KR102531281B1 - Method and system for generating passing object information using the sensing unit - Google Patents

Abstract

The present disclosure relates to a method and system for generating traffic object information. In the method according to an embodiment of the present disclosure, one or more surrounding objects may be recognized from a plurality of data obtained from the sensing unit. In addition, the method may determine one or more traffic objects corresponding to at least a part of the one or more neighboring objects based on whether the one or more neighboring objects are repeatedly counted. In addition, the method may assign a unique ID to each of the traffic objects and generate traffic object information obtained by analyzing the traffic objects.

Description

Method and system for generating traffic object information using a sensing unit {METHOD AND SYSTEM FOR GENERATING PASSING OBJECT INFORMATION USING THE SENSING UNIT}

The present invention relates to a method and system for generating traffic object information using a sensing unit.

Despite the recent pandemic period, outdoor display advertisements such as transportation facility advertisements, which are emerging as digital signage, are making new investments in areas preferred by advertisers, and are becoming a digital trend due to the characteristics that can be expanded without spatial limitations in the future. It has the potential to transform.

In addition, a special case for demonstration was recently approved for a platform business that utilizes mobile platform technology to enable private drivers to provide their cars as advertising media and earn advertising revenue while driving.

As such, in line with the growth of the outdoor advertising market, technology for evaluating the value of facilities where advertisements are posted or areas where vehicles with advertisements are driven is required. However, according to the conventional floating population analysis technology, objects recognized by the sensing unit, such as cameras and radars, are repeatedly counted regardless of whether they are the same, resulting in poor accuracy.

In the present invention, information having a high level of precision is generated by avoiding double counting of floating population or passing vehicles, and can be used as meaningful data in various businesses including outdoor advertising and real estate.

The foregoing background art is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention.

An object of the present disclosure is to provide meaningful analysis information about a traffic object by using a method and system for generating traffic object information. The problem to be solved by the present invention is not limited to the above-mentioned problems, and other problems and advantages of the present invention that are not mentioned can be understood by the following description and more clearly understood by the embodiments of the present invention. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by the means and combinations indicated in the claims.

As a technical means for achieving the above technical problem, a first aspect of the present disclosure is a method for generating traffic object information, comprising: recognizing one or more surrounding objects from a plurality of data obtained from a sensing unit; determining one or more transit objects corresponding to at least a part of the one or more neighboring objects based on whether the one or more neighboring objects are repeatedly counted; and generating traffic object information including a unique ID of each of the traffic objects.

A second aspect of the present disclosure is a system for generating traffic object information, comprising: a memory in which at least one program is stored; and at least one processor operating according to the at least one program, wherein the at least one processor recognizes one or more surrounding objects from a plurality of data obtained from the sensing unit, and redundant data for the one or more surrounding objects Based on whether or not counting, determining one or more traffic objects corresponding to at least a part of the one or more neighboring objects, assigning a unique ID to each of the traffic objects, and generating traffic object information obtained by analyzing the traffic objects, system can be provided.

A third aspect of the present disclosure may provide a computer-readable recording medium recording a program for executing the method according to the first aspect on a computer.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to an embodiment of the present invention, by providing meaningful information based on floating population and traffic through data collected by the sensing unit, valuation to help real estate market participants make decisions, valuation related to real estate/vehicle outdoor advertising, etc. can be utilized for

In addition, information with a high level of precision can be generated by processing data collected by cameras and radars to avoid double counting of floating population or passing vehicles.

1 and 2 are diagrams for explaining an autonomous driving method according to an embodiment.
3 is a block diagram of a transit object generation system according to an embodiment.
4 is an exemplary diagram for explaining a method of recognizing a surrounding object according to an exemplary embodiment.
5A and 5B are exemplary diagrams for explaining a method of determining a passing object according to an exemplary embodiment.
6A and 6B are exemplary diagrams for explaining a method of determining a detection range of a sensing unit.
7 is an exemplary diagram for explaining a process of de-identifying a travel object and generating a unique ID in order to generate travel object information according to an embodiment.
8 is a flowchart illustrating a method of generating transit object information using a sensing unit according to an exemplary embodiment.

Advantages and features of the present invention, and methods for achieving them will become clear with reference to the detailed description of embodiments in conjunction with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Some embodiments of the present disclosure may be represented as functional block structures and various processing steps. Some or all of these functional blocks may be implemented as a varying number of hardware and/or software components that perform specific functions. For example, functional blocks of the present disclosure may be implemented by one or more microprocessors or circuit configurations for a predetermined function. Also, for example, the functional blocks of this disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as an algorithm running on one or more processors. In addition, the present disclosure may employ prior art for electronic environment setting, signal processing, and/or data processing. Terms such as "mechanism", "element", "means" and "component" may be used broadly and are not limited to mechanical and physical components.

In addition, connecting lines or connecting members between components shown in the drawings are only examples of functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that can be replaced or added.

Hereinafter, 'vehicle' may refer to all types of transportation means such as a car, bus, motorcycle, kickboard, or truck that are used to move people or objects with engines. In addition, 'real estate' can mean all kinds of immovable property such as land, buildings, trees, etc. For example, buildings (offices, buildings), public facilities (bus shelters), transportation facilities (stations, airports) , public spaces (in elevators), leisure facilities (movie theaters, concert halls, exhibition halls, lodging and sports facilities), and shopping facilities (large stores, retail stores).

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

1 and 2 are diagrams for explaining an autonomous driving method according to an embodiment.

Referring to FIG. 1 , an autonomous driving device according to an embodiment of the present invention may be mounted on a vehicle to implement an autonomous vehicle 10 . An autonomous driving device mounted on the autonomous vehicle 10 may include various sensors for collecting surrounding situation information. As an example, the autonomous driving device may detect the movement of the preceding vehicle 20 running in front through an image sensor and/or an event sensor mounted on the front of the autonomous vehicle 10 . The self-driving device may further include sensors for detecting the front side of the self-driving vehicle 10, another driving vehicle 30 operating in a side road, and pedestrians around the self-driving vehicle 10.

At least one of the sensors for collecting situational information around the self-driving vehicle may have a predetermined field of view (FoV) as shown in FIG. 1 . For example, when a sensor mounted on the front of the autonomous vehicle 10 has an angle of view (FoV) as shown in FIG. 1 , information detected in the center of the sensor may have a relatively high importance. This may be because most of the information corresponding to the motion of the preceding vehicle 20 is included in the information detected from the center of the sensor.

