KR102560301B1 - Server and Method for prevent collisions between pedestrians and vehicles thereof - Google Patents

Abstract

A server and a control method for preventing a collision between a pedestrian and a vehicle are provided. The control method of the present server includes acquiring an image including a pedestrian and a vehicle from a photographing device, detecting the pedestrian and the vehicle in the image, predicting the moving direction and speed of each of the detected pedestrian and vehicle, determining the possibility of collision between the detected pedestrian and the detected vehicle based on the predicted moving direction and speed, recognizing the license plate number of the detected vehicle when it is determined that a collision between the detected pedestrian and the detected vehicle is possible, and sending a warning message to a user terminal corresponding to the vehicle number.

Description

Server and method for preventing collisions between pedestrians and vehicles

The present disclosure relates to a server for preventing collision between a pedestrian and a vehicle and a control method thereof, and more particularly, to a server for determining the possibility of a collision between a pedestrian and a vehicle through an image captured by a photographing device and providing a warning message, and a control method thereof.

In recent years, pedestrians (eg, children) enter the roadway before the pedestrian traffic light turns green at the crosswalk in the school zone, or after the signal changes, they run into the crosswalk without looking around and see only the front, and there are many accidents where they run into traffic violations or speeding vehicles. In particular, considering that jaywalking fatal accidents account for 40% of pedestrian fatal accidents, jaywalking fatal accidents can emerge as a major social problem.

In order to solve this problem, as an example of the prior art, there is a technology for providing a warning message by recognizing the current state of a traffic light, camera, and vehicle speed in order to prevent an accident between a pedestrian and a vehicle at a crosswalk in a school zone. In this case, a secondary coil must be installed to recognize the vehicle speed. That is, using various sensors is stable and accurate, but there is a limitation in that the installation cost of the system is high.

In addition, as another example of the prior art, a technology for providing a warning message using text and auditory signals on an electric signboard exists. However, it is difficult to give immediate attention to the driver because the electric signboard must be installed considering the appropriate location and size, and there is a limit to the acoustic signal that can be generated as noise.

In addition, as another example of the prior art, there is a technology for providing a warning message with a voice signal after predicting the direction of movement of the pedestrian by installing a sensor for recognizing a movement pattern on the road for recognizing the pedestrian. However, there are problems in terms of cost of constructing such a system, difficulty in maintenance and repair, and difficulty in using the system in a crowded city center or in a noisy place because the warning signal is acoustic.

The present disclosure is intended to solve the above-described problems, and an object of the present disclosure is to provide a warning message to a user terminal by determining the possibility of collision between a pedestrian and a vehicle through an image obtained through CCTV without a separate sensor. It is to provide a server and a control method thereof.

According to an embodiment of the present disclosure, a control method of a server for preventing collision between a pedestrian and a vehicle includes obtaining an image from a photographing device; detecting pedestrians and vehicles included in the image; predicting a moving direction and speed of each of the detected pedestrian and the detected vehicle; determining a possibility of collision between the detected pedestrian and the detected vehicle based on the predicted moving direction and speed; recognizing a license plate number of the detected vehicle when it is determined that a collision is possible between the detected pedestrian and the detected vehicle; and transmitting a warning message to a user terminal corresponding to the license plate number.

The predicting may include determining the moving direction and speed of the detected pedestrian and the detected vehicle, respectively, based on the positions of the detected pedestrian and the detected vehicle included in a plurality of image frames acquired for a critical period of time. Predictable.

In addition, the determining step may generate an expected path of each of the detected pedestrian and the detected vehicle based on the predicted moving direction and speed, and determine the possibility of collision between the detected pedestrian and the detected vehicle based on whether or not an intersection of the predicted path generated for each of the detected pedestrian and the detected vehicle exists at the same time point.

Then, identifying GPS information of the photographing device; and identifying an access point located at a point where the collision occurs based on the GPS information. Transmitting a signal to broadcast a warning message to the identified access point; may include.

In addition, when the user terminal of the detected pedestrian receives the broadcast warning message, a warning message may be output through an application installed in the user terminal of the detected pedestrian.

