KR102597023B1 - Floor signal lamp system for child protection and its operation - Google Patents

Abstract

A floor traffic light system for child protection according to an embodiment of the present invention includes an object detection device that detects the movement and approach of vehicles and pedestrians within the child protection zone; An object photographing device that is activated by an object detection signal from the object detection unit and photographs objects (vehicles and people) entering the child protection zone; An object analysis device that identifies an object as a person or an object from an object image and, if it is a person, classifies the object as an adult or child through facial analysis of the object; And it is installed on the floor of the child protection zone, and is linked with vehicle traffic lights and pedestrian traffic lights, so that when a vehicle traffic signal is applied, a child protection zone video and a speeding prevention video are output, and when a pedestrian signal is applied, a crosswalk mark character is displayed. Includes a floor traffic light device that outputs images.

Description

Floor traffic light system for child protection and its operation method {FLOOR SIGNAL LAMP SYSTEM FOR CHILD PROTECTION AND ITS OPERATION}

The present invention relates to a floor traffic light system for child protection and a method of operating the same.

In general, a crosswalk is a path provided on a roadway so that people can cross horizontally. In addition to general roadways, crosswalks are also provided at apartment parking lot entrances and government office parking lot entrances. In particular, in order to protect children who are distracted and have a wide range of activities, a school zone is designated in a certain radius around the school, and a crosswalk is located within the school zone (child protection zone) to prevent adults from crossing when vehicles pass by. Special care is required to protect children with poor judgment skills.

Therefore, through an alarm installed separately from the traffic lights installed on each side of the crosswalk and linked to the traffic controller, a notification signal is generated in addition to the blue light signal of the traffic light to draw children's attention, or parents or teachers can directly alert children to the crosswalk. It is located across from each other and provides transportation guidance for children going to and from school.

These warning signals and passive traffic guidance methods cannot monitor or control all activities of children in real time, so there is a risk of unexpected accidents occurring at separate times when monitoring is not performed.

In addition, although drivers need to be more careful in child protection zones, traffic accidents frequently occur every year at crosswalks in child protection zones as most people inadvertently violate the speed limit or vehicle signals when crossing the crosswalk formed within the child protection zone. A problem followed.

Patent Publication No. 10-2015-0064398

The purpose of the present invention is to provide a floor traffic light system and a method of operating the same for child protection that can solve the problems of the prior art.

A floor traffic light system for child protection according to an embodiment of the present invention to solve the above problem includes a plurality of object detection devices that detect the movement and approach of vehicles and pedestrians to a crosswalk in a child protection zone; A plurality of object photographing devices activated by an object detection signal from the object sensing device to photograph objects (vehicles and people) entering a child protection zone; An object analysis device that identifies an object as a person or an object from an object image and, if it is a person, classifies the object as an adult or child through facial analysis of the object; And it is installed on the floor of the child protection zone, and is linked with vehicle traffic lights and pedestrian traffic lights, so that when a vehicle traffic signal is applied, a child protection zone video and a speeding prevention video are output, and when a pedestrian signal is applied, a crosswalk mark character is displayed. It includes a floor traffic light device that outputs an image, and the object analysis device uses a deep learning algorithm to determine the location coordinates (x, y) and size (a, h: height and width) of the object (bounding box) in the object image. Detect, analyze objects into objects, people, adults, and children based on the detected information, create an integrated object detection area by merging and expanding the object detection areas of two different deep learning object analysis algorithms, and then create an integrated object detection area. A human body (human) object located in the integrated object detection area is detected according to the set detection condition value, and when a pedestrian signal is received from the traffic signal controller, the floor traffic light device projects an image suitable for the characteristics of the pedestrian to the crosswalk area. Pedestrian floor traffic lights; A vehicle that is installed on the road in the direction opposite to the vehicle's driving direction so that it is in the driver's frontal view, and indicates at least one of the following: proceed, stop, or detour through red, green, yellow, and green arrow indicators. floor traffic lights; and a control unit that receives one of a vehicle traffic signal and a pedestrian signal from a traffic signal controller installed in an adjacent area of the crosswalk, and controls the pedestrian floor signal light or the vehicle floor signal light to be activated according to the input signal, wherein the pedestrian In the case of children, the video is characterized as a character or animation.

