WO2016072627A1

WO2016072627A1 - System and method for managing multiplanar parking lot using one omnidirectional camera

Info

Publication number: WO2016072627A1
Application number: PCT/KR2015/010657
Authority: WO
Inventors: 송우식; 김수경; 이대호
Original assignee: 주식회사 넥스파시스템
Priority date: 2014-11-03
Filing date: 2015-10-08
Publication date: 2016-05-12
Also published as: AU2015282375A1; AU2015282375B2; KR101538488B1

Abstract

The present invention relates to a system and method for managing a parking lot, which can scan vehicles parked in a plurality of parking spaces and simultaneously perform a security function by using one omnidirectional camera. As a system that manages a parking lot in which a plurality of parking spaces are disposed to form a plurality of rows, a system for managing a multiplanar parking lot using one omnidirectional camera related to an embodiment of the present invention comprises: an omnidirectional camera installed on the ceiling of the parking lot between two adjacent rows from among the plurality of rows and having a fisheye lens, for capturing omnidirectional surveillance images; a cable connected to the omnidirectional camera, for transmitting the surveillance images; and a managing server connected to the cable, for receiving the surveillance images. The managing server further comprises: a vehicle sensing module that determines whether vehicles are parked in the plurality of parking spaces, by using the surveillance images; and a security module provided with a memory for storing the surveillance images. A portion of the parking spaces disposed in a first row and a portion of the parking spaces disposed in a second row are captured in the surveillance images, and the first row and the second row are the two rows between which the omnidirectional camera is installed.

Description

1 multi-faceted parking lot management system and management method using omnidirectional camera

The present invention relates to a multi-faceted parking lot management system and management method using an omnidirectional camera, and more particularly, it is possible to detect a vehicle parked on a plurality of parking surfaces by using one omnidirectional camera and at the same time perform a security function. It relates to a possible parking lot management system and management method.

Large buildings such as department stores, large shopping centers, and hospitals, which have a large floating population, generally have large parking facilities that provide a large number of parking spaces. However, with the rapid increase in the number of vehicles, parking facilities have become very scarce. to be.

In particular, on weekends and holidays, many people are crowded and the parking space is not enough. There is a problem in that time and money are consumed because the parking lot moves around the large parking facility.

Accordingly, a parking guidance system has been developed and widely commercialized by providing a driver with convenience of parking by indicating to the driver whether there is enough parking space by using a sensor for detecting whether a vehicle is parked on the parking surface.

Conventional parking guidance system has been using a method using a sensor installed on each of the parking surface to detect whether the vehicle parking.

However, there is a problem that the sensor used in the conventional parking guidance system is relatively expensive and requires a lot of cost and effort for its maintenance and management. Such sensors frequently misrecognize objects other than vehicles such as people or carts as vehicles, and there are problems that cause inconvenience due to misdetection.

In addition, in order to install a CCTV in a parking facility to perform a security function, there was a problem in that the installation cost was high because a separate camera facility, wiring, and management PC had to be installed. There was a problem.

Accordingly, there is a demand for development of a system capable of more efficiently detecting a vehicle and inducing parking, as well as providing security functions such as crime prevention.

The present invention has been made to solve the conventional problems as described above, parking lot management system and management method that can detect a vehicle parked on a plurality of parking surfaces using a single omnidirectional camera and at the same time can perform a security function The purpose is to provide the user with the.

Specifically, the present invention can shoot about 12 parking surfaces around a single omnidirectional camera does not require the installation of a lot of cameras, no installation of a separate CCTV, economical and easy to maintain and manage, and to take images The purpose is to provide a parking lot management system that can provide security functions to users.

In addition, the present invention can effectively detect the vehicle by installing a sensor on the parking surface of the position where the omnidirectional camera is impossible to shoot in the parking lot structure or the illumination surface is too strong or too weak to detect the vehicle is difficult to detect the wrong detection The purpose is to provide a parking management system that can prevent the user.

In addition, an object of the present invention is to provide a user with a parking lot management system that can simplify the wiring installation, the installation cost is reduced, and the construction period can be significantly reduced by operating the sensor and the omnidirectional camera in conjunction.

On the other hand, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems that are not mentioned are clearly to those skilled in the art from the following description. It can be understood.

