In other words, if the administrator wants to search, the search is performed based on the desired place and time, and it is difficult to find a desired result not only because it is time consuming due to the difficulty of manually searching from place to place. .

In addition, the detection camera of the conventional surveillance system has a problem that the identification of the object to be controlled is not easy because the resolution is low.

In order to solve the above-mentioned problems, the present invention provides an object tracking system capable of performing accurate detection by capturing an enlarged tracking image of a monitoring object by using a multiple detection camera and a PTZ camera in one pole, and its The purpose is to provide a method.

In addition, the present invention, by using a multi-detection camera and a PTZ camera in one pole can accurately recognize the detection target by object recognition through the first overview image and object recognition through the second magnification tracking image. Another object is to provide an object tracking system and method thereof.

In addition, the present invention, by performing a facial recognition from the image captured by the surveillance camera equipped with a multiple detection camera and a PTZ camera in one pole to extract the face area and compare the specific person corresponding to the information previously stored in the database Another object of the present invention is to provide an object tracking system and a method for identifying and tracking a specific person.

In addition, the present invention, by performing facial recognition from the image captured by a surveillance camera equipped with a multiple detection camera and a PTZ camera in one pole to extract the face area and compare with the information stored in the database (person, criminals) Another object of the present invention is to provide an object tracking system and a method for identifying a corresponding specific person and providing a moving line for the specific person while executing the tracking for the specific person.

In addition, the present invention, by connecting a surveillance camera installed with a multiple detection camera and a PTZ camera in one pole by a network, it is possible to continuously track the occurrence of a specific object or various situations to be monitored, it is notified by generating an alarm to the administrator It is another object of the present invention to provide an object tracking system and a method for enabling the inspection or the arrest in real time.

Object tracking system and method of an embodiment of the present invention for achieving the above object, the image captured from the multi-detection camera of the surveillance cameras installed with a multi-detection camera and a PTZ camera in one pole (pole) Receives facial recognition by performing facial recognition, and performs primary detection to measure similarity by comparing the information of the dangerous person database that stores information about the person to be detected, such as the wanted person and criminal, and the extracted face area. If the degree of similarity is greater than or equal to the threshold value, the PTZ camera is driven to receive a magnified image, perform facial recognition, extract a face region, and measure the similarity by comparing the information of the dangerous person database with the extracted face region. If the second detection is performed and the similarity is over the threshold, an image of the object is alarmed to the administrator. To inform, to change the shooting direction of the monitoring camera continues to keep track of the object.

In addition, the object tracking system and method of an embodiment of the present invention, by connecting a surveillance camera having a multi-detection camera and a PTZ camera installed in one pole by a network to continuously track the occurrence of a specific object or various situations to be monitored. In addition, the alarm is generated and notified to the administrator so that the inspection or the arrest is performed in real time.

According to the present invention, there is an effect that accurate object recognition is made through the first and second detection processes through the monitoring cameras installed with multiple detection cameras and PTZ cameras in one pole.

In addition, according to the present invention, by forming a network through the interlocking of a plurality of surveillance cameras to secure a multi-dimensional monitoring and rapid response to a specific object to be arrested for dangerous persons such as a wanted person or suspect or a thief in the field It is effective in improving the safety of citizens.

1 is a relationship diagram schematically showing the overall network relationship of the object tracking system according to the present invention.
FIG. 2 is a block diagram illustrating a camera system of the object tracking system shown in FIG. 1.
3 is a flowchart illustrating an object tracking method according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Further, in order to clearly illustrate the present invention in the drawings, portions not related to the description are omitted. In addition, the same code | symbol is attached | subjected about the similar part throughout the specification. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail.

1 is a relationship diagram schematically showing the overall network relationship of the object tracking system according to the present invention.

As shown in FIG. 1, the object tracking system includes a camera system 100, a comprehensive situation room system 300, a jurisdiction site dispatch center system 400, a mobile communication network system 500, and a portable wireless device 410. .

The camera system, the integrated situation room system, the jurisdiction site dispatch center system and the mobile communication network system are connected via a wired or wireless communication network (200).

In the camera system, a surveillance camera composed of a detection camera and a tracking camera forms a network.