In one embodiment, it further includes a sound device that outputs sound corresponding to the image output from the floor traffic light device.

delete

delete

delete

delete

In one embodiment, the object analysis device can calculate the speed, which is a characteristic of a moving object (vehicle) in the object image, and the speed according to the change in the position coordinates of the object (image bounding box) detected for each image frame. It is characterized by calculating .

In one embodiment, the object analysis device is characterized in that it identifies and analyzes the license plate of a moving object (vehicle) in the object image.

delete

delete

In one embodiment, when the speed of the object analyzed by the object analysis device exceeds the speed that complies with the child protection zone, the control unit activates the pedestrian floor signal light to output the license plate number and speed of the speeding vehicle. It is characterized in that it controls the pedestrian floor traffic light.

In one embodiment, the pedestrian floor traffic light may further include a pressure sensor, and when a pedestrian signal is received, display a spot at the pressure point or output a primary color series at the pressure point. It is characterized by

In one embodiment, the pedestrian floor traffic light irradiates a preset light to the head of the object (child) analyzed by the object analysis device at night, and illuminates the head of the object (child) to surrounding vehicles while the object (child) is crossing the crosswalk. It is characterized by emitting light so that the location of the child can be identified.

A method of operating a floor traffic light system for child protection according to an embodiment of the present invention to solve the above problem includes the steps of detecting at least one moving object passing or approaching a child protection zone (crosswalk); Photographing an area where the moving object is detected and analyzing the moving object based on the shape or characteristics of at least one moving object; And when a walking signal is input from an external device, it includes the step of transmitting a pedestrian protection image according to object characteristics to the crosswalk area, and the step of analyzing the moving object is to determine the object (bounding box) in the object image using a deep learning algorithm. ) detects the location coordinates (x, y) and size (a, h: height and width), analyzes moving objects as objects, people, adults, and children based on the detected information, and uses two different deep learning methods. After merging and expanding the object detection areas of the object analysis algorithm to create an integrated object detection area, human body (human) objects located in the integrated object detection area are detected according to preset detection condition values, and the pedestrian protection image is captured. The step of transmitting to the crosswalk area includes, when a pedestrian signal is received from the traffic signal controller, outputting an image suitable for the characteristics of the pedestrian from the pedestrian floor signal light that illuminates the crosswalk area, and if the pedestrian is a child, The video is characterized as a character or animation.

delete

delete

delete

delete

In one embodiment, the step of analyzing the moving object may calculate the speed, which is a characteristic of the moving object (vehicle) in the object image, and the change in position coordinates of the object (image bounding box) detected for each image frame. It is characterized in that it further includes the step of calculating the speed according to.

In one embodiment, the step of analyzing the moving object includes identifying and analyzing a license plate of the moving object (vehicle) in the object image.

delete

delete

In one embodiment, when a vehicle signal is received from a traffic signal controller, the vehicle floor signal light is installed on the road in a direction opposite to the direction of vehicle travel so as to be in the driver's frontal view, and red, green, yellow, and green arrow points are displayed. /It further includes a step of instructing the driving vehicle to proceed, stop, or detour by turning off the lights.

In one embodiment, when the speed of the object analyzed by the object analysis device exceeds the speed that complies with the child protection zone, the control unit activates the pedestrian floor signal light to output the license plate number and speed of the speeding vehicle. It further includes controlling a floor traffic light.

Therefore, the floor traffic light system for child protection disclosed in the present invention is installed in a child protection zone (School Zone), detects the approach of children or entry into vehicles, and simultaneously recognizes cautions and warnings to vehicle drivers and pedestrians (children). Additionally, the pedestrian's age can be estimated from the pedestrian's walking video, and if the pedestrian is a child, auditory and visual caution information such as sound and video is output to prevent physical signal violations by surrounding vehicles from occurring in advance. , it has the advantage of helping children move safely.

Figure 1 is a configuration diagram of a floor traffic light system for child protection according to an embodiment of the present invention.
FIG. 2 is an exemplary diagram showing the connection relationship of the components shown in FIG. 1.
Figures 3 and 4 are examples of images output from the floor traffic light device.
Figure 5 is a flowchart explaining a method of operating a floor signal light for child protection according to an embodiment of the present invention.
Figure 6 is a diagram illustrating an example computing environment in which one or more embodiments disclosed herein may be implemented.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server. In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, based on the attached drawings, a floor traffic light system for child protection and an operating method thereof according to an embodiment of the present invention will be described in more detail.