In a system for managing a parking lot in which a plurality of parking surfaces are arranged in a plurality of rows, the one-to-many parking lot management system according to an example of the present invention for realizing the above-described problem includes two adjacent rows among the plurality of rows. An omnidirectional camera installed on the ceiling between the parking lot and equipped with a fisheye lens to capture a surveillance image from all directions; A cable connected to the omnidirectional camera to transmit the surveillance image; And a management server connected with the cable to receive the surveillance image, wherein the management server comprises: a vehicle detection module that determines whether a vehicle is parked on the plurality of parking surfaces using the surveillance image; And a security module having a memory for storing the surveillance image, wherein the surveillance image is photographed with a portion of the parking surface disposed in the first row and a portion of the parking surface disposed in the second row. And the second row is two neighboring rows in which the omnidirectional camera is installed.

In addition, there are five to seven parking surfaces arranged in the first row photographed by the surveillance image, and five to seven parking surfaces arranged in the second row photographed by the surveillance image.

The vehicle detection module may further include: an area setting unit configured to set an area of the parking surface photographed in the surveillance image; A feature detector extracting a feature vector from an area of the parking surface set by the area setting unit; And a detector configured to determine whether a vehicle is parked in an area of the parking surface by using the feature vector.

The apparatus may further include a sensing sensor installed adjacent to a first parking surface which is a part of the plurality of parking surfaces, detecting a vehicle located on the first parking surface, and generating a detection signal corresponding to the sensing result. The cable may be connected to the detection sensor linked to the omnidirectional camera to transmit the detection signal to the management server.

In addition, the first parking surface is disposed at a position where it is impossible to determine whether the vehicle detection module is parked according to a change in environmental factors including a second parking surface and illuminance disposed on the shooting blind spot of the omnidirectional camera. And a third parking surface.

The vehicle detection module may determine whether the vehicle is parked on the first parking surface by using the detection signal.

In addition, when the vehicle detection module can determine whether the vehicle is parked on the third parking surface using the surveillance image, the vehicle detection module additionally uses the surveillance image to park the vehicle on the third parking surface. It can be determined whether or not.

The vehicle may further include a manhole difference outputting a preset display related to whether the vehicle is parked on the plurality of parking surfaces. The management server may control the output of the manhole difference according to the determination of the vehicle detection module. .

On the other hand, in the method of managing the parking lot management system in which a plurality of parking surfaces are arranged in a plurality of rows, the one-to-many parking lot management method according to an example of the present invention for realizing the above-described problem includes a fisheye lens. A first step in which a omnidirectional camera captures a surveillance image from all directions; A second step of transmitting the surveillance image through a cable connected to the omnidirectional camera; A third step of receiving, by the management server connected to the cable, the surveillance image; And a fourth step of determining, by the vehicle detection module of the management server, whether the vehicle is parked on the plurality of parking surfaces by using the surveillance image, wherein the omnidirectional camera has two neighboring columns among the plurality of columns. Installed on the ceiling of the parking lot between, and a part of the parking surface arranged in the first row and a part of the parking surface arranged in the second row are photographed in the surveillance image, and the first row and the second row are provided by the omnidirectional camera. Two installed neighboring columns, the management server may further include a security module having a memory for storing the surveillance image.

The present invention has been made to solve the conventional problems as described above, parking lot management system and management method that can detect a vehicle parked on a plurality of parking surfaces using a single omnidirectional camera and at the same time can perform a security function Can be provided to the user.

Specifically, the present invention can shoot about 12 parking surfaces around a single omnidirectional camera does not require the installation of a lot of cameras, no installation of a separate CCTV, economical and easy to maintain and manage, and to take images The parking lot management system that can provide a security function can be provided to the user.

In addition, the present invention can effectively detect the vehicle by installing a sensor on the parking surface of the position where the omnidirectional camera is impossible to shoot in the parking lot structure or the illumination surface is too strong or too weak to detect the vehicle is difficult to detect the wrong detection It is possible to provide the user with a parking management system that can prevent.

In addition, the present invention can provide a user with a parking lot management system that can simplify the wiring installation, the installation cost is reduced, and the construction period can be significantly reduced by operating the sensor and the omnidirectional camera in conjunction.

