JP7012070B2 - Parking guidance system and its control method - Google Patents

Description

The present invention relates to a parking guidance system to which an efficient object recognition and number recognition method is applied, and specifically, the present invention relates to a parking guidance system to which motion recognition, object recognition, parking surface setting, and number recognition method are applied.

The demand for vehicles is increasing rapidly along with economic growth and income growth, but the human power to manage road conditions and traffic conditions is in short supply. Therefore, efforts are being made to overcome the current traffic management system with limited personnel.

As part of such efforts, the development of automatic vehicle recognition (including number recognition) systems is being actively carried out. Through vehicle recognition or vehicle number (character) recognition, it can be efficiently used in various fields such as traffic control, traffic volume investigation, stolen vehicle arrest, entry / exit vehicle control, parking facility management, etc., and many studies have been conducted to date. Has been made.

In particular, the process for recognizing the characters on the vehicle license plate is different from other character recognition, and it is powerful because it causes distorted phenomena due to camera noise, lighting changes, weather, etc. due to the influence of the surrounding environment. Processing method should be considered. However, in the case of the license plate area of the vehicle, the content is limited due to its unique characteristics, and the structure is simple as compared with general character recognition (pattern recognition). For this reason, License Plate Recognition (LPR) is the most common system for efficiently managing environmental characteristics, increased demand for vehicles, labor supply and demand, and resource management of parking spaces. It can be said that.

The LPR system or number recognition technology was first developed in the United Kingdom in 1976. After that, for decades, as the technology evolved and the market demand increased, the LPR system grew and gradually expanded to Europe including Southeast Asia. As a result, the LPR system market is also growing significantly in the North American region of the United States. This provided a strong motivation for efficient crime suppression and prevention technologies, and triggered a revitalization of the wider market.

Past vehicle number recognition (LPR) or ALPR (Automated LPR) systems use Optical Character Recognition (OCR) on images acquired from cameras to interpret vehicle license plates. , Applied in the Surveillance Method. In recent years, under the name of parking management system, we have been doing efficient work of parking space. Currently, the LPR system solves the current situation of labor supply and demand and labor cost burden by the manager paying the parking fee regarding the parking environment, and the demand for the LPR system is increasing, and the technology is changing and developing. Has become persistent.

In addition, for reasons such as public safety and personal security, CCTV (closed circuit television) has been installed here and there in modern times, and it is still in progress, and the materials recorded by CCTV etc. are for crime prevention. It is used as evidence material when a crime occurs.

However, in order to confirm a specific vehicle by CCTV, the expected flow line of the vehicle is grasped in advance and the CCTV in the flow line is monitored in real time, or the recorded contents are played back one by one to confirm the vehicle. There are inconveniences of having to do it, and human, physical, and time constraints.

none

The present invention relates to a parking guidance system to which an efficient object recognition and number recognition method is applied, and specifically, to provide a parking guidance system to which motion recognition, object recognition, parking surface setting, number recognition method, etc. are applied. And.

On the other hand, the technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned above are usually described in the technical fields to which the present invention belongs. It will be clearly understood by those who have the knowledge of.

In the parking guidance method, which is one aspect of the present invention for achieving the above technical problem, the first step in which the camera inputs at least one image and the motion is sensed in the at least one image. The second step of determining whether or not the motion is detected, the third step of attempting to recognize an object in at least one video when the motion is detected, and the recognized object when the object recognition is successful. The fourth step of determining whether an area overlapping the first parking surface which is at least a part of a predetermined plurality of parking surfaces has occurred, and when the overlapping area has occurred, the recognized object is a vehicle. The fifth step of determining whether the vehicle is a human being, and if the recognized object is a vehicle, whether the vehicle occupies a predetermined ratio or more of the entire area of the first parking surface. A sixth step of determining whether or not the vehicle is used, a seventh step of determining that the vehicle is parked on the first parking surface when the vehicle occupies an area equal to or larger than the predetermined ratio, and the vehicle. It is characterized by including an eighth step of recognizing the vehicle number of the vehicle.

The third step further sets a third step of determining whether an object having a predetermined size or larger exists in the video, and an object box separated by a certain distance based on the object. Including the third step and the fifth step, it is determined whether the object existing in the object box is a vehicle or a human being.

The eighth step further performs a number recognition operation for the eighth step of setting a predetermined lower end area of the entire area of the object box as a number recognition area and the number recognition area. It includes the 8-2 step to be performed and the 8-3 step to accumulate and store the related value between the position of the license plate of the vehicle and the object box from the failure and success of the number recognition operation. ..

When the eighth step is applied to another vehicle other than the vehicle, among the accumulated related values,'the position of the license plate of the other vehicle and the object box of the other vehicle A first related value that is most similar to the "relevant value between" is determined, and the number recognition operation of the other vehicle is performed by the model related to the first related value.