Figure 1 is a configuration diagram of a floor traffic light system for child protection according to an embodiment of the present invention, Figure 2 is an exemplary diagram showing the connection relationship of the components shown in Figure 1, and Figures 3 and 4 are floor traffic light devices. This is an example of an image output from. As shown in Figure 1, it is a network configuration diagram of a floor traffic light system for child protection according to an embodiment of the present invention.

First, as shown in FIG. 1, the floor traffic light system 100 for child protection according to an embodiment of the present invention is installed in a child protection zone (School Zone) to detect the approach of a child or entry of a vehicle, This is an invention that aims to simultaneously recognize cautions and warnings to vehicle drivers and pedestrians (children) through a reinforced screen unit.

In addition, this invention is intended to estimate the age of a pedestrian from a walking image of the pedestrian and, if the pedestrian is a child, output auditory and visual caution information such as sound and video to prevent physical signal violations by surrounding vehicles from occurring in advance.

In addition, the invention aims to output auditory and visual information that can stimulate interest and alert children to relieve anxiety about traffic lights when walking.

More specifically, the floor traffic light system 100 for child protection may include a plurality of object detection devices 110, an object photography device 120, an object analysis device 130, and a floor traffic light device 140. .

A plurality of object detection devices 110 are provided at least one in the periphery of the screen floor traffic light device 140, which will be described later, and the movement and/or approach situation of vehicles and pedestrians passing through the screen floor traffic light device located in the child protection zone. It may be a configuration that detects .

The plurality of object detection devices 110a to 110d may be configured to detect the presence or absence of objects entering different designated areas.

Among the plurality of object detection devices (110a ~ 110f), 110a ~ 110d are located in pairs on the road and are configured to detect the location of an object about to enter the roadway, and 110e is an object about to enter the floor traffic light device from the first direction ( vehicle), and 110f may be configured to detect an object (vehicle) attempting to enter the screen floor traffic light device from the second direction.

Here, among the plurality of object detection devices, 110e and 110f may be configured to be activated when a vehicle passing signal input to a vehicle traffic light is applied. In addition, 110e and 110f may further include a speed detection sensor to detect the speed of an object (vehicle) passing through the screen bottom traffic light device 140. The speed information detected later is applied to the screen floor traffic light device 140, which will be described later, and when the speed information exceeds the speed limit 30 of the child protection zone, the floor traffic light device 140 displays the corresponding speed value on the road. Display.

Next, the plurality of object photographing devices 120 may be configured to photograph the surrounding area of the floor traffic light device 140, for example, the roadway, sidewalk, and the entire area of the reinforced screen of the screen floor traffic light device.

Among the plurality of object photographing devices 120, the first object photographing device 121 is configured to photograph objects (vehicles) moving in the first and second directions on the road, and the second object photographing device 122 is configured to photograph objects (vehicles) moving in the first and second directions on the road. It may be configured to photograph an object (pedestrian) entering the area.

Next, the object analysis device 130 may be configured to first classify objects into objects and people by analyzing object characteristics in the object image, and secondarily analyze the first classified people into adults and children.

The object analysis device 130 detects the location coordinates (x, y) and size (a, h: height and width) of the object (bounding box) in the object image using a deep learning algorithm, and based on the detected information It analyzes objects into objects, people, adults, and children.

Meanwhile, the object analysis device 130 creates an integrated object detection area by merging and expanding the object detection areas of two different deep learning object analysis algorithms, and then creates an integrated object detection area according to a preset detection condition value. It is possible to detect a positioned human body (human) object.

The two different deep learning object detection algorithms may be a first deep learning object detection algorithm (Gaussian YOLO v3) and a second deep learning object detection algorithm (MASK R-CNN), and each object detection area (bounding box) It may be configured to create the integrated object detection area by overlapping and exceeding a preset overlap value, preferably 70%.

For reference, the first deep learning object detection algorithm (Gaussian YOLO v3) has a fast object detection speed but low recognition accuracy, and the second deep learning object detection algorithm (MASK R-CNN) has a slow object detection speed but recognition accuracy. It has the characteristic of high accuracy.

Accordingly, in the present invention, the detection bounding boxes of the two deep learning object detection algorithms are integrated and expanded to create and use an integrated object detection area so that the advantages of the two deep learning object detection algorithms can be derived.

Meanwhile, the object analysis device 122 detects the object (bounding box) using the second deep learning object detection algorithm (MASK R-CNN) when the overlapped integrated object detection area is smaller than the preset overlap value (60%). can do.