And, the warning message is output through an application installed in the user terminal, and may be output in at least one of visual, auditory, and tactile forms.

In addition, when it is determined that a collision is possible between the detected pedestrian and the detected vehicle, storing the obtained image and the detected vehicle number; may include.

According to an embodiment of the present disclosure, a server for preventing collision between a pedestrian and a vehicle includes a communication interface; a memory storing at least one instruction; and a processor controlling the server based on the communication interface and the memory, wherein the processor, by executing the at least one instruction, obtains an image from the photographing device through the communication interface, detects a pedestrian and a vehicle included in the image, predicts a moving direction and speed of each of the detected pedestrian and the detected vehicle, determines a possibility of collision between the detected pedestrian and the detected vehicle based on the predicted moving direction and speed, and determines that a collision between the detected pedestrian and the detected vehicle is possible. In this case, the communication interface may be controlled to recognize the vehicle number of the detected vehicle and transmit a warning message to a user terminal corresponding to the vehicle number.

In addition, the processor may predict the moving direction and speed of the detected pedestrian and the detected vehicle, respectively, based on the positions of the detected pedestrian and the detected vehicle included in a plurality of image frames acquired for a critical period of time.

In addition, the processor generates an expected path of each of the detected pedestrian and the detected vehicle based on the predicted moving direction and speed, and determines the possibility of collision between the detected pedestrian and the detected vehicle based on whether or not an intersection of the predicted path generated for each of the detected pedestrian and the detected vehicle exists at the same time point.

In addition, the processor identifies GPS information of the photographing device, identifies an access point located at a point where the collision occurs based on the GPS information, and broadcasts a warning message to the identified access point. It can control the communication interface to transmit a signal to broadcast.

And, when the user terminal of the detected pedestrian receives the broadcast warning message, a warning message may be output through an application installed in the user terminal of the detected pedestrian.

In addition, the warning message is output through an application installed in the user terminal, and may be output in at least one of visual, auditory, and tactile forms.

And, when it is determined that a collision is possible between the detected pedestrian and the detected vehicle, the processor may store the obtained image and the license plate number of the detected vehicle in the memory.

As described above, according to various embodiments of the present disclosure, since audible and tactile warnings are issued through a user terminal, a pedestrian or driver can immediately recognize a warning even in a noisy environment or in a situation where the user is not paying attention. In addition, by broadcasting a warning to all nearby pedestrians in the event of a collision warning, it is possible to help in quick response in the event of an accident. In addition, since a photographing device installed at a high location is used, an accident that may suddenly occur in a driver's blind spot can be prevented.

1 is a diagram for explaining a traffic accident prevention system according to an embodiment of the present disclosure;
2 is a block diagram for explaining the configuration of a server for preventing a collision between a pedestrian and a vehicle according to an embodiment of the present disclosure;
3 is a diagram illustrating an image frame photographed by a photographing device according to an embodiment of the present disclosure;
4 is a diagram for explaining a method for determining a possibility of collision based on an expected path between a pedestrian and a vehicle according to an embodiment of the present disclosure;
5 is a view for explaining an embodiment of recognizing a license plate number of a vehicle according to an embodiment of the present disclosure;
6 is a flowchart illustrating a control method of a server for preventing a collision between a pedestrian and a vehicle according to an embodiment of the present disclosure.

Since the present embodiments can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope to the specific embodiments, and should be understood to include various modifications, equivalents, and/or alternatives of the embodiments of the present disclosure. In connection with the description of the drawings, like reference numerals may be used for like elements.

In describing the present disclosure, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present disclosure, a detailed description thereof will be omitted.

In addition, the following embodiments may be modified in many different forms, and the scope of the technical idea of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the spirit of the disclosure to those skilled in the art.

Terms used in this disclosure are only used to describe specific embodiments, and are not intended to limit the scope of rights. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In the present disclosure, expressions such as “has,” “can have,” “includes,” or “may include” indicate the presence of corresponding features (eg, numerical values, functions, operations, or components such as parts), and do not exclude the presence of additional features.

In this disclosure, expressions such as “A or B,” “at least one of A and/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” can refer to (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in the present disclosure may modify various components regardless of order and/or importance, and are used to distinguish one component from another component, but do not limit the components.