On the other hand, the effect obtained in the present invention is not limited to the above-mentioned effects, other effects that are not mentioned will be clearly understood by those skilled in the art from the following description. Could be.

The following drawings, which are attached to this specification, illustrate one preferred embodiment of the present invention, and together with the detailed description thereof, serve to further understand the technical idea of the present invention. It should not be construed as limited.

1 and 2 illustrate an example of a parking lot in which a multi-faceted parking lot management system of the present invention is implemented.

3 and 4 illustrate an embodiment of a surveillance image by the omnidirectional camera that can be applied to the present invention.

5 shows an example of a block configuration diagram of a multi-faceted parking lot management system of the present invention.

6 is a flowchart illustrating a management method of a parking lot related to an example of the present invention.

7 to 9 illustrate an embodiment of a vehicle detection process that can be applied to the present invention.

10: omnidirectional camera

15: detection sensor

20: cable

30: parking surface

40: vehicle

100: parking lot

200: management server

210: vehicle management module

212: area setting unit

214: feature detection unit

216: detection unit

230: security module

232: memory

In the multi-faceted parking lot management system according to the present invention, the omnidirectional camera installed on the ceiling of the parking lot between two adjacent columns among the plurality of rows photographs the omnidirectional surveillance image using the fisheye lens, and the surveillance image is connected to the omnidirectional camera. It is sent to the management server through. The surveillance image captures a portion of the parking surface arranged in the first column and a portion of the parking surface arranged in the second column.

The management server is composed of a vehicle detection module and a security module. The vehicle detection module determines whether the vehicle is parked on the plurality of parking surfaces by using the surveillance image, and the security module stores the surveillance image in a memory.

Hereinafter, with reference to the drawings will be described a preferred embodiment of the present invention. In addition, one Example described below does not unduly limit the content of this invention described in the Claim, and the whole structure demonstrated by this Embodiment is not necessarily required as a solution of this invention.

In the conventional parking lot management system, a sensor is configured to be connected to a controller or a server separately from the detection camera, which is disadvantageous in terms of cost or efficiency.

The present invention is to propose a parking lot management system and a management method that can simultaneously perform a vehicle detection and security functions for parking guidance by configuring the omnidirectional camera to interlock with the sensor.

Hereinafter, with reference to the drawings will be described in detail the one-to-many parking lot management system proposed by the present invention.

Referring to FIG. 1, the multiple parking lot management system of the present invention may be applied to an indoor large parking lot 100 in which a plurality of parking surfaces 30 are arranged in a plurality of rows. 1 illustrates a part of a parking lot 100 to which the present invention is applied, and each parking surface 30 is provided with a space in which one vehicle 40 can be parked.

The omnidirectional camera 10 is installed on the raceway of the ceiling of the parking lot 100 and is installed between two neighboring rows of the plurality of rows formed by the plurality of parking surfaces 30. That is, if one of the plurality of rows is called the first row and the row adjacent to the first row is the second row, the omnidirectional camera 10 is installed between the first row and the second row.

The omnidirectional camera 10 is implemented using a camera equipped with a fisheye lens. When the fisheye lens having a wide angle of view is used, an image of the omnidirectional (360 °) region may be captured around the omnidirectional camera 10.

As shown in FIG. 1, the omnidirectional camera 10 captures an image of a surrounding in which the omnidirectional camera 10 is installed. The area photographed by the omnidirectional camera 10 includes a vehicle detection area 12 and a security function area 14 of the parking lot 100.

The vehicle detection area 12 includes a parking surface 30 near a row in which the omnidirectional camera 10 is installed, and approximately one omnidirectional camera 10 includes a vehicle detection area including 12 parking surfaces 30. 12) can be taken. For example, the vehicle detection area 12 may include five to seven areas of the parking surface 30 disposed in each of the first row and the second row.

The surveillance image photographed by the omnidirectional camera 10 includes the vehicle detection region 12, and the image captured by the vehicle detection region 12 is as shown in FIGS. 3 and 4.

3 and 4 illustrate an embodiment of a surveillance image by the omnidirectional camera that can be applied to the present invention. 3 illustrates a surveillance image captured by the omnidirectional camera 10, and FIG. 4 is an image obtained by converting the image of FIG. 3.

The surveillance image photographed by the omnidirectional camera 10 may be converted into an image as shown in FIG. 4 by removing a distortion of each region by adjusting a distance ratio according to a long distance and a short distance. As a method of correcting the distorted image information, forward mapping through an application of a correction factor and an accompanying interpolation method may be used. Inverse mapping, which is a method of finding out which point matches, may be used.

Referring back to FIG. 1, the omnidirectional camera 10 is installed in an appropriate number to cover all of the plurality of parking surfaces 30 disposed in the parking lot 100. The plurality of omnidirectional cameras 10 installed in the parking lot 100 may be connected to the management server 200 by a cable 20.

Meanwhile, referring to FIG. 2, a sensing sensor 15 may be separately installed on the parking surface of the parking surface 30 of the parking lot 100 where it is difficult to detect the vehicle 40 by the omnidirectional camera 10. . In this case, the sensing sensor 15 may be an ultrasonic sensor, a laser sensor, a photo sensor, or the like.

The detection sensor 15 may be installed on a parking surface located in the shooting blind spot of the omnidirectional camera 10. As shown in FIG. 2, the parking surface 32 located next to the structural pillar of the parking lot 100 may be difficult to photograph by the omnidirectional camera 10, and the parking surface 32 may include a detection sensor 15. Detection of the vehicle 40 can be facilitated.

In addition, the parking surface disposed at a position where it is impossible to determine whether the parking according to the change of the environmental factors including the illuminance may require the installation of the sensor 15. When the illuminance is higher than a predetermined value, it may be difficult to detect the vehicle 40 even if the photographing is possible by the omnidirectional camera 10. On the contrary, there is a possibility that the vehicle 40 may not be properly sensed even in the case of the parking surface having a low illuminance. In this way, even if it is possible to shoot by the omni-directional camera 10, the sensing sensor 15 is separately installed on the parking surface of the position where it is difficult to detect the vehicle 40 using the surveillance image can facilitate the detection of the vehicle.

The sensor 15 may recognize an object located on a parking surface on which the sensor 15 is installed, and generates a detection signal according to whether the sensor 15 is recognized.

The sensor 15 is connected to the omnidirectional camera 10 and operates in conjunction with the omnidirectional camera 10. Since the sensor 15 and the omnidirectional camera 10 are connected by one cable 20, no additional wiring is required, and the facility is simplified and unitary processing is possible.

On the other hand, Fig. 5 shows an example of a block diagram of the one-to-many parking lot management system of the present invention.

Referring to FIG. 5, the omnidirectional camera 10 installed in the parking lot 100 is connected to the management server 200 by a cable 20. The management server 200 receives the surveillance image information captured by the omnidirectional camera 10 and the detection signal generated by the detection sensor 15.

The management server 200 is provided with a vehicle detection module 210 for determining whether the vehicle 40 is parked on the plurality of parking surfaces 30 of the parking lot 100 and a memory 232 for storing a surveillance image. It consists of a security module 230. In addition, the management server 200 may be driven in conjunction with the emergency bell facility and the light control facility of the parking lot 100.

The vehicle detection module 210 includes an area setting unit 212, a feature detector 214, a detector 216, and the like.

The area setting unit 212 sets an area of the parking surface 30 that is an area where the vehicle 40 is parked in the surveillance image photographed by the omnidirectional camera 10. The feature detector 214 extracts the feature vector from the area of the parking surface set by the area setting unit 212, and the detector 216 uses the feature vector extracted by the feature detector 214 to extract the feature vector from the area of the parking surface. It is determined whether the vehicle 40 is parked.

The security module 230 includes a memory 232 for storing a surveillance image, and the surveillance image stored in the memory 232 may be set to be accessible when a security related problem occurs in a parking facility to which the present invention is applied. have.

The memory 232 included in the security module 230 may include a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (eg For example, SD or XD memory), RAM (Random Access Memory, RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), PROM (Programmable) Read-Only Memory), magnetic memory, magnetic disk, optical disk may include at least one type of storage medium.

In addition, the management server 200 may further include a display unit, a sound output module, a warning unit, a communication unit, an interface unit, and the like.

The display unit may output the surveillance image stored in the memory 232 or the image transmitted / received through the communication unit, and display a related UI (User Interface) or GUI (Graphic User Interface).

The display unit includes a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, It may include at least one of a 3D display.

The sound output module may output audio data received from the communication unit or stored in the memory. The sound output module may also output a sound signal related to a function (for example, fullness check, etc.) performed by the management server 200. The sound output module may include a receiver, a speaker, a buzzer, and the like.

The warning unit outputs a signal for notifying occurrence of an event of the management server 200. Examples of events generated by the management server 200 include full parking or tolerance conditions of the parking surface, accidents or crimes in the enforcement area.

The warning unit may output other forms other than the audio signal or the video signal, for example, a warning guide document, and in this case, a printer for outputting the warning guide document may be connected.

The communication unit may include one or more modules that enable communication between the management server 200 and the wired / wireless communication system or between the management server 200 and the network in which the management server 200 is located.

The technologies of the wireless Internet used in the communication unit include wireless LAN (Wi-Fi), wireless broadband (Wibro), world interoperability for microwave access (Wimax), wideband code division multiple access (WCDMA), and high speed downlink Packet Access), Long Term Evolution (LTE), and the like.

The interface unit serves as a path with all external devices connected to the management server 200. The interface unit receives data from an external device, receives power, transfers the data to each component inside the management server 200, or transmits data inside the management server 200 to an external device.

For example, a port for externally connecting a surveillance image stored in the memory 232, an external charger port, a wired / wireless data port, a memory card port, a port for connecting a device equipped with an identification module, audio I An input / output (O / O) port and a video input / output (I / O) port may be included in the interface unit.

On the other hand, the parking lot 100 to which the present invention is applied may be provided with a manong differential (not shown) indicating whether or not the vehicle 40 is parked on the plurality of parking surfaces 30. Manhole differentials may be installed integrally with the omnidirectional camera 10 or installed separately.

Manong differential outputs a display that can easily tell whether or not there is a parking space available to the driver entering the parking lot (100). The display may include a visual output for a preset color or an audio output for providing a voice regarding whether there is a full gap or a tolerance.

In this case, the management server 200 may control the output of the manhole difference according to the determination of the parking surface 30 of the vehicle detection module 210. For example, when it is determined that the vehicle 40 is parked on all the parking surfaces 30, the mangong vehicle may output the full vehicle display, and there is a space in which the vehicle 40 can be parked among the parking surfaces 30. If it is determined, the empty tolerance and the like may output a tolerance indication. In addition, the man-wheeled vehicle may be configured to individually indicate whether or not the vehicle 40 is parked with respect to each parking surface 30.

<1 multi-faceted parking lot management method>

Hereinafter, a management method for a multi-faceted parking lot management system having the above-described configuration will be described in detail.

Referring to FIG. 6, first, an omnidirectional camera 10 having a fisheye lens captures an omnidirectional surveillance image (S10), and a sensing sensor installed adjacent to a first parking surface that is part of a plurality of parking surfaces 30 ( 15 detects the vehicle 40 located on the first parking surface and generates a detection signal corresponding to the detection result (S12).

Subsequently, input data including the surveillance image and the detection signal is transmitted through the cable 20 connected to the omnidirectional camera 10 and the sensor 15 (S20), and the management server 200 connected to the cable 20. Receives the input data (S30).

As described above, since the omnidirectional camera 10 of the present invention is connected to one cable 20, it can simultaneously provide a parking guidance and security function with a low installation cost.

Subsequently, the vehicle detection module 210 of the management server 200 determines whether the vehicle 40 is parked on the plurality of parking surfaces 30 by using the input data, and the security module 230 of the management server 200. ) Stores the surveillance image included in the input data in the memory 232 (S40).

Specifically, if the parking surface of the plurality of parking surface 30 is difficult to determine by the sensing image as the first parking surface, the vehicle detection module 210 uses the detection signal of the input data to the vehicle on the first parking surface It is determined whether the 40 is parked, and whether the vehicle 40 is parked on the parking surface other than the first parking surface may be determined using the surveillance image among the input data.

Since the first parking surface is difficult to detect the vehicle 40 by the omnidirectional camera 10, whether the vehicle 40 is parked on the first parking surface is determined by the detection signal generated by the detection sensor 15. .

However, when the vehicle detection module 210 may determine whether the vehicle is parked on a part of the first parking surface using the surveillance image, the vehicle detection module 210 may additionally determine whether the vehicle 40 is parked by using the surveillance image. have.

For example, when the detection of the vehicle by the surveillance image is enabled according to the change in the illumination, the vehicle detection module 210 detects both the surveillance image by the omnidirectional camera 10 and the detection signal by the detection sensor 15. Parking can be determined by using.

At this time, it is not a problem when the judgment according to the surveillance video and the detection signal is not a problem. However, if the judgment according to the surveillance video and the detection signal does not coincide, the surveillance video and the detection signal are received again after a predetermined time. As a result, a more accurate detection of the vehicle 40 can be achieved.

In addition, unlike FIG. 6, the vehicle detection module 210 may basically determine whether the vehicle 40 is parked on the plurality of parking surfaces 30 by using the surveillance image included in the input data. In the case where it is difficult to determine whether the vehicle 40 is parked using only the surveillance image, the detection signal generated by the detection sensor 15 is used.

Specifically, the vehicle detection module 210 first determines whether the vehicle 40 is parked on the plurality of parking surfaces 30 by using the surveillance image included in the input data. If the detection of the vehicle on a specific parking surface is not performed smoothly due to the influence of the surveillance image or the surrounding environment, the vehicle detection of the parking surface may be performed again by additionally using the monitoring signal of the input data.

As shown in FIG. 7, the area setting unit 212 sets an area of the parking surface 30 that is an area where the vehicle 40 is parked in the surveillance image. In the area of the parking surface set by the area setting unit 212, the vehicle 40 may be photographed as illustrated in FIG. 8. The feature vector may be extracted to correspond to the vehicle 40 as illustrated in FIG. 9. It can be determined.

Specifically, a feature vector may be extracted from the surveillance image by using a vehicle recognition algorithm for recognizing the vehicle 40. As the vehicle recognition algorithm, any one of a scale-invariant feature transform (SIFT), speeded up robust features (SURF), histogram of oriented gradients (HOG), haar-like features, and a gabor filter may be used.

Here, the SIFT algorithm is a representative algorithm for extracting feature vectors of an image and has invariant characteristics in image rotation, scaling, shifting, partial illumination variation, and projective transform. The SIFT algorithm may extract properties such as the position, scale, and direction of the feature in consideration of the characteristic of the local image.

That is, in the first step, the sample point (or candidate pixel) is selected by searching for the maximum and minimum in the scale space generated by the difference-of-Gaussian (DOG) function (Scale-space extrema detection).

In the second step, keypoint localization is selected based on the stability value.

In the third step, one or more directions are assigned to each keypoint.

The last step is to create a keypoint descriptor using local image gradients.

A detailed description of the SIFT algorithm is given in detail in the article "Distinctive image features from scale-invariant keypoints".

In addition, the SURF algorithm finds features that are invariant to changes in the environment, taking into account changes in the environment such as size, lighting, and viewpoints from multiple images. The algorithm is greatly improved.

A detailed description of the SURF algorithm is given in detail in the article "Robust Interest Point Detection and Descriptor".

In addition, the HOG algorithm is based on the fact that the appearance and shape of a specific object in the image can be determined by the slope size or the distribution of the edge direction. The HOG algorithm divides an image into a plurality of regions called cells, and generates a histogram of a slope or a corner of each cell to recognize a specific object.

A detailed description of the HOG algorithm is given in detail in the "Histograms of oriented gradients for human detection" article.

In addition, the Haar-like features algorithm can recognize a specific object using a prototype representing the feature information of the edge and a prototype representing the feature information of the line. This is described in detail in the paper "An Extended Set of Haar-like Features for Rapid Object Detection".

A detailed description of the Gabor filter algorithm is also provided in detail in "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters."

The feature vector extracted by the vehicle recognition algorithm may be compared with previously stored learning data. Since the learning data includes a feature vector for a general vehicle image, it is possible to determine whether the object photographed on the parking area of the surveillance image is a vehicle and recognize the vehicle.

According to the parking lot management system of the present invention described above, the parking guidance system can be implemented at an amount equal to or less than that of the ultrasonic equipment, and in case of an accident, the base data can be easily obtained, and malfunctions caused by the cart or people can be reduced. No need to build CCTV, it can be linked with emergency bell or lighting control equipment, which can reduce cost, improve convenience of customers by using dual manhole, etc., and shorten construction period by simplifying wiring. The vehicle can be detected and the back vehicle can be detected.

On the other hand, the present invention can also be embodied as computer readable codes on a computer readable recording medium. Computer-readable recording media include all kinds of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, and may also be implemented in the form of a carrier wave (for example, transmission over the Internet). Include. 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. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the art to which the present invention belongs.

In addition, the above-described apparatus and method may not be limitedly applied to the configuration and method of the above-described embodiments, but the embodiments may be selectively combined in whole or in part in each of the embodiments so that various modifications may be made. It may be configured.

Claims

In the system for managing a parking lot in which a plurality of parking surfaces are arranged in a plurality of rows,

An omnidirectional camera installed on a ceiling of the parking lot between two neighboring rows of the plurality of rows and equipped with a fisheye lens to capture a surveillance image from all directions;

A cable connected to the omnidirectional camera to transmit the surveillance image; And

And a management server connected with the cable to receive the surveillance image.

The management server,

A vehicle detection module that determines whether a vehicle is parked on the plurality of parking surfaces by using the surveillance image; And

And a security module having a memory for storing the surveillance image.

Part of the parking surface disposed in the first column and the part of the parking surface disposed in the second column is captured in the surveillance image,

And the first row and the second row are two neighboring rows in which the omnidirectional camera is installed.
The method of claim 1,

5 to 7 parking surfaces arranged in the first row photographed by the surveillance image,

One parking lot management system, characterized in that five to seven parking surfaces arranged in the second row taken by the surveillance image.
The method of claim 1,

The vehicle detection module,

An area setting unit for setting an area of the parking surface photographed on the surveillance image;

A feature detector extracting a feature vector from an area of the parking surface set by the area setting unit; And

And a detection unit for determining whether the vehicle is parked in the area of the parking surface by using the feature vector.
The method of claim 1,

A detection sensor installed adjacent to a first parking surface which is a part of the plurality of parking surfaces, detecting a vehicle located on the first parking surface, and generating a detection signal corresponding to the detection result;

The cable is connected to the detection sensor interlocked with the omnidirectional camera, the multi-faceted parking lot management system, characterized in that for transmitting the detection signal to the management server.
The method of claim 4, wherein

The first parking surface,

And a third parking surface disposed at a position where it is impossible to determine whether the vehicle detection module is parked according to a change in environmental factors including a second parking surface disposed in the shooting blind spot of the omnidirectional camera and illuminance. One multifaceted parking lot management system characterized by.
The method of claim 5,

The vehicle detection module,

The multi-faceted parking lot management system of claim 1, wherein the detection signal determines whether the vehicle is parked on the first parking surface.
The method of claim 6,

When the vehicle detection module determines whether the vehicle is parked on the third parking surface using the surveillance image,

And the vehicle detection module further determines whether the vehicle is parked on the third parking surface by additionally using the surveillance image.
The method of claim 1,

And a mangong differential for outputting a predetermined display relating to whether the vehicle is parked on the plurality of parking surfaces.

The management server is a multi-faceted parking lot management system, characterized in that for controlling the output of the mangong differential according to the determination of the vehicle detection module.
In the method for managing a parking system in which a plurality of parking surfaces are arranged in a plurality of rows,

A first step of capturing the surveillance image of the omnidirectional camera having a fisheye lens;

A second step of transmitting the surveillance image through a cable connected to the omnidirectional camera;

A third step of receiving, by the management server connected to the cable, the surveillance image; And

And a fourth step of determining, by the vehicle detection module of the management server, whether the vehicle is parked on the plurality of parking surfaces by using the surveillance image.

The omnidirectional camera is installed on the parking lot ceiling between two neighboring rows of the plurality of rows,

Part of the parking surface disposed in the first column and the part of the parking surface disposed in the second column is captured in the surveillance image,

The first row and the second row are two neighboring rows in which the omnidirectional camera is installed.

The management server, the multiple parking lot management method further comprises a security module having a memory for storing the surveillance image.