Meanwhile, the object analysis device 130 can calculate the characteristics of a moving object (vehicle) in an object image, for example, speed, and the speed according to the change in the position coordinates of the object (image bounding box) detected for each image frame. can be calculated.

Additionally, the object analysis device 130 can identify the license plate of a moving object (vehicle) in an image, and recognizing a vehicle license plate can be implemented in various ways.

If a square that meets the allowable specifications for a vehicle license plate is detected on a captured image, it is possible to recognize it as a license plate. It is also possible to detect a license plate by recognizing the color of the background and numbers, or to recognize a vehicle license plate using technology that recognizes the actual vehicle number. possible. Technology for detecting vehicle license plates is interpreted to encompass various variations, and of course machine learning or deep learning may be used.

Next, the sound output device may be configured to output sounds according to walking signals and vehicle passing signals, and sound information according to the characteristics of objects crossing the crosswalk.

For example, when the vehicle signal is activated, sound information related to safe driving is output, and when the walking signal is activated, when children are included among the moving objects, children's songs or songs related to the video displayed as a crosswalk, etc. It may be a configuration that outputs .

Next, the floor traffic light device 140 outputs the image necessary for pedestrian protection to the road (crosswalk) according to the pedestrian signal provided by the traffic signal controller on the road (crosswalk) in the child protection area, and drives the vehicle according to the vehicle signal. It may be configured to irradiate light in the direction of the driver's viewing angle.

More specifically, the floor traffic light device 140 includes a pedestrian floor traffic light 141, a vehicle floor traffic light 142, and a control unit 143.

The pedestrian floor signal light 141 may be an image output device for projecting an image suitable for the characteristics of the pedestrian described above to the crosswalk area when a pedestrian signal is received from the traffic signal controller.

As another example, the pedestrian floor traffic light 141 may be a reinforced screen unit that replaces a crosswalk, and may be configured to display an image suited to the characteristics of the pedestrian described above when a pedestrian signal is received from a traffic signal controller.

For example, if the pedestrian is a child, it may be configured to output characters, animation, etc.

Additionally, the pedestrian floor signal light 141 may include an illumination sensor and may vary the amount of light output depending on daytime and nighttime.

In addition, the pedestrian floor signal light 141 may further include a pressure sensor, and when a pedestrian signal is received, the pedestrian floor signal light 141 displays a spot at the pressurized point or displays a primary color series at the pressurized point. By outputting the colors, it can help to identify the location of pedestrians more clearly.

In addition, the pedestrian floor traffic light 141 irradiates a preset light to the head of the object (child) analyzed by the object analysis device 130 at night to illuminate the surrounding area while the object (child) is crossing the crosswalk. Light can be emitted to enable vehicles to identify the child's location.

Next, the vehicle floor signal light 142 is installed on the road in a direction opposite to the vehicle driving direction so as to be in the front view of the driver, and the vehicle progresses with red, green, yellow, and green arrow lights on/off, It may be a device that performs the function of instructing stop, detour, etc.

The control unit 143 receives either a vehicle traffic signal or a pedestrian signal from a traffic signal controller installed in an adjacent area of the crosswalk, and activates the pedestrian floor signal light 141 or the vehicle floor signal light 142 according to the input signal. It may be a configuration that is controlled as much as possible.

Meanwhile, in a dangerous situation, for example, when the speed of the object analyzed by the object analysis unit exceeds the speed that complies with the child protection zone, the control unit 143 activates the pedestrian traffic light 141 to display the license plate number and license plate number of the speeding vehicle. Pedestrian floor traffic lights can be controlled to output speeding speeds.

Figure 5 is a flowchart explaining the operation method of a floor traffic light system for child protection according to an embodiment of the present invention.

Referring to Figure 5, the operating method (S700) of the floor traffic light system for child protection according to an embodiment of the present invention first detects at least one moving object passing and approaching the child protection zone (crosswalk) ( S710).

The S710 process may further include detecting the speed of the moving object.

When the S710 process is completed, the area where the moving object was detected is photographed and features are analyzed and classified through the shape of at least one moving object (S720).

The S720 process is performed in the object analysis device 130 and includes the process of analyzing object characteristics in the object image to first classify objects into objects and people, and secondly analyzing the first classified people into adults and children. do.

The object analysis device 130 detects the location coordinates (x, y) and size (a, h: height and width) of the object (bounding box) in the object image using a deep learning algorithm, and based on the detected information It analyzes objects into objects, people, adults, and children.