When it is said that an element (eg, a first element) is "(functionally or communicatively) coupled with/to" or "connected to" another element (eg, a second element), it will be understood that the element may be directly connected to the other element or connected through another element (eg, a third element).

On the other hand, when an element (eg, a first element) is referred to as being “directly connected” or “directly connected” to another element (eg, a second element), it may be understood that no other element (eg, a third element) exists between the element and the other element.

The expression “configured to (or configured to)” used in this disclosure may be used interchangeably with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of” depending on the circumstances. The term "configured (or set) to" may not necessarily mean only "specifically designed to" hardware.

Instead, in some contexts, the phrase "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured (or configured) to perform A, B, and C" may refer to a dedicated processor (e.g., embedded processor) for performing the corresponding operation, or a generic-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations by executing one or more software programs stored in a memory device.

In an embodiment, a 'module' or 'unit' performs at least one function or operation, and may be implemented with hardware or software, or a combination of hardware and software. In addition, a plurality of 'modules' or a plurality of 'units' may be integrated into at least one module and implemented by at least one processor, except for 'modules' or 'units' that need to be implemented with specific hardware.

Meanwhile, various elements and areas in the drawings are schematically drawn. Therefore, the technical spirit of the present invention is not limited by the relative size or spacing drawn in the accompanying drawings.

Hereinafter, with reference to the accompanying drawings, an embodiment according to the present disclosure will be described in detail so that those skilled in the art can easily implement it.

1 is a diagram for explaining a traffic accident prevention system according to an embodiment of the present disclosure. As shown in FIG. 1 , the traffic accident prevention system 1 includes a photographing device 10 and a server 100. It may include a driver's user terminal 20, an access point 30, and a pedestrian's user terminal 40.

The photographing device 10 may be installed on a road and capture an image including at least one of a vehicle and a pedestrian. The photographing device 10 may transmit all captured images to the server 100 in real time, but this is only an example, and the image may be transmitted to the server 100 when at least one of a vehicle and a pedestrian is detected. The photographing device 10 may be implemented as a CCTV, but this is only an example and may be implemented as a device such as a black box of another vehicle. In addition, a plurality of photographing devices 10-1, 10-2, ... may be present at an arbitrary position.

The server 100 may detect pedestrians and vehicles from images received from the photographing device 10 . In addition, the server 100 may detect the moving direction and speed of each of the pedestrian and the vehicle from the plurality of image frames in which the pedestrian and the vehicle are detected. In addition, the server 100 may determine the possibility of collision between the pedestrian and the vehicle based on the moving direction and speed of the pedestrian and the vehicle, respectively. If it is determined that the pedestrian and the vehicle will collide, the server 100 may recognize the license plate number of the vehicle and provide a warning message to the user terminal 20 corresponding to the recognized license plate number.

In addition, the server 100 may identify GPS information of the photographing device 100 and identify an access point located at a point where a collision occurs based on the GPS information in order to provide a warning message to pedestrians as well. Then, the server 100 may transmit a signal to broadcast a warning message to the identified access point 30 . In addition, the server 100 may store information (eg, vehicle number, image, etc.) on a situation in which a warning situation occurs.

The driver's user terminal 20 may output the warning message received from the server through the application. In this case, the driver's user terminal 20 may provide a warning message in a visual form (eg, displaying a text message or an image message on the screen), as well as an audible warning message (eg, outputting a voice message saying “there is a person ahead”) or a tactile form (eg, a vibration message).

Meanwhile, the application installed in the driver's user terminal 20 may always be executed in the background, but this is only an example and may be executed in the background when it is determined that the driver is driving the vehicle. In addition, when installing the application, vehicle information may be provided to the server 100, and information on access rights (eg, location, camera, etc.) may be provided to the server 100.

The access point 30 may be installed around the photographing device 10 and may broadcast a warning message based on a signal received from the server 100 . Accordingly, all pedestrian user terminals 40 - 1 , 40 - 2 , ... located in an arbitrary area around the photographing device 10 may output a warning message.