When the recognized object is a human being, the step after the fifth step further includes a step of maintaining the existing state of the first parking surface as it is, and the existing state is an entry or an empty vehicle. It is a state.

In the sixth step, if the vehicle does not occupy more than the predetermined percentage of the area, the first parking surface further includes a step of determining that the vehicle has left.

If the motion is not detected for a predetermined time or longer in the second step, the third step is performed.

Further, the parking guidance system, which is another aspect of the present invention for achieving the above technical problem, includes a camera into which at least one image is input and a case where motion is sensed in the at least one image. The control unit includes, when the object recognition is successful, the recognized object is at least a part of a predetermined plurality of parking surfaces. When it is determined whether an area overlapping the parking surface of 1 is generated, when the overlapping area is generated, it is determined whether the recognized object is a vehicle or a human, and the recognized object is a vehicle. It is determined whether or not the vehicle occupies an area of a predetermined ratio or more in the entire area of the first parking surface, and when the vehicle occupies an area of a predetermined ratio or more, the vehicle occupies the area of the predetermined ratio or more. It is characterized in that it is determined that the vehicle is parked on the first parking surface and the vehicle number of the vehicle is recognized.

The control unit determines whether an object having a predetermined size or larger exists in the video, sets an object box separated by a certain distance from the object, and sets the object box.
It is determined whether the object existing in the object box is a vehicle or a human.

The control unit sets a predetermined lower end area of the entire area of the object box as a number recognition area, performs a number recognition operation on the number recognition area, and fails or succeeds in the number recognition operation. , The related value between the position of the license plate of the vehicle and the object box is accumulated and stored in the memory.

When the number recognition operation is applied to another vehicle that is not the vehicle, the control unit determines that, among the accumulated related values, the position of the license plate of the other vehicle and the position of the license plate of the other vehicle The first related value most similar to the related value between the object boxes is determined, and the number recognition operation of the other vehicle is performed by the model for the first related value.

When the recognized object is a human being, the control unit maintains the existing state of the first parking surface as it is, and the existing state is an entering or empty state.

The present invention relates to a parking guidance system to which an efficient license plate detection and number recognition method is applied. Specifically, the present invention provides a user with a parking guidance system to which motion recognition, object recognition, parking surface setting, number recognition method, etc. are applied. Can be provided.

In the present invention, regarding motion recognition, the movement with the previous image is determined from the camera image, and the operation is performed only when there is movement, and even when there is no movement, the processing operation is performed at a constant cycle, and the object recognition is performed. Accuracy can be improved by detecting an object of a certain size or larger on the screen, specifying the detection position in a square shape, and then determining the type.

Further, in the present invention, regarding the surface setting in the parking lot, when the detected object is identified in front of a certain amount or more in the parking scene, a portion overlapping with the corresponding parking surface is searched for and treated as a shield. If the ratio of overlapping with each parking surface exceeds a certain value in the car, it is treated as occupied by the parking surface, there is no automobile object with a ratio of overlapping with the corresponding parking surface larger than a certain value, and it does not correspond to shielding. In that case, the error can be reduced by determining that the parking surface is empty.

Further, in the present invention, the object area box is moved to the lower end of 1/3 in the image, the number recognition area is set, the number recognition result and the position are stored each time, the number statistics are obtained, and the most common one is obtained. By deciding, the number recognition rate can be increased.

On the other hand, the effects obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned above are clearly described below to those who have ordinary knowledge in the technical field to which the present invention belongs. Will be understood.

FIG. 1 is a block configuration diagram illustrating a parking guidance system applied to the present invention. FIG. 2 is a sequence diagram illustrating a parking guidance method to which motion recognition, object recognition, parking surface setting, number recognition method, and the like proposed by the present invention are applied. as well as Shows an example of vehicle object detection in the present invention. as well as Shows an example of mixed vehicle and human object detection in the present invention. as well as Shows an example of setting a parking surface in the present invention. as well as Shows an example of processing as a shield in the present invention. as well as Shows an example of recognizing a number in the present invention. FIG. 8 is a sequence diagram illustrating the parking guidance method proposed by the present invention.

Parking Guidance System Prior to the specific explanation of the parking guidance system to which the motion recognition, object recognition, parking surface setting, number recognition method, etc. proposed by the present invention are applied, the parking guidance system included in each configuration of the relevant system is described. I will explain basically.

FIG. 1 is a block configuration diagram illustrating a parking guidance system applied to the present invention.

The parking guidance system includes a wireless communication unit 110, an A / V (Audio / Video) input unit 120, a user input unit 130, a sensing unit 140, an output unit 150, a memory 160, an interface unit 170, and the like. A control unit 180 and a power feeding unit 190 are included.

However, the components shown in FIG. 1 are not essential, and a parking guidance system having more or less components can be embodied.

Hereinafter, the above components will be considered.

The wireless communication unit 110 includes one or more modules that enable wireless communication between the parking guidance system and the wireless communication system, or between the parking guidance system and the network in which the parking guidance system is located.

For example, the wireless communication unit 110 includes a broadcast reception module 111, a mobile communication module 112, a wireless Internet module 113, a short-range communication module 114, and a position information module 115.

The broadcast receiving module 111 receives a broadcast signal and / or information related to broadcasting from an external broadcast management server via a broadcast channel.

The broadcasting channel includes a satellite channel and a terrestrial channel. The broadcast management server is a server that generates and transmits information on broadcast signals and / or broadcasts, or a server that is provided with information on broadcast signals and / or broadcasts that have been generated and transmits the information to a parking guidance system. The broadcast signal includes not only a TV broadcast signal, a radio broadcast signal, and a data broadcast signal, but also includes a TV broadcast signal or a broadcast signal in the form in which a data broadcast signal is combined with a radio broadcast signal.

The information regarding broadcasting is information regarding a broadcasting channel, a broadcasting program, or a broadcasting service provider. Information about the broadcast is also provided via the mobile communication network. In such a case, it is received by the mobile communication module 112.

Information about the broadcast exists in various forms. For example, it exists in the form of EPG (Electronic Program Guide) of DMB (Digital Multimedia Broadcasting) or ESG (Electronic Service Guide) of DVB-H (Digital Video Broadcast-Handheld).

The broadcast receiving module 111 includes, for example, DMB-T (Digital Multimedia Broadcasting-Terrestrial), DMB-S (Digital Multimedia Broadcasting-Satellite), MediaFLO (Media Forward Link Only), DVB-H (Digital Video Broadcast-Handheld), and the like. A digital broadcasting signal can be received by using a digital broadcasting system such as ISDB-T (Integrated Services Digital Broadcast-Terrestrial). Of course, the broadcast receiving module 111 is suitable not only for the above-mentioned digital broadcasting system but also for other broadcasting systems.

The broadcast signal and / or information related to the broadcast received via the broadcast reception module 111 is stored in the memory 160.

The mobile communication module 112 transmits and receives radio signals to and from at least one of a base station, an external parking guidance system, and a server on the mobile communication network.

It can contain various forms of data by sending and receiving text / multimedia messages.

The wireless internet module 113 is a module for connecting to the wireless internet, and is installed or externally attached to the parking guidance system. Wireless Internet technologies include WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband (registered trademark)), Wimax (World Interoperability for Microwave Access (registered trademark)), and HSDPA (High Speed Downlink Packet Access). Is available.

The short-range communication module 114 is a module for short-range communication. As short range communication technology, Bluetooth (Bluetooth (registered trademark)), RFID (Radio Frequency Identification), infrared communication (IrDA, infrared Data Association), UWB (Ultra Wideband), ZigBee (registered trademark), Wi-Fi (Wireless Fidelity, Wi-Fi (registered trademark)) and the like can be used.

The position information module 115 is a module for acquiring the position of the parking guidance system, and a typical example thereof is a GPS (Global Position System) module.

Referring to FIG. 1, the A / V (Audio / Video) input unit 120 is for inputting an audio signal or a video signal, and includes a camera 121, a microphone 122, and the like. The camera 121 processes an image frame such as a still image or a moving image obtained by the image sensor in the shooting mode. The processed image frame is displayed on the display unit 151.

The image frame processed by the camera 121 is stored in the memory 160 or transmitted to the outside via the wireless communication unit 110. Two or more cameras 121 are provided depending on the usage environment.

The microphone 122 receives an external acoustic signal by a microphone in a recording mode, a voice recognition mode, or the like, and processes it as electrical voice data. The processed voice data is converted and output in a form that can be transmitted to the mobile communication base station via the mobile communication module 112. Various noise removal algorithms for removing noise generated in the process of inputting an external acoustic signal are embodied in the microphone 122.

The user input unit 130 generates input data for the user to control the operation of the parking guidance system. The user input unit 130 includes a key pad, a dome switch, a touch pad (static pressure / power failure), a jog wheel, and a jog switch.

The sensing unit 140 senses the current state of the parking guidance system, such as the open / closed state of the parking guidance system, the position of the parking guidance system, the presence or absence of contact by the user, the orientation of the parking guidance system, and the acceleration / deceleration of the parking guidance system. To generate a sensing signal that controls the operation of the parking guidance system.

The sensing unit 140 senses whether or not the power feeding unit 190 can supply power, and whether or not the interface unit 170 can be connected to an external parking guidance system.

On the other hand, the sensing unit 140 includes a proximity sensor 141.

The output unit 150 is for generating an output related to visual, auditory, tactile sense, etc., and includes a display unit 151, an acoustic output module 152, an alarm unit 153, a haptic module 154, and a projector module 155.

The display unit 151 displays (outputs) the information processed by the parking guidance system.

The display unit 151 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. Includes at least one of a 3D display.

Of these, some displays are either transparent or translucent so that they can be seen outside. This is called a transparent display, and a typical example of the transparent display is TOLED (Transparent OLED). The rear structure of the display unit 151 can also be a light transmissive structure. With such a structure, the user can see things located behind the parking guidance system body through the area occupied by the display unit 151 of the parking guidance system body.

Depending on the form of the parking guidance system, there are two or more display units 151. For example, in a parking guidance system, a plurality of display units may be separated from each other or arranged integrally on one surface, or may be arranged on different surfaces from each other.

When the display unit 151 and the sensor that detects the touch operation (hereinafter referred to as'touch sensor') form a mutual layer structure (hereinafter referred to as'touch screen'), the display unit 151 is an input device in addition to the output device. It can also be used as. The touch sensor has, for example, a form such as a touch film, a touch sheet, and a touch pad.

The touch sensor is configured to convert a change in pressure applied to a specific part of the display unit 151 or a capacitance generated in a specific part of the display unit 151 into an electrical input signal. The touch sensor is configured to detect not only the touched position and area but also the pressure at the time of touching.

If there is a touch input to the touch sensor, the corresponding signal is sent to the touch controller. After processing the signal, the touch controller transmits the corresponding data to the control unit 180. Therefore, the control unit 180 will know whether or not a certain area of the display unit 151 has been touched.

The proximity sensor 141 is located in the internal area of the parking guidance system covered by the touch screen or in the vicinity of the touch screen. The proximity sensor refers to a sensor that detects the presence or absence of an object that is close to a predetermined detection surface or an object that exists in the vicinity by using the force of an electromagnetic system or infrared rays without mechanically contacting the object. Proximity sensors have a longer life than contact sensors and are highly utilized.

Examples of the proximity sensor include a transmission type photoelectric sensor, a direct reflection type photoelectric sensor, a mirror reflection type photoelectric sensor, a high frequency oscillation type proximity sensor, a capacitance type proximity sensor, a magnetic proximity sensor, and an infrared proximity sensor. When the touch screen is electrostatic, it is configured to detect the proximity of the pointer by the change in the electric field due to the proximity of the pointer. In this case, the touch screen (touch sensor) is classified as a proximity sensor.

In the following, for convenience of explanation, the act of recognizing that the pointer is not touched and is close to the touch screen and that the pointer is located on the touch screen is referred to as “proximity touch”. ) ”, And the act of the pointer actually touching the touch screen is called“ contact touch ”. The position where the pointer is touched close to the pointer on the touch screen means the position where the pointer corresponds perpendicularly to the touch screen when the pointer is touched close to the pointer.

The proximity sensor senses a proximity touch and a proximity touch pattern (eg, proximity touch distance, proximity touch direction, proximity touch speed, proximity touch time, proximity touch position, proximity touch movement state, etc.). Information corresponding to the sensed proximity touch operation and proximity touch pattern is output on the touch screen.

The sound output module 152 outputs audio data received from the wireless communication unit 110 or stored in the memory 160 in a recording mode, a voice recognition mode, a broadcast reception mode, or the like. The acoustic output module 152 outputs an acoustic signal related to a function performed by the parking guidance system. Such an acoustic output module 152 includes a receiver (Receiver), a speaker (speaker), a buzzer (Buzzer), and the like.

The alarm unit 153 outputs a signal for notifying the occurrence of an event in the parking guidance system.

In addition to the video signal and the audio signal, the alarm unit 153 outputs, for example, a signal for notifying the occurrence of an event by vibration.

The video signal and audio signal are also output by the display unit 151 and the audio output module 152, and these display units 151 and the audio output module 152 can be classified as a part of the alarm unit 153.

The haptic module 154 produces various tactile effects that the user can perceive. Vibration is a typical example of the tactile effect generated by the haptic module 154. The strength and pattern of vibration generated by the haptic module 154 can be controlled.

For example, vibrations different from each other can be combined and output, or can be output sequentially.

In addition to vibration, the haptic module 154 has a pin arrangement that moves vertically on the contact skin surface, air injection force and suction input from the injection port and suction port, rubbing against the skin surface, electrode contact, electrostatic force, etc. Various tactile effects can be generated, such as the effect of the stimulus and the effect of reproducing the feeling of cold and warm using an element capable of absorbing heat and generating heat.

The haptic module 154 can not only transmit the tactile effect by direct contact, but can also be embodied so that the user can feel the tactile effect through muscular sensations such as fingers and arms. Two or more haptic modules 154 are provided depending on the configuration of the portable parking guidance system.

The projector module 155 is a component for performing the function of the image project (project) by using the parking guidance system, and is the same as the image displayed on the display unit 151 by the control signal of the control unit 180. Or, at least a partially different image can be displayed on an external screen or wall.

Specifically, the projector module 155 uses a light source (not shown) that generates light (for example, laser light) for outputting an image to the outside, and light generated by the light source to output an image to the outside. It includes an image generation means for generating (not shown) and a lens (not shown) for magnifying and outputting an image to the outside at a constant focal length. Further, the projector module 155 can include a device (not shown) for adjusting the image projection direction by mechanically moving the lens or the entire module.

The projector module 155 is classified into a CRT (Cathode Ray Tube) module, an LCD (Liquid Crystal Display) module, a DLP (Digital Light Processing) module, and the like, depending on the type of element of the display means. In particular, the DLP module is a method of magnifying and projecting an image generated by reflecting light generated from a light source on a DMD (Digital Micromirror Device) chip, which is advantageous for miniaturization of the projector module 151.

Desirably, the projector module 155 is provided lengthwise on the side, front, or back of the parking guidance system. Needless to say, the projector module 155 is also provided at a certain position of the parking guidance system, if necessary.

The memory 160 stores a program for processing and control of the control unit 180, and also performs a function for temporarily storing data to be input / output (for example, a message, audio, still image, moving image, etc.). The memory 160 also stores the frequency of use for each of the data. Further, the memory 160 can store various patterns of vibration and acoustic data output at the time of touch input on the touch screen.

The memory 160 includes a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), and a ram (Random). Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), Magnetic Memory, Magnetic Disk, Includes at least one type of storage medium for the optical disk. The parking guidance system can also operate on the Internet with respect to the web storage that performs the storage function of the memory 160.

The interface unit 170 serves as a passage to all external parking guidance systems connected to the parking guidance system. The interface unit 170 either transmits data from an external parking guidance system, is powered and transmits to each component in the parking guidance system, or data inside the parking guidance system is sent to the external parking guidance system. Be transmitted. For example, a wireless headset port, an external charger port, a wireless data port, a memory card port, a port for connecting devices equipped with an identification module, an audio I / O (Input / Output) port, and video. The interface unit 170 includes an I / O (Input / Output) port, an earphone port, and the like.

The identification module is a chip that stores various information for authenticating the usage authority of the parking guidance system, and is a user authentication module (User Identify Module, UIM), a subscriber authentication module (Subscriber Identify Module, SIM), and a general-purpose. Includes User Authentication Module (Universal Subscriber Identity Module, USIM) and others. A device provided with an identification module (hereinafter,'identification device') is manufactured in the form of a smart card. Therefore, the identification device can be connected to the parking guidance system via the port.

The interface unit serves as a passage through which power from the cradle is supplied to the mobile parking guidance system when the mobile parking guidance system is connected to an external cradle, or is input from the cradle by the user. Various command signals can be a passage transmitted to the mobile parking guidance system. Various command signals input from the cradle or the power supply are operated as signals for recognizing that the mobile parking guidance system is correctly mounted on the cradle.

The control unit 180 usually controls the overall operation of the parking guidance system.

The control unit 180 includes a multimedia module 200 for multimedia reproduction. The multimedia module 200 is embodied in the control unit 180 or separately from the control unit 180.

The control unit 180 can perform pattern recognition processing for recognizing handwriting input or drawing input performed on the touch screen as characters and images, respectively.

The power feeding unit 190 is controlled by the control unit 180 to apply an external power supply and an internal power supply to supply power necessary for the operation of each component.

The various embodiments described herein can be embodied in a recording medium readable by a computer or similar device, using, for example, software, hardware, or a combination thereof.

According to the hardware implementation, the examples described here are ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (fields). It can be embodied using programmable gate arrays, processors, controllers, microcontrollers, microprocessors, and at least one of the electrical units for performing other functions. In some cases, the embodiments described herein are embodied in the control unit 180 itself.

It can be realized as a software module. Each of the software modules can perform one or more functions and operations described herein. Software code is embodied in software applications written as appropriate programming languages. The software code is stored in the memory 160 and can be executed by the control unit 180.

Parking Guidance Method Based on the configuration of the present invention described above, the parking guidance method will be specifically described with reference to FIG.

FIG. 2 is a sequence diagram illustrating a parking guidance method to which motion recognition, object recognition, parking surface setting, number recognition method, and the like proposed by the present invention are applied.

Referring to FIG. 2, first, the step (S10) in which the control unit 180 detects the motion is performed. At this time, the motion detection (Motion Detection) is processed separately for the case where there is movement and the case where there is no movement.

That is, the motion with the previous image is determined from the image acquired by the camera 121, and the control unit 180 attempts to recognize the object only when there is a motion (S20).

On the other hand, when there is no movement, an object recognition is attempted by applying a certain cycle. For example, when there is no movement, it is determined once every 20 seconds whether or not motion is possible (S30).

At this time, if the motion is recognized within 20 seconds, the control unit 180 tries to recognize the object (S20), and if there is no motion to be recognized for 20 seconds or more, the control unit 180 after 20 seconds have elapsed. Object recognition will be attempted (S20).

However, here, the period of 20 seconds is merely an example to which the present invention is applied, and it is self-evident that a wider variety of periods can be applied.

In the object recognition step (S20), objects such as automobiles (passenger cars, SUVs, vans, trucks, etc.), buses, humans, motorcycles, bicycles, etc. are recognized.

Here, the control unit 180 can detect an object having a certain size or more on the screen, specify the detection position as a square shape, and determine the type.

3a and 3b show an example of vehicle object detection in the present invention.

With reference to FIGS. 3a and 3b, an example is shown in which the detection position of a vehicle, which is an object of a certain size or larger, is identified and recognized as a square shape on the screen.

Further, FIGS. 4a and 4b show an example of object detection in which a vehicle and a human are mixed in the present invention.

With reference to FIGS. 4a and 4b, an example is shown in which the detection positions of a vehicle and a plurality of human beings, which are objects of a certain size or larger, are identified and recognized as a quadrangle on the screen.

After step S20, a step (S40) of determining whether the control unit 18 has succeeded in object recognition is performed.

If the object recognition fails, steps S10 to S30 are repeated.

When the object recognition is successful, the control unit 180 compares the relationship with the set parking surface (S50) and determines whether or not an area overlapping the parking surface has occurred (S60).

If the area overlapping the parking surface does not occur, steps S10 to S30 are performed again, and if it does occur, the type of the object whether it is a vehicle or a human is determined (S70), and if it is a human, it is determined. The existing parking surface condition is maintained (S90).

If it is a vehicle, it is determined whether or not the object includes the front outside the parking surface area (S80), and if it is included, the existing parking surface state is maintained (S90), and if it is not included, it is not included. It will be determined whether or not the parking surface area occupies a certain area or more (S100).

5a and 5b show an example of setting a parking surface with respect to the present invention.

Referring to FIGS. 5a and 5b, if it is determined in step S100 that the vehicle occupies a certain area or more, the control unit 180 performs a vehicle entry process (S110).

Further, in step S100, if the vehicle does not occupy more than a certain area, the vehicle leaves (empty vehicle) is processed (S130).

Further, data such as images in steps S110, S120, and S130 can be stored in a database.

With respect to steps S50 to S130, when the detected object is identified in front of a certain amount of the parking scene, a portion overlapping the parking surface can be searched for and processed as a shield.

Further, it is also possible to obtain the ratio of overlapping the parking surface in each of the automobiles and buses that do not correspond to the shielding, and if the ratio exceeds a certain value, it is possible to determine that the parking surface vehicle exists.

6a and 6b show an example of the present invention being treated as a shield.

With reference to FIGS. 6a and 6b, if the overlapping ratio in this embodiment occupies two of the parking surfaces, it can be determined that the two surfaces are occupied at the same time.

Further, if there is a human being among the objects overlapping with the parking surface, it can be determined as a shield and the full / empty state of the parking surface can be maintained in the previous state.

In addition, if there is no automobile / bus object whose overlapping ratio on the parking surface is larger than a certain level, it is determined that the parking surface is empty if it does not correspond to shielding.

On the other hand, after step S110, the operation of recognizing the vehicle number is performed (S120).

In step S120, when the parking surface is determined to be occupied, the control unit 180 performs number recognition in the corresponding object area, but moves the object area box to the lower end of 1/3 in the image to move the number recognition area. Set.

This is applied to improve the recognition rate because the license plate is located at the lower end.

Further, the control unit 180 stores the number recognition result and the position each time, obtains the statistics of the numbers, and applies a method of determining that the number is the largest.

Further, the control unit 180 obtains a related value between the previously recognized position of the license plate and the current image, and if the related value is high, skips the number recognition to improve the overall processing speed. Can be done.

At this time, if skipping is repeated for a certain period of time, it is ignored and number recognition is performed.

In this regard, FIGS. 7a and 7b show an example of number recognition in the present invention.

On the other hand, there may be vehicles with unmatched numbers, and there is a need to search for such unmatched vehicles.

That is, an event that is unrecognized or misrecognized at the time of departure can be corrected by the operator, or an event that is misrecognized at the time of entry must be inspected for all vehicles.

In addition, there is a problem that it is not possible to find the corresponding vehicle due to misrecognition of entering the vehicle at the time of payment for departure, and it is necessary to search for an image similar to that of leaving the vehicle while entering the vehicle.

Therefore, in the present invention, among the unrecognized or recognized vehicles whose number recognition result is unrecognized while entering the vehicle, a vehicle similar to the 3-digit number is set as a candidate group, and based on the candidate group, hue, maker logo, and SURF matching are three. After determining the ranking by type and displaying it, the corresponding problem can be solved by the method selected by the worker.

Parking Guidance Method According to the Present Invention FIG. 8 is a sequence diagram illustrating a parking guidance method proposed by the present invention with respect to the present invention.

The parking guidance method proposed by the present invention according to FIG. 8 is performed based on the system 100 described above and the terminal used by the user.

Referring to FIG. 8, first, a step (S210) of periodically checking an empty parking area and an occupied parking area is performed by using the fixed camera 121.

At this time, a parking surface number sign is placed in front of each parking surface (S220), and after the driver parks, upload a photo using the application so that the corresponding parking surface number and parked vehicle number are displayed. Step (S230) is performed.

After that, the application transfers the current location information to the server together, determines the parking lot position (S240), acquires the parking surface number and the vehicle number from the uploaded photo, and stores them in the parking start DB. Step (S250) is performed.

Further, when the departure is selected from the application after step S250, the parking fee is processed by the pre-registered payment method (S260), and if there is no pre-registered payment method, the parking lot is installed. The step (S270) of inputting the parking lot number with the unmanned checkout machine and settling the parking fee is performed.

If the vehicle is entered but not registered within a certain period of time, the step to automatically notify the administrator (S280), and if the vehicle leaves without payment, the administrator is automatically notified. Step (S290) is applied.

Effect of the present invention The present invention relates to a parking guidance system to which an efficient object recognition and number recognition method is applied, and specifically provides a parking guidance system to which motion recognition, object recognition, parking surface setting, number recognition method, etc. are applied. , Can be provided to the user.

In the present invention, regarding motion recognition, the movement with the previous image is determined from the camera image, and the operation is performed only when there is movement, and even when there is no movement, the processing operation is performed at a constant cycle, and the object recognition is performed. , The accuracy can be improved by detecting an object of a certain size or more on the screen, specifying the detection position as a quadrangle, and then determining the type.

Further, in the present invention, regarding the surface setting in the parking lot, when the detected object is determined to be an object in front of a certain amount of the parking scene, a portion overlapping with the corresponding parking surface is searched for and treated as a shield, and the automobile is treated. , If the ratio of overlapping with each parking surface in the bus exceeds a certain value, it is treated as occupied by that parking surface, and there is no car / bus object with a ratio of overlapping with the corresponding parking surface larger than a certain value, and it is shielded. If this is not the case, the error can be reduced by determining it as an empty parking surface.

Further, in the present invention, the object area box is moved to the lower end of 1/3 in the image, the number recognition area is set, the number recognition result and the position are stored each time, and the number statistics are obtained, which is the most common. By determining, the number recognition rate can be increased.

The above-described embodiment of the present invention can be embodied by various means. For example, the embodiments of the present invention are embodied by hardware, firmware, software, or a combination thereof.

In the case of hardware implementation, the method according to the embodiment of the present invention is one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices). , FPGAs (Field Programmable Gate Arrays), processors, controllers, microprocessors, microprocessors, etc.

In the case of realization by firmware or software, the method according to the embodiment of the present invention is embodied in the form of a module, procedure or function performing the function or operation described above. The software code is stored in a memory unit and driven by a processor. The memory unit may be located inside or outside the processor and may exchange data with the processor by means already known.

Detailed descriptions of preferred embodiments of the invention disclosed as described above are provided so that those skilled in the art can embody and practice the invention. Although the above description has been made with reference to preferred embodiments of the present invention, it is understood that skilled skill in the art can modify and modify the present invention in various ways without departing from the realm of the present invention. Will be done. For example, one of ordinary skill in the art can use a method in which the configurations described in the above-described embodiments are combined with each other. Accordingly, the present invention is not limited to the embodiments presented herein, but seeks to provide the broadest scope consistent with the principles and novel features disclosed herein.

The present invention can be embodied in other particular embodiments without departing from the spirit and essential features of the invention. Therefore, the above detailed description should not be analyzed in a restrictive manner in all aspects and should be considered as an example. The scope of the invention should be determined by reasonable analysis of the appended claims, and all modifications within the equivalent scope of the invention are within the scope of the invention. The present invention is not limited to the embodiments presented herein, but seeks to provide the broadest scope consistent with the principles and novel features disclosed herein. In addition, claims that do not have an explicit citation relationship within the scope of claims can be combined to form an example, or can be included as a new claim by amendment after filing.

Claims (8)

The first step when the camera inputs at least one image,
The second step of determining whether or not motion is detected in at least one image, and
When the motion is sensed, a third step of attempting to recognize an object in at least one image, and
When the object recognition is successful, a fourth step of determining whether an area where the recognized object overlaps with a first parking surface which is at least a part of a predetermined plurality of parking surfaces is generated.
When the overlapping area occurs, the fifth step of determining whether the recognized object is a vehicle or a human, and
When the recognized object is a vehicle, the 5-1 step of determining whether or not the object includes the front outside the first parking surface area, and
In the step 5-1 when it is determined that the object does not include the front outside the first parking surface area, the vehicle has a predetermined ratio or more in the entire area of the first parking surface. The sixth step of determining whether or not to occupy the area of
A seventh step of determining that the vehicle has parked on the first parking surface when the vehicle occupies an area equal to or greater than the predetermined ratio.
Including the eighth step of recognizing the vehicle number of the vehicle.
The front outside the first parking surface area is an area between the first parking surface and the camera.
In the fifth step, an object having a certain size or larger is determined to be a vehicle on the screen based on the image of the camera, and the object is determined to be a vehicle.
If it is determined in step 5-1 that the object includes the front outside the first parking surface area, the existing parking surface state is maintained .
The parking guidance method , wherein the existing parking surface state is shielded by the object or an empty parking surface . If the motion is not detected for a predetermined time or longer in the second step, the third step is performed.
The third step further sets a third step of determining whether an object having a predetermined size or larger exists in the video, and an object box separated by a certain distance based on the object. Including step 3-2,
When the recognized object is a human being in the fifth step, the subsequent step of the fifth step further includes a step of maintaining the existing state of the first parking surface as it is.
In the sixth step, if the vehicle does not occupy an area equal to or larger than the predetermined ratio, it is determined that the first parking surface has left the vehicle.
The eighth step is further
The eighth step of setting the predetermined lower end area of the entire area of the object box as the number recognition area, and
The parking guidance method according to claim 1, further comprising a step 8-2 for performing a number recognition operation with respect to the number recognition area. With a camera that inputs at least one image,
When motion is detected in the at least one image, the control unit that attempts to recognize an object in the at least one image is included.
The control unit
When the object recognition is successful, it is determined whether or not an area where the recognized object overlaps with a first parking surface which is at least a part of a predetermined plurality of parking surfaces is generated.
When the overlapping area occurs, it is determined whether the recognized object is a vehicle or a human being.
When the recognized object is a vehicle, it is determined whether or not the object includes the front outside the first parking surface area.
When it is determined that the object does not include the front outside the first parking surface area, it is determined whether or not the vehicle occupies a predetermined ratio or more of the entire area of the first parking surface. death,
When the vehicle occupies an area equal to or larger than the predetermined ratio, it is determined that the vehicle is parked on the first parking surface.
Recognize the vehicle number of the vehicle and
An object of a certain size or larger is judged to be a vehicle on the screen based on the image of the camera.
If it is determined that the object includes the front outside the first parking surface area, the existing parking surface state is maintained .
The front outside the first parking surface area is an area between the first parking surface and the camera.
The parking guidance system , wherein the existing parking surface state is a shield by the object or an empty parking surface . The control unit
Judging whether there is an object of a predetermined size or larger in the video,
Set an object box separated by a certain distance based on the above object,
The parking guidance system according to claim 3, wherein it is determined whether the object existing in the object box is a vehicle or a human being. If the recognized object is a human
The control unit
The parking guidance system according to claim 3, wherein the existing state of the first parking surface is maintained as it is. The output unit includes an output unit that generates an output related to visual, auditory, or tactile sensation, and the output unit includes a display unit that displays information processed by the parking guidance system and an acoustic signal related to a function performed by the parking guidance system. The parking guidance system according to claim 3, further comprising an acoustic output module for output, an alarm unit for notifying the occurrence of an event in the parking guidance system, a haptic module, and a projector module. The parking guidance system according to claim 6, wherein the haptic module generates various tactile effects felt by the user of the parking guidance system. The projector module is characterized in that an image that is the same as or at least partially different from the image displayed on the display unit can be displayed on an external screen or a wall by a control signal of the control unit. The parking guidance system according to claim 6 or 7.

Images