Meanwhile, the object analysis unit 130 creates an integrated object detection area by merging and expanding the object detection areas of two different deep learning object analysis algorithms, and then creates an integrated object detection area according to a preset detection condition value. It is possible to detect a positioned human body (human) object.

The two different deep learning object detection algorithms may be a first deep learning object detection algorithm (Gaussian YOLO v3) and a second deep learning object detection algorithm (MASK R-CNN), and each object detection area (bounding box) It may be configured to create the integrated object detection area by overlapping and exceeding a preset overlap value, preferably 70%.

For reference, the first deep learning object detection algorithm (Gaussian YOLO v3) has a fast object detection speed but low recognition accuracy, and the second deep learning object detection algorithm (MASK R-CNN) has a slow object detection speed but recognition accuracy. It has the characteristic of high accuracy.

Accordingly, in the present invention, the detection bounding boxes of the two deep learning object detection algorithms are integrated and expanded to create and use an integrated object detection area so that the advantages of the two deep learning object detection algorithms can be derived.

Meanwhile, the object analysis device 130 detects the object (bounding box) using the second deep learning object detection algorithm (MASK R-CNN) when the overlapped integrated object detection area is smaller than the preset overlap value (60%). can do.

Meanwhile, the object analysis device 130 can calculate the characteristics of a moving object (vehicle) in an object image, for example, speed, and the speed according to the change in the position coordinates of the object (image bounding box) detected for each image frame. can be calculated.

Additionally, the object analysis device 130 can identify the license plate of a moving object (vehicle) in an image, and recognizing a vehicle license plate can be implemented in various ways.

If a square that meets the allowable specifications for a vehicle license plate is detected on a captured image, it is possible to recognize it as a license plate. It is also possible to detect a license plate by recognizing the color of the background and numbers, or to recognize a vehicle license plate using technology that recognizes the actual vehicle number. possible. Technology for detecting vehicle license plates is interpreted to encompass various variations, and of course machine learning or deep learning may be used.

When the S720 process is completed, when a walking signal is input from an external device, for example, a traffic signal controller, a pedestrian protection image according to the classified object characteristics is transmitted to the crosswalk area (S730).

The S730 process is performed by the floor traffic light device 150, which includes a pedestrian floor traffic light 151, a vehicle floor traffic light 152, and a control unit 153.

The pedestrian floor signal light 151 may be an image output device for projecting an image suitable for the characteristics of the pedestrian described above to the crosswalk area when a pedestrian signal is received from the traffic signal controller.

As another example, the pedestrian floor traffic light 151 may be a reinforced screen unit that replaces a crosswalk, and may be configured to display an image suited to the characteristics of the pedestrian described above when a pedestrian signal is received from a traffic signal controller.

For example, if the pedestrian is a child, it may be configured to output characters, animation, etc.

Additionally, the pedestrian floor signal light 151 may include an illumination sensor and may vary the amount of light output depending on daytime and nighttime.

In addition, the pedestrian floor signal light 151 may further include a pressure sensor, and when a pedestrian signal is received, the pedestrian floor signal light 151 displays a spot at the pressurized point or displays a primary color series at the pressurized point. By outputting the colors, it can help to identify the location of pedestrians more clearly.

In addition, the pedestrian floor traffic light 151 irradiates a preset light to the head of the object (child) analyzed by the object analysis unit 130 at night to illuminate the surrounding area while the object (child) is crossing the crosswalk. Light can be emitted to enable vehicles to identify the child's location.

Next, the vehicle floor signal light 152 is installed on the road in a direction opposite to the vehicle driving direction so as to be in the front view of the driver, and the vehicle progresses with red, green, yellow, and green arrow lights on/off, It may be a device that performs the function of instructing stop, detour, etc.

The control unit 153 receives either a vehicle traffic signal or a pedestrian signal from a traffic signal controller installed in an adjacent area of the crosswalk, and activates the pedestrian floor signal light 141 or the vehicle floor signal light 142 according to the input signal. It may be a configuration that is controlled as much as possible.

Meanwhile, in a dangerous situation, for example, when the speed of the object analyzed by the object analysis unit exceeds the speed that complies with the child protection zone, the control unit 152 activates the pedestrian traffic light 151 to display the license plate number and license plate number of the speeding vehicle. Pedestrian floor traffic lights can be controlled to output speeding speeds.