The object tracking system uses software to automate object recognition and motion tracking, so that dangerous objects such as criminal suspects can be detected through facial recognition in images captured by the camera system, and automatic alarm function is detected when dangerous objects are detected. It is configured to inform the administrator.

FIG. 2 is a block diagram illustrating a camera system of the object tracking system shown in FIG. 1.

As shown in FIG. 2, the camera system includes a plurality of surveillance cameras, and a plurality of cameras are installed. Each camera system can be linked to each other to form a network, and can be controlled and managed in a comprehensive situation room system. To be installed. Such a camera system is installed to enable communication with wired and wireless communication networks.

The surveillance camera is composed of at least one detection camera 101 and a tracking camera 102.

The detection camera may be fixed or rotating as an overview camera, and acquires an image by photographing the installed location and location.

The tracking camera can be a PTZ camera, and it tracks an object to obtain an enlarged video image, and includes pan, tilt, tilt, and zoom functions. The camera is free to rotate and zoom, and may be a megapixel IP camera. The megapixel IP camera has a much higher resolution than conventional analog video equipment, so that the megapixel IP camera can capture an input image having a high resolution image quality.

Such a surveillance camera may be applied to a camera having various types and functions, including high resolution.

In addition, the camera system may include a video server 110, a control device 112, a storage device 114, and a transceiver 130.

3 is a flowchart illustrating an object tracking method according to an embodiment of the present invention.

As shown in FIG. 3, first, one overview camera and one PTZ camera are installed in one pole.

Then, the image of the place and location installed by the overview camera is taken in real time, facial recognition is performed after facial recognition from the captured image, and compared with the extracted face region and the information of the criminal DB, Acquire coordinate values in the image.

Subsequently, the PTZ camera is rotated to a corresponding position to track and zoom in on the face of the person, and face recognition is performed by performing facial recognition from the magnified image.

Then, after re-recognition of the matching rate is measured by comparing the extracted face area with the information of the criminal DB, if it is more than the specified matching rate, the alarm is registered in the alarm lock list to generate an alarm in the local site dispatch center system such as a police station.

The alarm displays location information, criminal information (photos), and real-time video of the camera on the status board.

In addition, when an alarm occurs, the location of surveillance cameras located in the vicinity of the road to the corresponding area is displayed and the image of each camera is displayed on the screen of the situation room so that the movement path of the criminal can be identified.

In addition, when the same person is found by surveillance cameras in other areas, the criminal line may be displayed on the GIS map.

In addition, if a person registered in the alarm potential list stays in the overview camera image for more than 3 minutes, a second alarm is generated at the police station so that the police can immediately recognize and take action.

The alarms are accumulated and displayed on the software for easy recognition and the criminal information, location information and time information can be checked when the alarm is clicked. The software generates an alarm (person SMS text, video display) to alert you.

Meanwhile, although the present invention has been described as recognizing a specific object by extracting a face region through facial recognition from a captured image, the present invention is not limited thereto. When the object corresponds to a specific action previously input through motion detection of the object, The object may be configured to recognize an object as dangerous and notify an administrator.

So far I looked at the center of the preferred embodiment for the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments are to be regarded as illustrative rather than restrictive, and all differences within the equivalent scope should be construed as being included in the present invention.

Further, the system and method according to the present invention can be embodied as computer readable codes on a computer readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like, and also include a carrier wave (for example, transmission through the Internet). The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

Claims (1)

Receiving an image taken from the multi-detection camera of the surveillance cameras installed with a multi-detection camera and a PTZ camera in one pole;
Extracting a face region by performing facial recognition on the received image;
Performing primary object detection for measuring similarity by comparing a match rate of extracted face region information with information of a dangerous person database;
If the similarity is greater than or equal to a threshold, receiving a magnified image obtained by tracking a corresponding object from a PTZ camera;
Performing facial recognition on the received image to extract a face region, and performing a second object detection to measure similarity by comparing a match rate of the extracted face region information with information of the dangerous person database;
If the similarity is greater than or equal to a threshold value, notifying an image of a corresponding object to an administrator through an alarm, and tracking a corresponding object by changing a photographing direction of the surveillance camera.

Images