The pedestrian's user terminal 40 may also output a warning message through an application, and may provide the warning message in at least one form among a visual form, an auditory form, and a tactile form.

2 is a block diagram illustrating a configuration of a server for preventing a collision between a pedestrian and a vehicle according to an embodiment of the present disclosure. As shown in FIG. 2 , the server 100 may include a communication interface 110 , a memory 120 and a processor 130 .

The communication interface 110 includes a circuit and can perform communication with an external device (eg, the photographing device 10, the user terminal 20, and the access point 30. Specifically, the processor 120 can receive various data or information from an external device connected through the communication interface 110, and can also transmit various data or information to the external device.

The communication interface 110 may include at least one of a WiFi module or a wireless communication module. Specifically, the WiFi module may perform communication using a WiFi method or a Bluetooth method. In the case of using the WiFi module, various connection information such as SSID is first transmitted and received, and various information can be transmitted and received after communication is connected using this. In addition, the wireless communication module may perform communication according to various communication standards such as IEEE, Zigbee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and 5th Generation (5G).

The memory 120 may store various data for preventing a traffic accident between a pedestrian and a vehicle. Specifically, the memory 120 may store an object detection module 131, a motion prediction module 133, a collision prediction module 135, a warning message providing module 137, and the like, and may store various neural network models. In addition, the memory 120 may store situation information (eg, image, vehicle number, etc.) when a warning situation occurs. Also, the memory 120 (particularly, a buffer) may store an image received through the communication interface 110 .

The memory 120 may be implemented as an internal memory such as a ROM (e.g., electrically erasable programmable read-only memory (EEPROM)) or RAM included in the processor 130, or may be implemented as a separate memory from the processor 130. In this case, the memory 120 may be implemented in the form of a memory embedded in the server 100 or in the form of a removable memory in the server 100 depending on the data storage purpose. For example, data for driving the server 100 is stored in a memory embedded in the server 100, and data for an extended function of the server 100 is removable from the server 100. It can be stored in a memory.

Meanwhile, in the case of memory embedded in the server 100, volatile memory (e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (e.g., one time programmable ROM (OTPROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory ( Example: NAND flash or NOR flash, etc.), a hard drive, or a solid state drive (solid state drive (SSD)), in the case of a memory that is removable from the server 100, a memory card (eg, CF (compact flash), SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.), external memory (eg, USB memory) connectable to a USB port It may be implemented in a form such as the like.

The processor 130 may be electrically connected to the memory 120 to control overall functions and operations of the server 100 . In particular, the processor 130 may include an object detection module 131, a motion prediction module 133, a collision prediction module 135, and a warning message providing module 137.

The processor 130 may detect at least one pedestrian and at least one vehicle included in an image frame received from the photographing device 10 through the object detection module 131 . In this case, the object detection module 131 may detect at least one pedestrian and at least one vehicle by using a neural network model learned to detect an object (eg, a pedestrian, a vehicle, a motorcycle, an animal, etc.) on the road. The neural network model may be implemented as a Convolution Neural Network (CNN) model, but this is only an example, and may be implemented as at least one artificial neural network model of a deep neural network (DNN), a recurrent neural network (RNN), and a generative adversarial network (GAN).

The object detection module 131 may detect at least one pedestrian and at least one vehicle from a plurality of image frames received during a predetermined period of time. The object detection module 131 may assign an ID to each of the detected at least one pedestrian and at least one vehicle.

The processor 130 may predict the moving direction and speed of at least one pedestrian and at least one vehicle based on the positions and moving times of at least one pedestrian and at least one vehicle detected by the motion estimation module 133 . For example, as shown in FIG. 3 , based on the positions and movement times of the pedestrian 310 and the vehicle 320 included in the first image frame 310-1 to the n-th image frame 310-n, the movement direction and speed of the pedestrian 310 and the vehicle 320 can be predicted.

The processor 130 may determine the possibility of collision based on the moving distance and speed of at least one pedestrian and at least one vehicle through the collision prediction module 135 . Specifically, the collision prediction module 135 may obtain the predicted path of the at least one pedestrian and the at least one vehicle based on the moving distance and speed of the at least one pedestrian and the at least one vehicle. In addition, the collision prediction module 135 may determine the possibility of collision between the pedestrian and the vehicle based on whether there exists an intersection of the predicted paths generated for each of the pedestrian and the vehicle at the same time point. For example, as shown in FIG. 4 , the collision prediction module 135 determines the first predicted path 410 of the pedestrian based on the moving direction and moving speed of the pedestrian 310, and the moving direction and moving speed of the vehicle. Based on the predicted second expected path 420 of the pedestrian. If it is determined that the intersection 430 occurs between the first expected warning 410 and the second predicted path 420 at the same time point (for example, 2 seconds later), the collision prediction module 135 may predict that the pedestrian 310 and the vehicle 320 may collide.

The processor 130 may provide a warning message to the driver and pedestrians of the vehicle through the warning message providing module 137 . Specifically, if it is determined that the vehicle has collided, the warning message providing module 327 may identify the vehicle number. For example, as shown in FIG. 5, the warning message providing module 137 may recognize a license plate located at a specific location (e.g., around the front bumper) of the detected vehicle 510, and may recognize a vehicle number included in a license plate through a neural network model trained for number recognition. Meanwhile, the license plate number of the vehicle may be identified when the possibility of collision is high, but this is only an example, and may be identified when the object recognition module 131 recognizes the object and assigns an ID.

The warning message providing module 137 may retrieve information about a driver having identification information (eg, contact number, ID, etc.) corresponding to the identified vehicle number. When the driver is searched for, the warning message providing module 137 may output a warning message to the driver's user terminal 20 based on information about the driver.

Also, the warning message providing module 137 may identify GPS information of the photographing device 20 that has transmitted the image in order to search for an access point 30 around the photographing device 10 . Also, the warning message providing module 137 may identify the access point 30 around the photographing device 10 based on the identified GPS information. And, the warning message providing module 137 may transmit a signal to broadcast the warning message to the identified access point 30 . Accordingly, when the user terminal of the detected pedestrian receives the broadcast warning message, the warning message may be output through an application installed in the user terminal of the detected pedestrian. In addition, a warning message may be output to user terminals of not only the detected pedestrian but also all pedestrians located around the photographing device 10 .

When it is determined that a warning situation occurs or an accident situation occurs, the processor 130 may store situation information. In this case, the situation information may include at least one of an image, a vehicle number, and GPS information of the photographing device 10 .

Meanwhile, the system hardware of the server 10 may utilize an embedded board, and through this, it is possible to detect the possibility of a collision between a pedestrian and a vehicle through low power of 15 W or less.

6 is a flowchart illustrating a control method of a server for preventing a collision between a pedestrian and a vehicle according to an embodiment of the present disclosure.

First, the server 100 may obtain an image from the photographing device 10 (S605).

The server 100 may detect pedestrians and vehicles from the obtained image (S610). At this time, the server 100 may detect pedestrians and vehicles from the obtained image using a neural network model learned through deep learning.

The server 100 may collect data on the location and time of pedestrians and vehicles (S615). That is, the server 100 may collect data on the location and time of pedestrians and vehicles from image frames received in real time from the photographing device 10 .

When the number of data is obtained equal to or greater than the threshold value N (S620-Y), the server 100 may predict the moving direction and speed of the pedestrian and vehicle based on the location and time data of the pedestrian and vehicle (S625).

The server 100 may predict the possibility of collision based on the moving direction and speed of the pedestrian and the vehicle (S630). Specifically, the server 100 generates an expected path for each pedestrian and vehicle based on the predicted moving direction and speed, and determines the possibility of collision between the pedestrian and the vehicle based on whether or not there exists an intersection of the predicted path generated for each of the pedestrian and the detected vehicle detected at the same time.

If it is determined that the pedestrian and the vehicle will collide (S635-Y), the server 100 may detect the vehicle license plate and recognize the vehicle number (S640). In this case, the server 100 may use a neural network model learned through deep learning to recognize license plates and vehicle numbers.

The server 100 may transmit a warning message to the driver's user terminal 20 (S645).

Also, the server 100 may transmit a signal to the access point where the photographing device is located (S650). In this case, the signal may include control information to broadcast a warning message to transmit the warning message to the user terminal of the pedestrian.

The server 100 may store information on the warning situation (S655). Specifically, the server 100 may store an image of a warning situation, vehicle information, and the like.

According to various embodiments of the present disclosure as described above, since the server 100 issues an audible and tactile warning through the user terminals 20 and 40, the pedestrian or driver can immediately recognize the warning even in a noisy environment or in a situation where the user is not paying attention. In addition, by broadcasting a warning to all nearby pedestrians in the event of a collision warning, it is possible to help in quick response in the event of an accident. In addition, since a photographing device installed at a high location is used, an accident that may suddenly occur in a driver's blind spot can be prevented.

On the other hand, in the present disclosure, it has been described that a warning message is provided by determining the possibility of collision between a pedestrian and a vehicle, but this is only one embodiment, and a separate terminal (eg, a device installed in a CCTV) determines the possibility of collision between a pedestrian and a vehicle and provides a warning message.

Meanwhile, functions related to the neural network model as described above may be performed through a memory and a processor. A processor may consist of one or a plurality of processors. At this time, one or a plurality of processors are CPUs, general-purpose processors such as APs, GPUs. It may be a graphics-only processor, such as a VPU, or an artificial intelligence-only processor, such as an NPU. One or more processors control the input data to be processed according to predefined operating rules or artificial intelligence models stored in the non-volatile memory and the volatile memory. A predefined action rule or artificial intelligence model is characterized in that it is created through learning.

Here, being created through learning means that a predefined operation rule or an artificial intelligence model having desired characteristics is created by applying a learning algorithm to a plurality of learning data. Such learning may be performed in the device itself in which artificial intelligence according to the present disclosure is performed, or may be performed through a separate server/system.

A neural network model may be composed of a plurality of neural network layers. Each layer has a plurality of weight values, and the layer operation is performed through the operation result of the previous layer and the plurality of weight values. Examples of neural networks include Convolutional Neural Network (CNN), Deep Neural Network (DNN), RNN (Recurrent Neural Network), RBM (RBM) Network), BRDNN (Bidirectional Recurrent Deep Neural Network), GAN (Generate Adversarial Networks), and Deep Q-Networks, except for the case of the nerve network in this disclosure. It is not limited to a drunken example.

A learning algorithm is a method of training a predetermined target device (eg, a robot) using a plurality of learning data so that the predetermined target device can make a decision or make a prediction by itself. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithm in the present disclosure is not limited to the above-described examples except for the cases specified.

The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-temporary storage medium' only means that it is a tangible device and does not contain a signal (e.g., electromagnetic wave), and this term does not distinguish between the case where data is semi-permanently stored in the storage medium and the case where it is temporarily stored. For example, a 'non-temporary storage medium' may include a buffer in which data is temporarily stored.

According to one embodiment, the method according to various embodiments disclosed in this document may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. A computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read only memory (CD-ROM)), or may be distributed (e.g., downloaded or uploaded) online, through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a part of a computer program product (e.g., a downloadable app) is at least temporarily stored in a device-readable storage medium, such as a manufacturer's server, an application store server, or a relay server's memory, or may be temporarily created.

Each of the components (eg, modules or programs) according to various embodiments of the present disclosure as described above may be composed of a single object or a plurality of entities, and some of the sub-components may be omitted or other sub-components may be further included in various embodiments. Alternatively or additionally, some components (eg, modules or programs) may be integrated into one entity and perform the same or similar functions performed by each corresponding component prior to integration.

According to various embodiments, operations performed by modules, programs, or other components may be executed sequentially, in parallel, repetitively, or heuristically, or at least some operations may be executed in a different order, may be omitted, or other operations may be added.

Meanwhile, the term “unit” or “module” used in the present disclosure includes a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A “unit” or “module” may be an integrated component or a minimum unit or part thereof that performs one or more functions. For example, the module may be composed of an application-specific integrated circuit (ASIC).

Various embodiments of the present disclosure may be implemented as software including instructions stored in a storage medium readable by a machine (eg, a computer). A device is a device capable of calling instructions stored in the storage medium and operating according to the called instructions, and may include a server according to the disclosed embodiments.

When the command is executed by a processor, the processor may directly or use other elements under the control of the processor to perform a function corresponding to the command. An instruction may include code generated or executed by a compiler or interpreter.

Although preferred embodiments of the present disclosure have been shown and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications and implementations are possible by those skilled in the art without departing from the gist of the present disclosure claimed in the claims, and these modified implementations should not be individually understood from the technical spirit or prospect of the present disclosure.

10: shooting device 100: server
20: driver's user terminal 30: access point (AP)
40: pedestrian user terminal

Claims (14)

In the server control method for preventing collision between a pedestrian and a vehicle,
Obtaining an image from a photographing device;
detecting pedestrians and vehicles included in the image;
predicting a moving direction and speed of each of the detected pedestrian and the detected vehicle;
determining a possibility of collision between the detected pedestrian and the detected vehicle based on the predicted moving direction and speed;
recognizing a license plate number of the detected vehicle when it is determined that a collision is possible between the detected pedestrian and the detected vehicle;
Transmitting a warning message to a user terminal corresponding to the vehicle number;
identifying GPS information of the photographing device;
identifying an access point located at a point where the collision occurs based on the GPS information;
transmitting a signal to broadcast a warning message to the identified access point; and
When the user terminal of the detected pedestrian receives the broadcast warning message, outputting a warning message through an application installed in the user terminal of the detected pedestrian;
The step of judging is
Based on the predicted moving direction and speed, an expected path of each of the detected pedestrian and the detected vehicle is generated;
The method of determining the possibility of collision between the detected pedestrian and the detected vehicle based on whether there is an intersection of the predicted path generated for each of the detected pedestrian and the detected vehicle at the same time point. According to claim 1,
The predicting step is
A method of predicting a moving direction and speed of each of the detected pedestrian and the detected vehicle based on the positions of the detected pedestrian and the detected vehicle included in a plurality of image frames acquired for a critical period of time. delete delete delete According to claim 1,
The warning message is
A method of outputting through an application installed in the user terminal and outputting in the form of at least one of visual, auditory, and tactile. According to claim 1,
and storing the obtained image and the detected vehicle number when it is determined that a collision is possible between the detected pedestrian and the detected vehicle. In the server control method for preventing collision between a pedestrian and a vehicle,
communication interface;
a memory storing at least one instruction; and
A processor controlling the server based on the communication interface and the memory; includes,
The processor, by executing the at least one instruction,
Obtaining an image from a photographing device through the communication interface;
Detecting pedestrians and vehicles included in the image,
predicting the moving direction and speed of each of the detected pedestrian and the detected vehicle;
Based on the predicted moving direction and speed, generating an expected path of each of the detected pedestrian and the detected vehicle;
Determining a possibility of collision between the detected pedestrian and the detected vehicle based on whether there exists an intersection of an expected path generated for each of the detected pedestrian and the detected vehicle at the same time point;
When it is determined that a collision is possible between the detected pedestrian and the detected vehicle, recognizing the license plate number of the detected vehicle;
Controlling the communication interface to transmit a warning message to a user terminal corresponding to the vehicle number;
identifying GPS information of the photographing device;
Identifying an access point located at a point where the collision occurs based on the GPS information,
Sending a signal to broadcast a warning message to the identified access point;
When the user terminal of the detected pedestrian receives the broadcast warning message, the server outputs a warning message through an application installed in the user terminal of the detected pedestrian. According to claim 8,
the processor,
A server for predicting a moving direction and speed of the detected pedestrian and the detected vehicle, respectively, based on the positions of the detected pedestrian and the detected vehicle included in a plurality of image frames acquired for a critical period of time. delete delete delete According to claim 8,
The warning message is
A server that is output through an application installed in the user terminal and is output in the form of at least one of visual, auditory, and tactile. According to claim 8,
the processor,
When it is determined that a collision is possible between the detected pedestrian and the detected vehicle, the server stores the obtained image and the license plate number of the detected vehicle in the memory.

Images