Therefore, the floor traffic light system for child protection disclosed in the present invention is installed in a child protection zone (School Zone), detects the approach of children or entry into vehicles, and simultaneously recognizes cautions and warnings to vehicle drivers and pedestrians (children). Additionally, the pedestrian's age can be estimated from the pedestrian's walking video, and if the pedestrian is a child, auditory and visual caution information such as sound and video is output to prevent physical signal violations by surrounding vehicles from occurring in advance. , it has the advantage of helping children move safely.

6 is a diagram illustrating an example computing environment in which one or more embodiments disclosed herein may be implemented, and is an illustration of a system 1000 that includes a computing device 1100 configured to implement one or more embodiments described above. shows. For example, computing device 1100 may include a personal computer, server computer, handheld or laptop device, mobile device (mobile phone, PDA, media player, etc.), multiprocessor system, consumer electronics, minicomputer, mainframe computer, Distributed computing environments including any of the above-described systems or devices, etc. are included, but are not limited thereto.

Computing device 1100 may include at least one processing unit 1110 and memory 1120. Here, the processing unit 1110 may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc. and can have multiple cores. Memory 1120 may be volatile memory (eg, RAM, etc.), non-volatile memory (eg, ROM, flash memory, etc.), or a combination thereof. Additionally, computing device 1100 may include additional storage 1130. Storage 1130 includes, but is not limited to, magnetic storage, optical storage, etc. The storage 1130 may store computer-readable instructions for implementing one or more embodiments disclosed in this specification, and other computer-readable instructions for implementing an operating system, application program, etc. may also be stored. Computer-readable instructions stored in storage 1130 may be loaded into memory 1120 for execution by processing unit 1110. Computing device 1100 may also include input device(s) 1140 and output device(s) 1150.

Here, the input device(s) 1140 may include, for example, a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, or any other input device, etc. Additionally, output device(s) 1150 may include, for example, one or more displays, speakers, printers, or any other output devices. Additionally, the computing device 1100 may use an input device or output device provided in another computing device as the input device(s) 1140 or the output device(s) 1150.

Additionally, computing device 1100 may include communication connection(s) 1160 that allows computing device 1100 to communicate with another device (e.g., computing device 1300).

Here, communication connection(s) 1160 may include a modem, network interface card (NIC), integrated network interface, radio frequency transmitter/receiver, infrared port, USB connection, or other device for connecting computing device 1100 to another computing device. May contain interfaces. Additionally, communication connection(s) 1160 may include a wired connection or a wireless connection. Each component of the computing device 1100 described above may be connected by various interconnections such as buses (e.g., peripheral component interconnect (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.) and may be interconnected by a network 1200. As used herein, terms such as "component", "system", etc. generally refer to computer-related entities that are hardware, a combination of hardware and software, software, or software in execution.

For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. For example, both the application running on the controller and the controller can be components. One or more components may reside within a process and/or thread of execution, and a component may be localized on one computer or distributed between two or more computers.

In the above, the present invention has been described in detail with reference to examples, but those skilled in the art will be able to make various substitutions, additions, and modifications without departing from the technical spirit described above. It is natural, and such modified embodiments should also be understood as falling within the scope of protection of the present invention as defined by the patent claims attached below.

100: Floor traffic light system for child protection
110: Object detection device
120: Object photography device
130: Object analysis device
140: Floor traffic light device

Claims (18)