The self-driving device controls the movement of the self-driving vehicle 10 by processing information collected by sensors of the self-driving vehicle 10 in real time, while storing at least some of the information collected by the sensors in a memory device. .

Referring to FIG. 2 , an autonomous driving device 40 may include a sensor unit 41 , a processor 46 , a memory system 47 , a vehicle body control module 48 , and the like. The sensor unit 41 includes a plurality of sensors 42-45, and the plurality of sensors 42-45 may include an image sensor, an event sensor, an illuminance sensor, a GPS device, an acceleration sensor, and the like.

Data collected by sensors 42-45 may be passed to processor 46. The processor 46 stores the data collected by the sensors 42-45 in the memory system 47, and controls the body control module 48 based on the data collected by the sensors 42-45 to control the vehicle movement can be determined. The memory system 47 may include two or more memory devices and a system controller for controlling the memory devices. Each of the memory devices may be provided as a single semiconductor chip.

In addition to the system controller of the memory system 47, each of the memory devices included in the memory system 47 may include a memory controller, and the memory controller may include an artificial intelligence (AI) operation circuit such as a neural network. The memory controller may generate calculation data by assigning a predetermined weight to data received from the sensors 42 to 45 or the processor 46 and store the calculation data in a memory chip.

3 is a block diagram of a transit object generation system according to an embodiment.

In one embodiment, the transit object generation system 300 according to the present invention includes a sensing unit 310, an object recognition unit 320, an object determination unit 330, an information generation unit 340 and a display unit 350. It may include, and each module may include a processor (not shown).

A processor (not shown) may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to a processor (not shown) by a storage medium (not shown) or a communication module (not shown). For example, the processor (not shown) may be configured to execute received instructions according to program codes stored in a recording device such as a storage medium.

In one embodiment, the sensing unit 310 may include a radar 311 and a camera 312 .

The system 300 of the present invention may include a plurality of sensing units 310 , and each sensing unit 310 may include a plurality of radars 311 and a plurality of cameras 312 . The sensing unit 310 may be mounted on at least one of the front, rear, and side surfaces of certain objects including real estate (buildings) and vehicles. The system 300 may generate traffic object information based on the installation location of each sensing unit 310 .

The radar 311 may acquire a plurality of measurement values by radiating radio waves to the surroundings and detecting reflected waves that are reflected and incident on an object. Specifically, the plurality of measurement values may be a plurality of measurement points. The radar 311 is relatively robust to an external environment, and can physically directly acquire an accurate distance and speed with a round-trip time of radio waves.

The camera 312 may acquire a plurality of images or video data through photographing. The camera 312 can effectively recognize an object by detecting an object in the form of a feature.

In one embodiment, the object recognition unit 320 may recognize one or more surrounding objects existing around the system 300 by receiving a plurality of data acquired by the sensing unit. Neighboring objects may include object objects and traffic objects, and traffic objects may include vehicles and pedestrians. An embodiment in which the object recognition unit 320 recognizes a surrounding object will be described in detail with reference to FIG. 4 below.

4 is an exemplary diagram for explaining a method of recognizing a surrounding object according to an exemplary embodiment.

The object recognizing unit may receive a plurality of images including a previous image 410 and a current image 420 from the sensing unit. A plurality of images received from the sensing unit may include a plurality of objects.

For example, object 412 may be a pedestrian. The plurality of images 410 and 420 may have a predetermined size. The plurality of images 410 and 420 may include the same object 412 and 422, but the relative position of the object 411 and 412 continues as the object on which the sensing unit is mounted moves or the object 412 and 422 moves. Accordingly, even the same objects 411 and 412 have different positions within each image.

In the case of using the entire image to determine which object is the same in each image, the amount of data transmission and calculation becomes considerably large. Accordingly, in the case of a device mounted on a vehicle in one embodiment of the present invention, it is difficult to process through edge computing and real-time analysis is also difficult.

Referring to FIG. 4 , bounding boxes 411 and 421 included in images 410 and 420 are illustrated.

Referring to the previous image 410 , the bounding box 411 is metadata for the object 412 , and the bounding box information may include location information and size information on the image 410 . For example, the bounding box information may include information that the upper left vertex of the object 412 is located at (x, y) on the image and information that the size of the object 412 is w x h. The description of the bounding box 421 of the object 422 of the current image 420 is the same as described above.

The object recognizing unit may recognize surrounding objects from a plurality of received images.

In one embodiment, the object recognizing unit divides the image into grids of the same size, predicts the number of bounding boxes designated in a predefined form around the center of the grid for each grid, and calculates reliability based on this. The object recognizing unit determines whether an object is included in the image or only a background is present, selects a location having high object reliability, and determines an object category, thereby recognizing the object as a result. However, the method of recognizing an object in the present disclosure is not limited thereto.

In one embodiment, the object recognition unit may determine the identity of each neighboring object included in the plurality of images. For example, the object recognizing unit may obtain first location information of the surrounding object 412 recognized in the previous image 410 . The first location information may include coordinate information of any one vertex (eg, upper left vertex) of the bounding box 411 corresponding to the surrounding object 412 on the previous image 410 and horizontal and vertical length information. there is. Also, the object recognizing unit may obtain second location information of the surrounding object 422 recognized in the current image 420 .

The object recognizing unit may calculate a similarity between first location information of the surrounding object 412 recognized from the previous image 410 and second location information of the surrounding object 422 recognized from the current image 420 .

Referring to FIG. 4 , using the first location information and the second location information, the object recognition unit determines the intersection and union between the surrounding object 412 of the previous image 410 and the surrounding object 422 of the current image 420. can be calculated The pedestrian positioning device may calculate a value of the intersection area compared to the union area, and determine that the two neighboring objects 412 and 422 are the same object when the calculated value is greater than or equal to a threshold value. However, a method of determining the identity of neighboring objects in a plurality of images is not limited to the above method.

In another embodiment, referring to FIG. 3 again, the object recognizer 320 generates a sensor fusion image based on the image data received from the sensing unit 310 and a plurality of measurement values, and obtains location information of surrounding objects. can be calculated For example, a sensor fusion image is generated by matching lateral distance information with an object calculated from a plurality of measurement values obtained by the radar 311 and image data obtained by the camera 312, and a plurality of measurement values and By analyzing the sensor fusion image, it is possible to calculate the location information of the surrounding objects included in the image data.

The object recognizing unit 320 projects the information acquired from the radar 311 onto the camera coordinate system, and provides lateral distance information between the object obtained from the radar 311 and the surrounding objects in the 2D image captured by the camera 312. can be mapped.

In addition, the object recognizing unit 320 estimates first location information about a target recognized as a surrounding object from a plurality of measurement values detected through the radar 311, or sensor fusion between the camera 312 and the radar 311. It is possible to finally calculate the location information of the surrounding object by recognizing the surrounding object included in the image as a target and estimating the second location information of the target.

For example, the object recognition unit 320 obtains measurement points corresponding to a plurality of measurement values by radiating radio waves from the radar 311 and detecting reflected waves that are reflected and incident on surrounding objects, and based on the target detection probability Measurement points may be clustered into a predetermined group. For example, clustering can be performed through a linear model criterion. At this time, by updating the clustered group using measurement points obtained consecutively, the clustered group maintaining continuity may be recognized as a neighboring object. Also, the object recognizer 320 may estimate a point in the clustering area as first location information of a neighboring object.

As another example, the object recognizing unit 320 may apply an object recognition algorithm to a sensor fusion image to recognize a surrounding object, and set a bounding box for the recognized surrounding object area as described above. The object recognition unit 320 may track the second location information targeting an area where a bounding box is set. Specifically, the object recognizing unit 320 extracts continuous previous image frames and current image frames from sensor fusion images, compares the two image frames, and calculates continuous location information reflecting real-time location changes of surrounding objects, thereby calculating the second continuous location information. Location information can be tracked.

In addition, the object recognizing unit 320 may track second location information of a surrounding object using image data taken by the camera 312 as well as the sensor fusion image. For example, the object recognizing unit 320 extracts the previous image frame and the current image frame consecutively of the received image data, and tracks the second location information by targeting a bounding box of the surrounding object area of the two image frames. can Specifically, since bounding box information including location information and size information on an image is mapped to the bounding box, second location information is obtained by comparing successive image frames to calculate location information reflecting real-time location changes of surrounding objects. can track.

The object recognizing unit 320 may calculate a cost function using the center point of the surrounding object based on the estimated first location information and the second location information, and calculate the location information of the surrounding object accordingly. For example, location information of surrounding objects may be calculated by comparing a first cost function calculated based on the first location information and a second cost function calculated based on the second location information and selecting an optimal cost function. there is.

In one embodiment, the first cost function may be calculated as follows. The object recognizer 320 may calculate the first cost function by summing the vertical virtual line perpendicular to the horizontal central point of the surrounding object included in the first location information and the horizontal distance of each measurement value of the clustered area.

In another embodiment, the second cost function may be calculated as: The object recognizing unit 320 calculates a second cost function by summing horizontal distances of a plurality of measured values based on a virtual line corresponding to the heading direction of surrounding objects passing through the center point of the bounding box included in the second location information. can be calculated The cost function may be an indicator of how many measurement values are concentrated on the basis of a vertical imaginary line.

The object recognizing unit 320 may compare the first cost function and the second cost function, select a surrounding object having a minimum cost function value, and calculate location information of the corresponding surrounding object.

In the above, it has been described that the object recognition unit 320 calculates the location information of surrounding objects, but is not limited thereto. In another embodiment, a processor (not shown) of the sensing unit 310 may generate a sensor fusion image of a surrounding object and calculate location information of the surrounding object.

When there are a plurality of sensing units 310, each data received from each sensing unit 310 may include the same surrounding object. and can be counted. In addition, when the object recognizing unit 320 recognizes an object, it recognizes not only vehicles or pedestrians constituting traffic or floating population but also floating objects including object objects, so in order to generate meaningful information, the object determining unit 330 It is necessary to determine the passing object among the surrounding objects recognized by the object recognition unit 320.

5A and 5B are exemplary diagrams for explaining a method of determining a passing object according to an exemplary embodiment.

Referring to FIG. 5A , the traffic object information generating system may constitute a part of the building 500 or may be installed in the building 500 . In addition, the sensing unit, object recognition unit, object determination unit, information generation unit, and display unit, which are each component of the traffic object information generation system, may be mounted in different parts of the building 500 and connected to each other to operate, but are limited thereto. it is not going to be

The object determination unit may determine whether or not one or more neighboring objects recognized by the object recognition unit are repeatedly counted.

In one embodiment, the sensing unit may include a first sensing unit 501 and a second sensing unit 502 attached to different surfaces of the building 500 . The object recognizing unit may recognize the first surrounding object 511, the second surrounding object 512, and the third surrounding object 513 as surrounding objects based on the plurality of data received from the first sensing unit 501. . The object recognizer generates a fourth surrounding object 513, a fifth surrounding object 514, a sixth surrounding object 515, and a seventh surrounding object 516 based on the plurality of data received from the second sensing unit 502. can be recognized as a surrounding object.

The object determination unit may receive information on the first to seventh neighboring objects 511 to 516 from the object recognition unit to determine whether or not to count redundantly.

In an embodiment, the object determination unit may obtain information about a predetermined area 520 where the imaging areas of each sensing unit overlap through installation coordinates and a photographing angle of the first sensing unit and the second sensing unit. The object determination unit includes a third peripheral object 513 including coordinate information in a predetermined area 520 among a plurality of data received from the first sensing unit and a predetermined area 520 among a plurality of data received from the second sensing unit. ) may receive information about the fourth surrounding object 513 including coordinate information. The object determination unit may calculate similarities between the third and fourth surrounding objects 513 and 514 to determine whether the two surrounding objects are the same object. A method of calculating the similarity of a plurality of objects may be as described above with reference to FIG. 4 .

If the calculated similarity is greater than or equal to the threshold value, the object determination unit may determine that the counting has been duplicated, and determine one of the third and fourth surrounding objects 513 and 514 as a passing object. In one embodiment, the object determining unit may determine a neighboring object containing more information about the object among the third neighboring object 513 and the fourth neighboring object 514 as a traffic object, but among the duplicate counted neighboring objects The criterion for determining one as a traffic object is not limited thereto.

In the above-described embodiment, the traffic object information system or the sensing unit is described as being mounted on a building, but is not limited thereto and may be mounted on all types of real estate including buildings.

Information about objects includes object type information and object attribute information. Here, the object type information is index information indicating the type of object, and is composed of a group, which is a large range, and a class, which is a detailed range. And, the object attribute information represents attribute information on the current state of the object, and includes motion information, rotation information, traffic information, color information, and visibility information.

Classes included in the object type information may include object objects such as traffic lights, signs, and fountains, vehicle objects such as cars, trucks, and buses, and pedestrian objects.

Information included in object property information may include Action, Rotate, Traffic info, color, and visibility information. Action information expresses motion information of an object. In the case of a vehicle object, stop, parking, and movement are used. In the case of a pedestrian, movement, stop, and unknown are used. can be determined Rotate information expresses rotation information of an object and can be defined as front, back, horizontal, vertical, and side. Traffic info means the traffic information of an object, and can be defined as directions, cautions, regulations, auxiliary signs, etc. of traffic signs. Color means the color information of an object and can express the color of an object, the color of traffic lights and traffic signs.

Referring to FIG. 5B , the traffic object information generation system may constitute a part of the vehicle 530 or may be mounted on the vehicle 530 . In addition, the sensing unit, object recognition unit, object determination unit, information generation unit, and display unit, which are each component of the transit object information generation system, may be mounted on different parts of the vehicle 530 and connected to each other to operate, but are limited thereto. it is not going to be

In one embodiment, the sensing unit may include a first sensing unit 531 and a second sensing unit 532 attached to different surfaces of the vehicle 530 . Since the vehicle 530 can move with speed unlike a building, information on the surrounding objects 517 and 518 can be configured based on the real-time speed of the vehicle.

A process of recognizing a surrounding object and determining a passing object through a sensing unit mounted in a vehicle is the same as described above with reference to FIG. 5A.

The object determination unit may receive a plurality of measurement values from the radar of the sensing unit to calculate the speed of the surrounding object. Referring to FIG. 5A , the object determination unit may receive a plurality of measurement values from radars of the sensing units 501 and 502 to calculate the speed of the surrounding objects 511 to 516 . Referring to FIG. 5B , the object determination unit may receive a plurality of measurement values from radars of the sensing units 531 and 532 to calculate the speed of the surrounding objects 517 and 518 .

The radar may determine state information of an object through a plurality of measurement values, an antenna, a transmitting/receiving terminal, and a signal processing terminal. For example, a radar may detect distance, angle, and speed of each object using a transmission antenna and a plurality of reception antennas. In addition, the radar may directly obtain speed information of objects using Doppler frequencies reflected from the objects.

As shown in FIG. 5A, when the sensing units 501 and 502 are attached to or mounted on a building 500, etc., the absolute speed can be calculated by extracting Doppler components of the surrounding objects 511 to 516 from a plurality of measured values. 5B, when the sensing units 531 and 532 are attached to or mounted on the vehicle 530, the relative speed is calculated by extracting the Doppler component of the surrounding objects 517 and 518, and the real-time speed of the vehicle 530 , the absolute speed can be finally calculated.

The object determination unit determines whether the surrounding object moves within a predetermined time based on the speed of the surrounding object, and determines the surrounding object 511 to 516 as one of the object objects 515 and 516 and the traffic objects 511 to 514. can

In an embodiment, the object determining unit may determine the surrounding object as the object object when it is determined that the surrounding object does not move within a predetermined time. For example, if the surrounding object is a vehicle, it may not temporarily move due to a stop signal, so the object determining unit may determine the surrounding object as an object object only when the surrounding object does not move for a predetermined threshold time or longer. Conversely, the object determining unit may determine a passing object when the surrounding object moves within a predetermined threshold time.

The object determination unit may classify the surrounding object determined as a traffic object into a vehicle or a pedestrian.

In one embodiment, the object determination unit uses a plurality of images or video data received from the sensing unit as an input frame and uses a convolutional neural network (CNN) to extract unique features of each passing object included in the image or video. there is. This feature may be a part of object property information, and may be used to obtain object type information by classifying a passing object at a specific location in a frame. Alternatively, the object determining unit may classify the passing object into a vehicle or a pedestrian based on the size information of the bounding box received from the object recognizing unit, or may classify the passing object into a vehicle or a pedestrian based on the calculated speed of the surrounding object. The method of classifying the object determination unit as a vehicle or a pedestrian is not limited to the above description, and may be classified as a combination of two or more methods.

In the above, the speed of the surrounding object has been described as being calculated by the object determination unit, but the sensing unit, the object recognition unit, or a separate module may calculate the speed, but is not limited thereto.

6A and 6B are exemplary diagrams for explaining a method of determining a detection range of a sensing unit.

Referring to FIG. 6A , the object determination unit may consider the distance between the display unit and the passing object in order to determine the detection range of the sensing unit.

As described above with reference to FIGS. 3 to 5B , the detection range of the sensing unit is not only an area included in a plurality of images or video data acquired by a camera and an area in which a plurality of measurement values obtained by a sensor exist, but also a passing object can detect a display unit It may be determined as a limited area considering a view point or field of view.

으로 정의할 수 있으나, 위 면적에 제한되는 것은 아니다.In one embodiment, the object determination unit includes at least 1/2 of the area of the display unit 610 in the viewing range 640 of the transit object 620 with respect to the display unit 610 mounted in a part of the building The minimum distance between the building and the traffic object 620

It can be defined as, but is not limited to the above area.

로 정의할 수 있다. 또는, 객체결정부는 거리에 따른 통행객체(630)의 이미지 또는 영상에 대한 평균 집중도 또는 시력이 미치는 범위에 기초하여 기 설정된 상한값에 따라

를 정의할 수 있다.In addition, the object determining unit determines the maximum distance between the building and the passing object 630, in which the entire area of the display unit 610 is included in the viewing range 650 of the passing object 630.

can be defined as Alternatively, the object determination unit according to the upper limit set in advance based on the average concentration on the image or video of the passing object 630 according to the distance or the range of visual acuity

can define

Meanwhile, the viewing ranges 640 and 650 may be set differently according to the type of passing object. In one embodiment, when the type of the transit object corresponds to a pedestrian, it may be determined based on the national average height. Alternatively, when the type of traffic object corresponds to a vehicle, it may be determined based on the average overall height of a sedan or SUV.

및

에 기초하여 센싱부의 탐지범위를 결정할 수 있다.Referring to Figure 6b, the object determination unit

and

It is possible to determine the detection range of the sensing unit based on.

,

)에 기초하여 결정된 센싱부의 탐지범위에 포함되는 객체만 통행객체로 결정할 수 있다. 예를 들어, 객체(690)는 디스플레이부(660)와의 거리가

보다 작고, 객체(670)는 통행객체의 시야범위를 고려했을 때 센싱부의 탐지범위에 포함되지 않을 수 있다. 반면, 객체(680)은 디스플레이부(660)와의 거리가

이상

이하의 범위에 속하며 통행객체의 시야범위를 고려했을 때 센싱부의 탐지범위에 포함될 수 있다.Distance of the object determination unit to the display unit 660 or the building (

,

), only objects included in the detection range of the sensing unit determined on the basis of may be determined as transit objects. For example, the distance between the object 690 and the display unit 660 is

It is smaller and the object 670 may not be included in the detection range of the sensing unit when considering the field of view of the passing object. On the other hand, the distance between the object 680 and the display unit 660 is

more

It belongs to the following range and can be included in the detection range of the sensing unit when considering the field of view of the passing object.

However, this is limited to the description of the detection range of the sensing unit attached to the same side of the building as the display unit 660, and the object 670 may be included in the detection range of the display unit 660 and the sensing unit attached to the other side of the building. there is.

Returning again, the object determination unit may determine the objects 670 and 690 not included in the detection range of the sensing unit as transit objects, and the object 680 included in the detection range of the sensing unit as transit objects.

In this way, by determining the detection range based on the time of the traveling object, it is possible to determine the traveling object and generate the traveling object information only in a limited area instead of all areas included in the data acquired by the sensing unit. Therefore, reasonable data collection is possible and advantageous effects can be derived for the processor's arithmetic processing.

In the above, it has been described that the object determination unit determines the detection range of the sensing unit, but the sensing unit, the object recognition unit, the information generation unit, or a separate module may determine the detection range, but is not limited thereto.

7 is an exemplary diagram for explaining a process of de-identifying a travel object and generating a unique ID in order to generate travel object information according to an embodiment.

A plurality of images and video data photographed by a camera of the sensing unit includes a face of a pedestrian or a license plate of a vehicle, and thus personal information is exposed as it is. Therefore, in order to protect personal information, passing objects such as pedestrians and vehicles must be screened so that third parties cannot identify them.

Accordingly, referring to FIG. 7 , the information generating unit may de-identify (blurring) the area within the bounding box for the traveling object in which the bounding boxes 711 and 712 are set. In one embodiment, the information generating unit may manipulate pixel values of an area inside the bounding boxes 711 and 712 with respect to a plurality of images or an arbitrary image frame of video data. For example, de-identification may be performed by applying an algorithm that changes an arbitrary pixel to an average color value of adjacent pixels within a predetermined radius.

In another embodiment, the information generating unit may apply de-identification differently according to the type of traffic object. When the resolution of the original image increases in manipulating the pixel value of the image, the amount of data calculation and memory usage may increase. Accordingly, the information generating unit applies an algorithm that changes the average color value of neighboring pixels within a larger radius to a random pixel than that of the vehicle 712 in the case of the pedestrian 711, who is more concerned about the exposure of personal information. can

The information generating unit may assign a unique ID to each passage object corresponding to the bounding boxes 711 and 712 .

The unique ID is identification information for classifying traffic objects, and may be generated based on at least one of bounding box information, traffic object type information, and traffic object attribute information of an arbitrary traffic object. For example, since the bounding box information may include position information and size information on an image of an object, when changes in position information and size information of the bounding box are continuous within consecutive image frames, the corresponding bounding box is corresponded to. A specific unique ID can be assigned to a travel object.

In another example, the object type information is composed of a large scope group and a detailed scope class, and the object property information may include motion information, rotation information, traffic information, color information, visibility information, etc., so that each successive image frame When the amount of change in motion information or color information extracted within the bounding box is less than or equal to the threshold and the object type information is the same, a specific unique ID may be assigned to a transit object corresponding to the corresponding bounding box.

In one embodiment, by assigning ID01 to a pedestrian object and assigning ID02 to a vehicle object, information on the pedestrian object and the vehicle object may be matched to ID01 and ID02, respectively. Information on objects may include object type information and object property information, and descriptions on object type information and object property information are as described above with reference to FIG. 5A.

The information generating unit may store the unique ID and information about the object for a certain period of time without deleting them even after the passing object to which the unique ID is assigned temporarily disappears from the image or video obtained from the sensing unit.

For example, when a passing object disappears from an image or image frame, it is not possible to obtain the information required for forming and tracking a bounding box and the amount of change in information, but the object recognition unit or information generator accumulates the tracking results and returns the bounding box. Passing object attribute information in the box may be stored for a preset time.

In one embodiment, the object recognition unit or the information generation unit stores only the information about the corresponding traffic object for a predetermined first time when the specific traffic object disappears within the image frame, and other traffic objects that do not disappear within the image frame. Some of the related information may be deleted after a preset second time period has elapsed. The first time and the second time may change based on processor speed or memory capacity.

In addition, the information generator may assign an existing unique ID to the corresponding transit object when the corresponding transit object reappears in the image or video within a predetermined time, and continuously store information on the corresponding transit object.

For example, if it is determined that a specific travel object that has disappeared within the image frame reappears within a first time based on the stored travel object attribute information, the information generating unit may assign an existing unique ID to the corresponding travel object again. A method of determining that a specific transit object reappears within the first time may be the same as the method of determining whether the plurality of objects described above are the same object in FIG. 5A .

Returning to FIG. 3 again, the information generating unit 340 may track the passing object based on the bounding box.

As described above, the object recognizing unit 320 or the object determining unit 330 sets a bounding box for each object included in an image frame of a plurality of images or video data, and identifies the corresponding object through real-time object recognition result update. tracking information can be obtained. The information generating unit 340 may calculate the trajectory of the passing object by accumulating tracking information on the passing object.

In one embodiment, when the system 300 is mounted on a building, information about how long a passing object has stayed around the building, what route it has traveled, and the like may be included. Alternatively, when the system 300 is mounted on a vehicle, information about how much the system 300 matches the driving route of the vehicle may be included. The information generating unit 340 may generate traffic object information using the calculated trajectory of the traffic object.

According to the traffic object information generated by the information generating unit 340, information on the floating population or traffic volume around a building or vehicle in which the system 300 is mounted may be included. Specifically, the number of passing objects, tracking information and trajectory information generated by accumulating it, speed information, time exposed to the sensing unit, distance to the sensing unit, and disappearing from a plurality of images or video data acquired by the sensing unit and then reappearing Comprehensive information in which the number of appearances and the above-described information is matched to each unique ID may be included. Since the traffic object information generated in this way is information that avoids duplicate counting, it can provide results with higher reliability than information according to the prior art. In addition, as information reflecting the characteristics of each object rather than information on universal floating population or traffic volume, a new interpretation or precise valuation of the area around the system of the present invention can be made.

The information generating unit 340 may derive a score for an area around the sensing unit.

The score is a score derived using traffic object information generated from a plurality of data obtained by the sensing unit 310, and may be used as an evaluation index for an area around the sensing unit 310. In addition, the score can facilitate interpretation of the above-described passing object information.

The information generating unit 340 may derive a score based on the number of passing objects, the type of passing objects, and the trajectory of the passing objects in the area around the sensing unit.

In one embodiment, when the system 300 is installed in a specific building, the information generating unit 340 assigns a weight to each unique ID based on at least one of the type of the passing object and the trajectory of the passing object, thereby determining the area around the sensing unit. A score can be derived for For example, the information generating unit 340 may derive a score for the surrounding area by assigning a higher weight to a unique ID of a vehicle than a unique ID of a pedestrian. Alternatively, the information generating unit 340 may derive a score for the area around the sensing unit by assigning a higher weight to a unique ID that has stayed in the area around the building for a long time through the trajectory of the passing object.

In another embodiment, when the system 300 is mounted on a specific vehicle, the information generating unit 340 assigns a weight to each unique ID based on at least one of the type of the passing object and the trajectory of the passing object, thereby determining the area around the sensing unit. A score can be derived for The information generating unit 340 may derive a score for the area around the sensing unit by assigning a higher weight to the unique ID exposed to the sensing unit 310 for a long time in accordance with the driving path of the vehicle through the trajectory of the passing object. .

For example, when the system 300 is installed in a specific building located in Gangnam Station or a vehicle driving around Gangnam Station, the information generating unit 340 derives a score for a passing object in the area around Gangnam Station, narrowly A score related to a specific building or the vehicle driving section, and a score related to Gangnam Station in a broad sense may be derived.

In another example, when the system 300 is mounted on a specific building located in Yangjae Station or a vehicle driving around Yangjae Station, a score for the specific building or vehicle driving section in a narrow sense, and a score for Yangjae Station in a broad sense may be derived. can

Finally, as the scores for each area in which each system 300 is mounted are derived, it is possible to compare and analyze scores for various areas.

The sensing unit 310 may include a plurality of sensing units and derive a score for an area around each sensing unit.

In one embodiment, referring to FIG. 5A , the sensing unit may include a first sensing unit 501 and a second sensing unit 502, and the first sensing unit 501 and the second sensing unit 502 may include It can be mounted on different sides of the building 500. The information generator may derive a first score for an area around the first sensing unit 501 and derive a second score for an area around the second sensing unit 502 . Since the floating population and traffic volume or object type information of the surrounding area may be different for each sensing unit, the first score and the second score may be different from each other.

Similarly, referring to FIG. 5B , the sensing unit may include a first sensing unit 531 and a second sensing unit 532 , and the first sensing unit 531 and the second sensing unit 532 may include a vehicle 530 ) can be mounted on different sides of the As described above, the information generator may derive the first score and the second score.

In one embodiment, according to the above description, the information generating unit 340 may derive a score according to Equations 1 and 2 below.

는 본 발명에서 도출하고자 하는 스코어를 의미하고,

은 현재 시점에서 복수의 데이터에 포함된 통행객체의 수를 의미한다.In Equation 1,

Means the score to be derived in the present invention,

means the number of transit objects included in the plurality of data at the current point in time.

은 n번째 통행객체의 종류에 따른 수를 의미한다. 예를 들어, 보행자는 1, 차량은 2일 수 있다. 기 설정된 수이거나, 임의로 설정되는 수일 수 있다.

means the number according to the type of the n-th traffic object. For example, a pedestrian may be 1 and a vehicle may be 2. It may be a preset number or an arbitrarily set number.

은 n번째 통행객체의 궤적 정보에 따른 수를 의미한다. 예를 들어, 수학식 2를 참조하면,

은 n번째 통행객체가 센싱부에 노출된 시간(

), n번째 통행객체의 속도(

), n번째 통행객체의 센싱부(310)와의 거리(

) 및 n번째 통행객체가 센싱부가 획득한 복수의 이미지 또는 영상 데이터에서 사라졌다가 다시 나타난 횟수(

)에 관한 함수일 수 있다.

denotes the number according to the trajectory information of the nth travel object. For example, referring to Equation 2,

is the time when the nth traffic object is exposed to the sensing unit (

), the speed of the nth traffic object (

), the distance from the sensing unit 310 of the nth traffic object (

) and the number of times the nth transit object disappeared and reappeared in a plurality of images or video data acquired by the sensing unit (

) may be a function about.

)는 통행객체의 수(

)가 증가할수록, 통행객체의 종류(

)가 보행자보다는 차량일수록, 통행객체가 센싱부에 노출된 시간(

)이 길수록, 통행객체의 속도(

)가 느릴수록, 통행객체의 센싱부(310)와의 거리(

)가 가까울수록, 사라졌다가 다시 나타난 횟수(

)가 많아질수록 높은 점수로써 도출될 수 있다.In one embodiment, the score (

) is the number of traffic objects (

) increases, the type of traffic object (

) is a vehicle rather than a pedestrian, the time the passing object is exposed to the sensing unit (

) is longer, the speed of the passing object (

) is slower, the distance from the sensing unit 310 of the passing object (

) is closer, the number of disappearances and reappearances (

) can be derived as a higher score.

은 n번째 통행객체에 부여되는 가중치일 수 있다. 특정 통행객체의 고유의 특성 또는 복수의 통행객체의 종류 또는 궤적에 의해 센싱부 주변 영역의 가치가 변동될 수 있으므로 정보생성부는 스코어(

)를 도출함에 있어 각 통행객체에 가중치를 부여할 수 있다. 상술한 센싱부 주변 영역의 가치는 재산적 가치, 경제적 가치 이외의 다양한 관점에서의 가치를 의미할 수 있다.

may be a weight given to the n-th traffic object. Since the value of the area around the sensing unit may change due to the unique characteristics of a specific traffic object or the type or trajectory of a plurality of traffic objects, the information generator score (

), a weight can be assigned to each traffic object. The above-described value of the area around the sensing unit may mean value from various viewpoints other than property value and economic value.

)는 다른 통행객체보다 작을 수 있다. 사람이 많이 모여있는 경우 후술할 디스플레이부가 송출하는 이미지 또는 영상에 대한 집중도가 낮을 수 있기 때문이다.In one embodiment, when a plurality of traffic objects are dense, a weight given to a unique ID of each corresponding traffic object (

) may be smaller than other traffic objects. This is because when a large number of people are gathered, the concentration of an image or video transmitted by a display unit, which will be described later, may be low.

) 또는 궤적(

)에 따라 특정 고유 ID에 더 높거나 낮은 가중치(

)가 부여될 수도 있다. 예를 들어, 궤적(

)에 포함되는 정보인 통행객체의 속도(

)가 증가할수록 해당 통행객체에 부여되는 가중치(

)는 낮아질 수 있다. 마찬가지로, 디스플레이부가 송출하는 이미지 또는 영상에 대한 집중도가 낮을 수 있기 때문이다.In another embodiment, as described above, the type of traffic object (

) or trajectory (

Depending on ), certain unique IDs have higher or lower weights (

) may be given. For example, the trajectory (

), which is the information included in the speed of the traveling object (

) increases, the weight given to the corresponding traffic object (

) can be lowered. Similarly, this is because the degree of concentration on the image or video transmitted by the display unit may be low.

The formula for deriving the score of the present invention is not limited to Equation 1 above.

In another embodiment, when the system 300 is mounted on a specific vehicle, the information generating unit 340 assigns a weight to each unique ID based on at least one of the type of the passing object and the trajectory of the passing object, thereby determining the area around the sensing unit. A score can be derived for The information generating unit 340 may assign a higher weight to a unique ID exposed to the sensing unit 310 for a long time in accordance with the driving path of the vehicle through the trajectory of the passing object.

On the other hand, the information generator 340 provides a value capable of calculating the value of the area where the real estate equipped with each sensing unit is located or the area viewed from different sides of the real estate according to the scores for the surroundings of each sensing unit. can

For example, when the first side of a specific property faces the roadside, and the second side, which is different from the first side of the property, faces an alleyway, the score of the area around the sensing unit generally facing the roadside is higher. It can be expected to be high, but as a result of deriving the score through accurate traffic object recognition according to the present invention, the score for the area around the sensing unit attached to the second side facing the alley is attached to the first side facing the roadside. It may be higher than the score for the area around the sensing unit. In this case, insight can be provided to real estate market participants to help in decision making, and real estate valuation information can be provided to outdoor advertising operators to help generate profits.

In the above-described embodiment, different aspects of a specific real estate are described, but it is not limited thereto, and it is obvious that it can be used as insight or value evaluation data related to the real estate itself.

The information generating unit may transmit a predetermined image or video to the display unit based on the first score and the second score.

5A, the display unit may include a first display unit 503 and a second display unit 504, and each display unit may be mounted on one side of the same building as each sensing unit. Similarly, in FIG. 5B , the display unit may include a first display unit (not shown) and a second display unit (not shown), and each display unit may be mounted on the same side of the vehicle as each sensing unit.

Different images or videos may be transmitted to the display unit mounted on the same surface as each sensing unit according to the score for the vicinity of each sensing unit. For example, the image or video may be an advertisement image or advertisement video.

8 is a flowchart illustrating a method of generating transit object information using a sensing unit according to an exemplary embodiment.

Since the method of generating traffic object information shown in FIG. 8 is related to the embodiments described in the drawings described above, the contents described in the drawings will be applied to FIG. 8 even if omitted below. can

Referring to FIG. 8 , in step 810, the system may recognize one or more surrounding objects from a plurality of data acquired from the sensing unit.

The sensing unit may be a plurality of sensing units including a first sensing unit and a second sensing unit.

The sensing unit may include a camera and a radar, and the plurality of data may include a plurality of images or video data obtained from the camera and a plurality of measurement values obtained from the radar.

Neighboring objects may include object objects and traffic objects, and traffic objects may include vehicles and pedestrians.

In one embodiment, the system estimates the first location information of the surrounding object using a plurality of measurement values, and estimates the second location information of the surrounding object using a plurality of data to obtain the first location information and the second location information. Based on the location information of the surrounding object can be calculated.

In one embodiment, the system may calculate the velocity of a surrounding object from a plurality of data.

In one embodiment, the system may set bounding boxes for surrounding objects.

Then, in step 820, the system may determine one or more transit objects corresponding to at least a part of the one or more neighboring objects based on whether the one or more neighboring objects are repeatedly counted.

In one embodiment, the system determines whether a first surrounding object recognized based on data received from the first sensing unit and a second surrounding object recognized based on data received from the second sensing unit are the same object; , Based on this, it is possible to determine one of the first and second surrounding objects as a traffic object.

In one embodiment, the system determines the surrounding object as an object object when it is determined that the surrounding object does not move within a predetermined time based on the speed of the surrounding object calculated from a plurality of data, and the surrounding object moves within the predetermined time If it is determined to do so, the surrounding object may be determined as the transit object. Alternatively, the system may classify the traffic object as a vehicle or a pedestrian.

Then, in step 830, the system may generate travel object information including a unique ID of each travel object.

The unique ID is identification information for classifying a traveling object, and may be given based on at least one of bounding box information, travel object type information, and travel object attribute information.

In one embodiment, the system may de-identify traffic objects for which a bounding box is set, and assign a unique ID to each traffic object.

In one embodiment, the system may store information about the passing object for a predetermined time in response to determining that the passing object to which the unique ID has been assigned has disappeared from a plurality of images or video data.

In one embodiment, it is possible to determine whether the transit object is the same object as other transit objects appearing in a plurality of images or video data within a predetermined time based on information about the transit object.

In one embodiment, an existing unique ID may be assigned to a traffic object in response to being determined to be the same object as other traffic objects.

The information about the traffic object may include at least one of bounding box information, traffic object type information, and traffic object attribute information.

In one embodiment, the system may track the transit object based on the bounding box and calculate the trajectory of the transit object by accumulating the tracking results.

In one embodiment, the system may derive a score for an area around the sensing unit.

The score may be derived by assigning a weight to each unique ID based on at least one of the type of the passing object and the trajectory of the passing object.

In one embodiment, the system derives a first score for an area surrounding a first sensing unit, derives a second score for an area surrounding a second sensing unit, and displays one or more displays based on the first score and the second score. A predetermined image or video can be transmitted to the unit.

Embodiments according to the present invention may be implemented in the form of a computer program that can be executed on a computer through various components, and such a computer program may be recorded on a computer-readable medium. At this time, the medium is a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. An example of a computer program may include not only machine language code generated by a compiler but also high-level language code that can be executed by a computer using an interpreter or the like.

According to one embodiment, the method according to various embodiments of the present disclosure 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 is distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)), or through an application store (eg Play Store™) or between two user devices. It can be distributed (e.g., downloaded or uploaded) directly or online. In the case of online distribution, at least part of the computer program product may be temporarily stored or temporarily created in a device-readable storage medium such as a manufacturer's server, an application store server, or a relay server's memory.

The steps constituting the method according to the present invention may be performed in any suitable order unless an order is explicitly stated or stated to the contrary. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is simply to explain the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms unless limited by the claims. it is not going to be In addition, those skilled in the art can appreciate that various modifications, combinations and changes can be made according to design conditions and factors within the scope of the appended claims or equivalents thereof.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments and should not be determined, and all scopes equivalent to or equivalently changed from the claims as well as the claims described below are within the scope of the spirit of the present invention. will be said to belong to

Claims (12)

In the method of generating traffic object information,
Recognizing one or more surrounding objects from a plurality of data obtained from the sensing unit (including the first sensing unit and the second sensing unit);
determining one or more transit objects corresponding to at least a part of the one or more neighboring objects based on whether the one or more neighboring objects are repeatedly counted;
setting a bounding box for the traffic object; and
generating traffic object information including a unique ID of each of the traffic objects;
including,
The step of generating the traffic object information,
tracking the transit object based on the bounding box;
calculating a trajectory of the passing object by accumulating the tracking result;
deriving a first score for an area around the first sensing unit and a second score for an area around the second sensing unit based on at least one of a type of a passing object and a trajectory of the passing object; and
transmitting a predetermined image or video to one or more display units based on the first score and the second score;
Including, method. According to claim 1,
The plurality of data includes a plurality of images or video data obtained from a camera of the sensing unit and a plurality of measurement values obtained from a radar of the sensing unit,
Recognizing the surrounding object,
estimating first location information of the surrounding object using the plurality of measurement values;
estimating second location information of the surrounding object using the plurality of data; and
calculating location information of the surrounding object based on the first location information and the second location information;
Further comprising a method. According to claim 1,
The step of determining the traffic object is,
determining whether a first surrounding object recognized based on data received from the first sensing unit and a second surrounding object recognized based on data received from the second sensing unit are the same object; and
determining at least one of the first surrounding object and the second surrounding object as the transit object based on the determination;
Including, method. According to claim 1,
The method,
calculating the velocity of the surrounding object;
Including more,
The step of determining the traffic object is,
determining the surrounding object as an object object when it is determined from the speed that the surrounding object does not move within a predetermined time, and determining the surrounding object as a traffic object when it is determined that the surrounding object moves within a predetermined time ; and
classifying the traffic object as a vehicle or a pedestrian;
Including, method. According to claim 1,
The method,
setting a bounding box for the traffic object;
Including more,
The step of generating the traffic object information,
de-identifying a traffic object included in the bounding box; and
assigning a unique ID to each travel object;
Further comprising a method. According to claim 5,
The unique ID is identification information for distinguishing the traffic object,
The unique ID may be assigned based on at least one of bounding box information, traffic object type information, and traffic object attribute information. According to claim 5,
The step of assigning the unique ID is,
storing information about the passing object for a predetermined time in response to determining that the passing object to which the unique ID has been assigned has disappeared from the plurality of data;
determining whether the transit object is the same object as another transit object appearing in the plurality of data within the predetermined time period based on the information about the transit object; and
assigning an existing unique ID to the transit object in response to determining that the object is the same as the other transit object;
Including,
Wherein the information about the traffic object includes at least one of bounding box information, traffic object type information, and traffic object attribute information. According to claim 5,
The step of generating the traffic object information,
tracking the transit object based on the bounding box;
calculating a trajectory of the passing object by accumulating the tracking result;
Including, method. According to claim 8,
The first score and the second score,
It is derived by assigning a weight to each unique ID based on at least one of a type of a traffic object and a trajectory of the traffic object. delete In the traffic object information generating system,
a memory in which at least one program is stored; and
Including at least one processor that operates according to the at least one program,
The at least one processor,
recognizing one or more surrounding objects from a plurality of data obtained from the sensing unit -including the first sensing unit and the second sensing unit;
Determine one or more traffic objects corresponding to at least a part of the one or more neighboring objects based on whether the one or more neighboring objects are repeatedly counted;
Set a bounding box for the traffic object,
Generating traffic object information including a unique ID of each of the traffic objects,
Generating the traffic object information,
Based on the bounding box, tracking the traffic object,
Calculating the trajectory of the traffic object by accumulating the tracking result;
Deriving a first score for an area around the first sensing unit and a second score for an area around the second sensing unit based on at least one of a type of a passing object and a trajectory of the passing object;
Based on the first score and the second score, a predetermined image or video is transmitted to one or more display units. A computer-readable recording medium recording a program for executing the method of claim 1 on a computer.

Images