KR102310567B1 - Method for sensing a car in a parking lot and server using the same - Google Patents

Abstract

According to the present invention, a method for detecting a vehicle in a parking lot comprises: a step in which in a state in which at least one radar module for detecting a vehicle and at least one camera are installed in the parking lot, a parking lot server causes at least one radar module to detect a moving object to obtain detection information; a step in which the parking lot server causes at least one camera to acquire image information about the parking lot; and a step in which the parking lot server receives the detection information from the at least one or more radar modules and receives the image information from the at least one or more cameras, and primarily determines whether the vehicle is located in the parking lot on the basis of the detection information to secondarily determine whether the vehicle is located in the parking lot on the basis of the image information according to the previous determination result. It is possible to detect the presence of a vehicle in a parking lot more accurately.

Description

A method for detecting a vehicle in a parking lot and a server using the same

The present invention relates to a method for detecting a vehicle in a parking lot, and more particularly, in a method for detecting a vehicle in a parking lot, in which at least one radar module and at least one camera for detecting the vehicle are installed in the parking lot in the parking lot server, causing the at least one radar module to detect a moving object and obtain sensing information; allowing the parking server server to acquire image information about the parking lot by the one or more cameras; and the parking lot server receives the detection information from the at least one or more radar modules and receives the image information from the at least one or more cameras, primarily based on the detection information, whether the vehicle is located in the parking lot and determining whether the vehicle is located in the parking lot based on the image information secondary according to the determination result.

As large-scale buildings such as residential-commercial apartments and large shopping malls have been built, large-scale underground parking has become an essential element. In addition, development of a system for managing a large-scale underground parking lot, such as access vehicle management and display of available parking spaces, is continuously being made.

In particular, various technologies such as a camera, a radar module, and an ultrasonic module are used in relation to vehicle detection in a parking lot. The ultrasonic module currently used in the parking lot must be installed one by one on each parking space, and is placed on the parking surface for power and data communication. It is necessary to install a raceway, which requires a lot of cost.

In addition, when tracking the movement of a vehicle in a parking lot using only a camera, errors occurred due to overlapping vehicles, foreign substances in the camera lens, weather, and the effects of light and shadow in the case of night.

Therefore, a new method that requires less installation cost and accuracy while sensing a wide range was required, and the present inventors propose a method for detecting a vehicle in a parking lot that maximizes the recognition rate using a radar module and a camera and a server using the same want to

An object of the present invention is to solve all of the above problems.

Another object of the present invention is to more accurately detect the presence of a vehicle in a parking lot by sequentially using a radar module and a camera.

In addition, another object of the present invention is to improve a vehicle detection function by performing machine learning using artificial intelligence.

In order to achieve the object of the present invention as described above and to realize the characteristic effects of the present invention to be described later, the characteristic configuration of the present invention is as follows.

According to an aspect of the present invention, in a method for detecting a vehicle in a parking lot, in a state in which at least one or more radar modules and at least one or more cameras for detecting the vehicle are installed in the parking lot, the parking lot server includes the at least one radar causing the module to detect a moving object to obtain sensing information; allowing the parking server server to acquire image information about the parking lot by the one or more cameras; and the parking lot server receives the detection information from the at least one or more radar modules and receives the image information from the at least one or more cameras, primarily based on the detection information, whether the vehicle is located in the parking lot and determining whether the vehicle is located in the parking lot based on the image information secondarily according to the determination result.

In addition, according to another aspect of the present invention, in the parking lot server for detecting a vehicle in the parking lot, in a state in which at least one or more radar modules and at least one or more cameras for detecting the vehicle are installed in the parking lot, the at least one or more radar modules a communication unit that detects a moving object and acquires detection information, and causes the at least one camera to acquire image information about the parking lot; database; and receiving the detection information from the at least one or more radar modules through the communication unit, receiving the image information from the at least one or more cameras, and primarily determining whether the vehicle is located in the parking lot based on the detection information There is provided a parking lot server comprising a processor for determining whether the vehicle is located in the parking lot based on the image information secondarily based on the image information according to the determination result.

According to the present invention, the following effects are obtained.

The present invention has an effect of more accurately detecting the presence of a vehicle in a parking lot by sequentially using a radar module and a camera.

In addition, the present invention has an effect of improving the vehicle detection function by performing machine learning using artificial intelligence.

1 is a diagram showing a schematic configuration of a radar system installed in a parking lot according to an embodiment of the present invention.
2 is a diagram showing a schematic configuration of a radar module according to an embodiment of the present invention.
3 is a diagram illustrating a detection result of a radar module according to an embodiment of the present invention.
4 is a view showing the appearance of a parking lot and a vehicle photographed with a camera and analyzed by an AI algorithm according to an embodiment of the present invention.
5 is a diagram illustrating an example of a point output to a radar according to an embodiment of the present invention.
6 is a diagram illustrating a learning process of an AI module according to an embodiment of the present invention.
7 is a diagram illustrating in detail the configuration of a radar module according to an embodiment of the present invention.
8 is a view showing a location of a radar module for a specific parking space according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0023] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be embodied in other embodiments without departing from the spirit and scope of the invention. In addition, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those of ordinary skill in the art to easily practice the present invention.

1 is a diagram showing a schematic configuration of a radar system installed in a parking lot according to an embodiment of the present invention.

As shown in FIG. 1 , the parking lot server 100 of the present invention includes a processor 110 and a database 120 , and may communicate with a radar module 200 or a camera 300 installed in the parking lot. .

In addition, the parking lot server may communicate with the plurality of radar modules 200 and the camera 300 including a communication unit (not shown), and the communication unit at this time may be implemented with various communication technologies. Namely, Ethernet, RS232, RS485, Wi-Fi (WIFI), WCDMA (Wideband CDMA), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), HSPA (High Speed Packet Access), Mobile WiMAX (Mobile WiMAX), WiBro, LTE (Long Term Evolution), 5G, Bluetooth, infrared data association (IrDA), NFC (Near Field Communication), Zigbee, wireless LAN technology, etc. This can be applied. In addition, when a service is provided by being connected to the Internet, TCP/IP, which is a standard protocol for information transmission on the Internet, may be followed.

Next, the database 120 of the present invention may store information received from the radar module 200 and the camera 300 . In this case, an external database may be used instead of the database 120 in the parking lot server 100 .

2 is a diagram showing a schematic configuration of a radar module according to an embodiment of the present invention.

As can be seen in FIG. 2 , the radar module 200 may include an antenna 210 , a measurement sensor 220 , a microcontroller 230 , and the like, and the components may be merged or separated into one PCB. , microcontroller, etc. can be implemented in one chip. The role of each of the above components will be described later.

The radar module 200 of the present invention uses a microwave, which is a microwave, as a signal, and uses a microwave, centimeter wave, and millimeter wave signal to send a communication radio wave to a distant place. It can mean a frequency between 20 and 300 GHz. .

Recently, along with autonomous vehicles, products that use frequencies of 20-30GHz and 60-80GHz as short-range and long-distance radars are attracting a lot of attention.

Hereinafter, a process of detecting a vehicle in a parking lot by using the radar module 200 and the camera 300 will be described. First, at least one radar module 200 and at least one camera 300 for detecting a vehicle may be installed in a parking lot.

The processor 110 of the parking lot server 100 may cause the at least one radar module 200 to detect a moving object to obtain detection information. In this case, the detection information may include the number or location of parking spaces available in the parking lot by checking whether the moving object is a vehicle (or other object) and whether it is parked.

3 is a diagram illustrating a detection result of a radar module according to an embodiment of the present invention.

First, for convenience of explanation, it can be assumed that a plurality of parking surfaces (ex 10) exist in a parking lot, and a specific radar module 200 using a process of detecting the plurality of parking surfaces and outputting the detected result as a point exists. have.

The specific radar module 200 outputs a point corresponding to a moving object based on a plurality of parking surfaces, and acquires detection information based on the properties of the points, such as the number of points recorded on each of the plurality of parking surfaces, and the movement of the points can do.

Specifically, the specific radar module 200 can cover a predetermined number (ex 10) of parking surfaces among parking surfaces existing in the parking lot, and outputs a signal and detects a predetermined number of parking surfaces based on the reflected signal. A moving object can be detected.

As can be seen in FIG. 3 , as a result of detection by the specific radar module 200, a point indicating the presence of a moving object may appear on each parking surface of an area representing a parking lot. That is, when a point appears on a certain parking surface, it can be confirmed that a moving object exists on the corresponding parking surface.

In addition, the specific radar module 200 may cluster based on a predetermined number of points, and determine whether the vehicle is parked on the parking surface based on the movement or direction of the cluster. That is, it is possible to determine whether the moving object corresponds to a vehicle or whether the vehicle is parked based on the properties of the points, such as the number of points and movement.

For example, as shown in FIG. 3 , in the specific radar module 200, the parking plane t5 and the related specific radar module 200 are located in the opposite direction based on the location (the red triangle at the bottom of each parking plane in FIG. 3 ). It is possible to determine whether the object is a moving object by checking a predetermined number of points (ex 10) and determining whether the number of points is equal to or greater than a preset number. In addition, the specific radar module 200 may determine whether the moving object (vehicle) enters or leaves the parking surface through the movement of the points, and may determine that the moving object (vehicle) is parked.

Looking at the parking surface t5 area (square box) of FIG. 3( a ), a number of points greater than a predetermined number (ex 10) in the opposite direction based on the location of the specific radar module 200 is a green display. You can see that they are lined up like the location of the vehicle on the screen. The specific radar module 200 may determine that the vehicle is moving (parking) with respect to an object moving from the left to the second parking surface of the parking surface t5.

As a result, as can be seen in the right figure of FIG. 3(a), it is indicated that a moving object (vehicle) is being parked on the second parking surface from the left among the four parking surfaces in the t5 area covered by the specific radar module 200, and the remaining It may be determined that parking is possible only on the parking surface.

On the other hand, through the points, it is possible to sequentially determine at which parking surface the moving object is stopped (parked) and whether the moving object corresponds to a vehicle, which will be described in detail below.

As can be seen in FIG. 3A , points corresponding to the moving object on the parking surface t5 may be visually displayed as green (the color may vary according to settings). For reference, the green points may mean some of the reflected signals (ex strong signals) acquired from the moving object recognized through the specific radar module 200, and the (green) points and the parking surface The administrator or the like may check the display unit interlocked with the specific radar module 200 .

In addition, the center (cluster center) of a plurality of green points (thick points in the drawing) scattered over a certain range can be displayed as one red point (a thick point in the drawing) (the color is set according to the setting). may vary), through which it can be more easily determined whether the corresponding moving object has entered the parking surface.

When the plurality of green points and red points stop moving after entering the parking surface, the specific radar module 200 may determine that the corresponding moving object has stopped on the corresponding parking surface. When the points stop moving, the plurality of green points disappear (depending on the settings, but the red points may remain and indicate the position of the moving object), and at t1, t2, t5, and t6 of FIG. A (blue) rectangular point may be created to be located inside the parking surface as shown in FIG. Here, the blue square point may mean that the movement of the moving object stops and exists in the corresponding parking plane.

Next, the specific radar module 200 may determine whether the moving object stopped at the parking surface is a vehicle based on the properties of the points, such as the number, movement, and direction of the points. For example, when the number of green points is less than or equal to a preset number (ex 5), it may be determined whether the vehicle is a vehicle or not.

In addition, whether the movement or direction of the point coincides with the direction in which the general vehicle moves may be considered. When it is determined that the vehicle is parked on both sides of the parking surface, if the moving object moves at a right angle of 90 degrees from the center parking surface (normal vehicles are parked in a curved shape), it moves to a path that cannot be passed considering the size of the vehicle. If the movement is opposite to that of a general vehicle, such as when moving, it may be determined that it is unclear whether the moving object is a vehicle. Also, when the shape of the green point spread out of the vehicle shape or larger than a preset area, it may be determined whether the moving object is a vehicle or not.

Additionally, as another embodiment, when the reflected signal (signal strength) received from the moving object is smaller than the range of the preset SNR value, the specific radar module 200 may determine that it is unclear whether the moving object is a vehicle, It may be determined whether the moving object is a vehicle by using the Doppler effect.

As a result, the specific radar module 200 may check whether the moving object has entered the parking surface and stopped (parking), and may perform a process of determining whether the moving object is a vehicle. Depending on the settings, the process may be performed by the parking lot server 100 .

In the case of FIG. 3(b), the specific radar module 200 generates points (green, red) again on the parking surface where the vehicle is located (the blue square point disappears) and moves and exits. It can be tracked, and when the vehicle disappears completely, it can be determined that the vehicle can be parked on the parking surface. For reference, the blue square point may disappear when the red point leaves the parking surface.

The (specific) radar module 200 may acquire sensing information based on the number, movement, direction, etc. of points recorded on each of the plurality of parking surfaces. Here, the sensing information may include whether the moving object corresponds to the vehicle, on which parking surface the vehicle is parked among a plurality of parking surfaces, and the like.

In addition, as described above, it is possible to determine whether the moving object corresponds to the vehicle through the Doppler effect using the signal output from the parking surface and the reflected signal, that is, the signal strength and direction. In particular, when the SNR value corresponds to a signal equal to or greater than a predetermined SNR value, the SNR value may also correspond to the attribute of the point because it is output as a (green) point.

Specifically, if the wavelength of the received reflected signal is shorter than the predetermined reference value, the radar module 200 may determine that the moving object approaches the radar module 200, and the wavelength of the received reflected signal is set to the predetermined reference value. If longer than the value, it may be determined that the moving object moves away from the radar module 200 . That is, the radar module 200 may detect the moving direction of the moving object.

In this case, the radar module 200 may determine whether the moving direction of the moving object coincides with the moving direction of the general vehicle. For example, if it is determined that the vehicle is parked on both sides of the parking surface, and a moving object moves at a right angle of 90 degrees from the center parking surface (normal vehicles are parked in a curved shape), considering the size of the vehicle, it cannot pass. When a movement opposite to that of a general vehicle is shown, such as when moving on a non-existent path, the radar module 200 may acquire sensing information indicating whether the moving object is a vehicle or not.

Also, as another embodiment, when the reflected signal received from the moving object is smaller than the range of the preset SNR value, the radar module 200 may acquire sensing information indicating that it is unclear whether the moving object is a vehicle. Of course, in this case, it will be possible to determine whether the moving object is a vehicle by considering not only the SNR value but also other properties of the points, such as the number, movement, and direction of the points.

As another embodiment, the radar module 200 may acquire detection information indicating that it is unclear whether the vehicle is a vehicle when the moving object passes without stopping or continuously moves on the parking surface by tracking the position of the moving object.

In the above, the (specific) radar module 200 determines whether it is a vehicle, whether parking is possible, etc., but in some cases, the radar module 200 outputs only the number, shape, direction, and reflected signal information (SNR) of the points. It is transmitted only to the server 100 , and the determination may be performed in the parking lot server 100 .

4 is a view showing the appearance of a parking lot and a vehicle photographed with a camera and analyzed by an AI algorithm according to an embodiment of the present invention.

The parking lot server 100 may cause the at least one or more cameras 300 to acquire image information about the parking lot. In addition, the parking lot server 100, based on the received image information, when it is unclear whether the radar module 200 is a moving object or an object located on the parking surface is a vehicle, the parking lot server 100 may request information of the area. And, if there is the request, the parking lot server 100 may determine whether the vehicle is located in the requested area by analyzing and comparing it with the information of the radar module 200 based on the camera image information.

Specifically, the parking lot server 100 may determine whether a moving object existing in the requested area (parking surface) is a vehicle in real time based on the received image information. Depending on the setting, the parking lot server 100 may determine, based on the image information, the total number of parking surfaces in the parking lot, the number of parking spaces available in the parking lot, and whether there are parking surfaces available in the parking lot.

In some cases, the parking lot server 100 analyzes the vehicle at a predetermined period based on the image information received through the camera 300 and compares and analyzes the vehicle with the radar information to determine whether the vehicle exists in the parking surface (requested area). Whether my vehicle is located) can be determined.

Therefore, through the interlocking and analysis of the radar module 200 and the camera 300, it is possible to determine the total number of parking surfaces in the parking lot, the number of parking spaces available in the parking lot, and whether there is a parking space available in the parking lot. have.

As described above, the processor 110 of the parking lot server 100 may receive detection information from at least one or more radar modules 200 , and may receive image information from at least one or more cameras 300 .

Next, the processor 110 of the parking lot server 100 primarily determines whether a vehicle is located in the parking lot based on the detection information, and secondary image information according to the determination result and the request of the radar module 200 It can be determined whether the vehicle is located in the parking lot based on the . That is, whether to use the image information may be determined according to the determination result of the detection information, which is the first determination result.

Specifically, it is determined that it is unclear whether the moving object corresponds to the vehicle based on the properties of the points, such as the number of points recorded on each of the plurality of parking surfaces acquired by the (specific) radar module 200, the movement of the points, and the direction of the points. can do. That is, the specific radar module 200 may transmit specific detection information indicating that it is unclear whether the moving object corresponds to a vehicle to the parking lot server 100 .

5 is a diagram illustrating an example of an output point according to an embodiment of the present invention.

A red triangular mark at the bottom of the drawing means the position of the radar module 200, and green (a number of thin dots) and red points (a thick rhombus-shaped dot) in the drawing may indicate a moving object. The radar module 200 may determine on which parking surface the moving object is located and whether the moving object corresponds to a vehicle through the point.

When the specific detection information indicating that it is unclear whether the moving object corresponds to the vehicle is received from the specific radar module 200, the processor 110 receives specific image information received from the specific camera 300 for photographing a plurality of parking surfaces. Based on whether the moving object corresponds to the vehicle, it may be determined whether the vehicle is parked on which parking surface among a plurality of parking surfaces.

As can be seen in FIG. 4 , the processor 110 of the parking lot server 100 determines whether it is a vehicle, whether it is a car, a bus, or a motorcycle, etc. for each moving object existing on the parking surface included in the specific image information. It can be determined, and what is used at this time will be the AI module included in the parking lot server 100 .

6 is a diagram illustrating a learning process of an AI module according to an embodiment of the present invention.

An AI algorithm may be required to calculate whether a vehicle is located in a parking lot based on image information. This may be performed by the AI module included in the parking lot server 100, and it may be assumed that at least one parameter exists in the AI module.

The processor 110 of the parking lot server 100 may perform a deep learning operation while passing the image information for learning including the moving object for learning through the AI module. The result of performing the calculation in the AI module may be an output value. Here, the calculated value is a value indicating whether the moving object for learning included in the image information for learning is a vehicle, and may correspond to a probability (ex 0.9). For reference, if the calculation result is 1, it will correspond to the meaning that the probability that the learning moving object is a vehicle is 100%.

The processor 110 may adjust at least one parameter by using a difference value between the calculated value and the correct answer value. For reference, the correct answer value corresponds to the correct answer indicating whether the moving object for learning is a vehicle or not a vehicle, and it is also possible to classify the object whether it is a bus or a motorcycle. For example, the probability of being a bus is 90%, and a probability of being a motorcycle is 20%, so it can be classified. The processor 110 may repeatedly adjust at least one parameter while passing the plurality of training image information to the AI module.

In the state in which the parameter is adjusted, the processor 110 passes the specific image information received from the specific camera 300 photographing a plurality of parking surfaces through the AI module, and more accurately determines whether the moving object corresponds to the vehicle can do. That is, it is possible to automatically determine whether the moving object included in the specific image information is a vehicle through the AI module including the learned parameter.

After all, the present invention primarily checks whether the vehicle is a vehicle using the radar module 200, and secondarily, at the request of the radar module 200, whether the vehicle is a vehicle in the camera 300 image through the AI module can be checked.

For reference, the radar module 200 may transmit a radar signal in the form of a signal (pulse) or a continuous signal (pulse) in a specific area through the included antenna 210, and receive a reflected signal therefor. .

That is, each of the radar modules 200 may receive a signal that a transmitted radar signal collides with a vehicle located within a detection range and is reflected to obtain vehicle motion information and may be displayed in the form of a point.

The specific region may mean a frequency domain or a time domain. For example, a radar signal may be transmitted only in a specific frequency band, and a signal may be continuously transmitted in a frequency band within an allowable range. In addition, the radar signal may be transmitted only in a specific time period, and the signal may be continuously transmitted regardless of time. This may vary depending on your settings.

In addition, the radar module 200 calculates motion information including speed information of the vehicle and distance information between the radar module and the vehicle by analyzing the change in frequency and magnitude of the reflected signal received through the included MCU 230 . can do.

That is, the MCU 230 may acquire vehicle motion information based on a change in frequency and magnitude of a transmission signal and a reflection signal, a time interval between the transmission signal and the reception signal, and the like.

7 is a diagram illustrating in detail the configuration of a radar module according to an embodiment of the present invention.

Unlike FIG. 2 , in FIG. 7 , the configuration of the radar module 200 is illustrated in detail, and a process will be described based on this.

The radar module 200 may include a control unit 710 , a signal processing unit 720 , a signal transmitting unit 730 , a signal receiving unit 740 , a signal antenna 220 , a communication unit 750 , and the like. The radar module 200 may transmit a radar signal through the antenna 220 and receive a reflected signal to acquire vehicle motion information.

In this case, the antenna 220 may receive a radar signal from the controller 710 through the signal transmitter 730 and the signal receiver 740 or transmit a reflected signal.

In addition, the signal processing unit 720 may calculate the vehicle motion information by analyzing the changes in the frequency and magnitude of the reflected signal received from the control unit 710 .

The radar module 200 may transmit the acquired motion information to the parking lot server 100 through the communication unit 750 .

8 is a view showing a location of a radar module for a specific parking space according to an embodiment of the present invention.

In a state in which the parking lot is located outdoors and a plurality of parking spaces exist in the parking lot, it can be assumed that the plurality of parking spaces are in the form of N x M. Here, N represents the number of parking spaces in the vertical length, and M represents the number of parking spaces in the horizontal length.

In addition, it can be assumed that the N x M type parking space includes a specific p x q type parking space group (provided that p ≠ q, p <= N, q <= M).

The total number of parking spaces is N x M, and in the case of a specific parking space group, it can be seen that the number of vertical parking spaces means p and the number of horizontal parking spaces means q. The specific parking space group may mean an arbitrary group among all parking spaces (N x M).

In this case, the position of any one of the first radar module 200 - 1 or the second radar module 200 - 2 may be determined according to the following situation.

First, according to an embodiment, when p corresponding to the vertical length of a specific parking space group is greater than q corresponding to the horizontal length, the positions of the first and second radar modules are located on the left or right side of the specific parking space group. can be located

In addition, when p corresponding to the vertical length of the specific parking space group is smaller than q corresponding to the horizontal length, it may be located above or below the specific parking space group.

For example, in Fig. 8(a), the vertical length p is greater than the horizontal length q, so the radar module 200 is located on the left side, and Fig. 8(b) shows the vertical length p. Since it corresponds to a case smaller than the horizontal length q, it can be confirmed that the radar module 200 is located at the lower side.

That is, the radar module 200 is installed on the side corresponding to the longer length of the horizontal or vertical length.

In addition, according to another embodiment, when p corresponding to the vertical length of a specific parking space group is smaller than q corresponding to the horizontal length, the positions of the first and second radar modules are located on the left or right side of the specific parking space group. can be located

That is, the radar module 200 is installed on the side corresponding to the shorter of the horizontal or vertical length, as can be seen in FIGS. 8( c ) and 8 ( d ).

As a result, the position of the radar module may be determined based on the structure (horizontal and vertical length) of a specific parking space group.

As described above, the reason to sense a large area in the sectoral shape is to more effectively utilize the detection range of the radar module 200 . It is essential to check the movement/parking information of a large number of vehicles in an outdoor parking lot.

In the above, it is assumed that a plurality of parking spaces or a specific parking space group has a rectangular shape, but it is not necessary to be limited thereto, and this depends on the shape of the parking lot.

Meanwhile, a plurality of radar modules 200 installed in the parking lot are installed to detect the entire parking lot. However, in this case, the detection ranges between the radar modules 200 may overlap each other. In this case, the overlapping area may be minimized by adjusting the position or the detection range of the radar module 200 .

That is, the first radar module and the second radar module may be respectively positioned in the parking lot so that the overlapping area of the first detection range and the second detection range is smaller than the preset area.

Here, the preset area may vary according to the setting, and may correspond to a certain percentage value (ex 5%) of the total area of the parking lot or a predetermined area value (ex 5m ² ).

The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

In the above, the present invention has been described with specific matters such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , those of ordinary skill in the art to which the present invention pertains can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and not only the claims described below but also all modifications equivalently or equivalently to the claims described below belong to the scope of the spirit of the present invention. will do it

100: parking lot server
110: processor
120: database
200: radar module
210: antenna
220: sensor
230: MCU
710: control unit
720: signal processing unit
730: signal transmitter
740: signal receiver
750: communication department

Claims (6)

A method for detecting a vehicle in a parking lot, the method comprising:
In a state in which at least one radar module for detecting a vehicle and at least one or more cameras are installed in the parking lot,
(a), by the parking lot server, causing the at least one radar module to detect a moving object and obtain detection information;
(b) the parking lot server, allowing the at least one camera to acquire image information about the parking lot; and
(c) the parking lot server receives the detection information from the at least one or more radar modules and receives the image information from the at least one or more cameras,
primarily determining whether the vehicle is located in the parking lot based on the detection information, and secondarily determining whether the vehicle is located in the parking lot based on the image information according to the determination result;
including,
In step (a),
In a state in which a plurality of parking surfaces exist in the parking lot, and a specific radar module using a process of detecting the plurality of parking surfaces and outputting the detected result as a point exists,
The specific radar module causes a plurality of first color points corresponding to the moving object to be displayed through an interlocked display unit, and a center of the plurality of first color points is displayed as a second color point, so that an administrator can make the movement A method characterized in that it is determined whether the object has entered the inside of the parking surface. According to claim 1,
In step (a),
In the state that the plurality of parking surfaces exist in the parking lot, and the specific radar module using a process of detecting the plurality of parking surfaces and outputting the detected result as the point exists,
The specific radar module outputs the point corresponding to the moving object based on the plurality of parking surfaces, and based on the number of points recorded in each of the plurality of parking surfaces or the movement of the points, the moving object Method characterized in that obtaining the detection information indicating whether the vehicle corresponds to the vehicle and on which parking surface the vehicle is parked among the plurality of parking surfaces. 3. The method of claim 2,
When receiving specific detection information from the specific radar module that it is unclear whether the moving object corresponds to the vehicle based on the number of points recorded on each of the plurality of parking surfaces or the movement of the points,
The parking server is, based on the specific image information received from the specific camera photographing the plurality of parking surfaces, whether the moving object corresponds to the vehicle, and on which parking surface among the plurality of parking surfaces the vehicle is parked. A method comprising determining whether or not there is. 4. The method of claim 3,
At least one parameter exists in the AI module to calculate whether the vehicle is located in the parking lot based on the image information,
The parking lot server performs an operation while passing the learning image information including the moving object for learning through the AI module, and adjusts the at least one parameter using the difference value between the calculated value and the correct answer value as a result of the operation in the state of
Method characterized in that it is determined whether the moving object corresponds to the vehicle while passing the specific image information received from the specific camera that has photographed the plurality of parking surfaces through the AI module. According to claim 1,
In step (b),
When there is a request from the at least one or more radar modules, the parking lot server determines whether the vehicle is located in the parking lot in real time based on the image information received from the at least one or more cameras. . In the parking lot server for detecting the vehicle in the parking lot,
In a state in which at least one radar module for detecting a vehicle and at least one or more cameras are installed in the parking lot,
a communication unit for causing the at least one radar module to detect a moving object to obtain detection information, and for the at least one camera to obtain image information about the parking lot;
database; and
Receives the detection information from the at least one radar module through the communication unit, receives the image information from the at least one or more cameras, and primarily determines whether the vehicle is located in the parking lot based on the detection information and a processor for secondarily determining whether the vehicle is located in the parking lot based on the image information according to the determination result;
including,
In a state in which a plurality of parking surfaces exist in the parking lot, and a specific radar module using a process of detecting the plurality of parking surfaces and outputting the detected result as a point exists,
The specific radar module causes a plurality of first color points corresponding to the moving object to be displayed through an interlocked display unit, and a center of the plurality of first color points is displayed as a second color point, so that an administrator can make the movement Parking server, characterized in that to determine whether the object has entered the inside of the parking surface.

Images