A plurality of object detection devices that detect the movement and approach of vehicles and pedestrians to a crosswalk in a child protection zone;
A plurality of object photographing devices activated by an object detection signal from the object sensing device to photograph objects (vehicles and people) entering a child protection zone;
An object analysis device that identifies an object as a person or an object from an object image and, if it is a person, classifies the object as an adult or child through facial analysis of the object; and
It is installed on the floor of the child protection zone and is linked with vehicle traffic lights and pedestrian traffic lights, so that when a vehicle traffic signal is applied, a child protection zone image and a speeding prevention video are output, and when a pedestrian signal is applied, a character image as a crosswalk mark is displayed. It includes a floor traffic light device that outputs,
The object analysis device is
Using a deep learning algorithm, the location coordinates (x, y) and size (a, h: height and width) of the object (bounding box) in the object image are detected, and based on the detected information, the object is classified into an object, person, or adult. and analyzed by children;
After merging and expanding the object detection areas of two different deep learning object analysis algorithms to create an integrated object detection area, human (human) objects located in the integrated object detection area are detected according to preset detection condition values. ,
The floor traffic light device is
When a pedestrian signal is received from a traffic signal controller, a pedestrian floor signal light that projects an image suitable for the characteristics of the pedestrian to the crosswalk area;
A vehicle that is installed on the road in the direction opposite to the vehicle's driving direction so that it is in the driver's frontal view, and indicates at least one of the following: proceed, stop, or detour through red, green, yellow, and green arrow indicators. floor traffic lights; and
A control unit that receives one of a vehicle traffic signal and a pedestrian signal from a traffic signal controller installed in an adjacent area of the crosswalk and controls the pedestrian floor signal light or the vehicle floor signal light to be activated according to the input signal,
A floor traffic light system for child protection, wherein when the pedestrian is a child, the image is a character or animation.
According to paragraph 1,
A floor traffic light system for protecting children, further comprising a sound device that outputs sound corresponding to the image output from the floor traffic light device.
delete delete According to paragraph 1,
The object analysis device is
The speed, which is a characteristic of the moving object (vehicle) in the object image, can be calculated, and the speed is calculated according to the change in the position coordinates of the object (image bounding box) detected for each image frame. floor traffic light system. According to paragraph 1,
The object analysis device is
A floor traffic light system for child protection, characterized in that it identifies and analyzes the license plate of a moving object (vehicle) in the object image.
delete According to paragraph 1,
The control unit
When the speed of the object analyzed by the object analysis device exceeds the speed that complies with the child protection zone, the pedestrian floor signal light is activated to control the pedestrian floor signal light to output the license plate number and speed of the speeding vehicle. Features a floor traffic light system for child protection.
According to clause 8,
The pedestrian floor signal light may further include a pressure sensor,
A floor traffic light system for child protection that displays a spot at the pressurized point or outputs primary colors at the pressurized point when a pedestrian signal is received.
According to clause 9,
The pedestrian floor traffic lights are
At night, a preset light is irradiated to the head of the object (child) analyzed by the object analysis device, allowing surrounding vehicles to identify the child's location while the object (child) is crossing the crosswalk. A floor traffic light system for child protection, characterized in that it investigates.
Detecting at least one moving object passing or approaching a child protection zone (crosswalk);
Photographing an area where the moving object is detected and analyzing the moving object based on the shape or characteristics of at least one moving object; and
When a walking signal is input from an external device, it includes the step of transmitting a pedestrian protection image according to object characteristics to the crosswalk area,
The step of analyzing the moving object is
Using a deep learning algorithm, the location coordinates (x, y) and size (a, h: height and width) of the object (bounding box) in the object image are detected, and moving objects are classified into objects, people, etc. based on the detected information. Analyzed by adults and children,
After merging and expanding the object detection areas of two different deep learning object analysis algorithms to create an integrated object detection area, human (human) objects located in the integrated object detection area are detected according to preset detection condition values. ,
The step of transmitting the pedestrian protection video to the crosswalk area is
When a pedestrian signal is received from the traffic signal controller, outputting an image suitable for the characteristics of the pedestrian from the pedestrian floor signal light that illuminates the crosswalk area,
When the pedestrian is a child, the image is a character or animation. A method of operating a floor traffic light system for protecting children.
delete delete According to clause 11,
The step of analyzing the moving object is
Calculating the speed, which is a characteristic of a moving object (vehicle) in the object image, and further comprising calculating the speed according to a change in the position coordinates of the object (image bounding box) detected for each image frame. How to operate a floor traffic light system for child protection.
According to clause 14,
The step of analyzing the moving object is
A method of operating a floor traffic light system for child protection, comprising the step of identifying and analyzing a license plate of a moving object (vehicle) in the object image.
delete According to clause 11,
When a vehicle signal is received from the traffic signal controller, the vehicle floor signal light is installed on the road in the direction opposite to the vehicle's driving direction so that it is in the driver's frontal view, and the vehicle is driven with red, green, yellow, and green arrow lights on/off. A method of operating a floor traffic light system for child protection, further comprising the step of instructing at least one of progress, stop, and detour.
According to clause 11,
If the speed of the object analyzed by the object analysis device in the control unit exceeds the speed that complies with the child protection zone, the pedestrian floor signal light is activated to control the pedestrian floor signal light to output the license plate number and speed of the speeding vehicle. A method of operating a floor traffic light system for child protection, comprising the steps: