KR102169910B1 - A vehicle driving behavior analysis system using images by uav - Google Patents

Abstract

The present invention is a vehicle driving behavior analysis capable of providing a microscopic and empirical method capable of clearly diagnosing a problem occurrence point and a cause of a traffic problem occurring on a road by using aerial images of an unmanned aerial vehicle. It's about the system.

Description

Vehicle driving behavior analysis system using unmanned aerial vehicle image {A VEHICLE DRIVING BEHAVIOR ANALYSIS SYSTEM USING IMAGES BY UAV}

The present invention relates to a technology capable of analyzing the driving behavior of a vehicle through an image captured by an unmanned aerial vehicle. More specifically, the driving of a vehicle running on a road by analyzing a road image captured by an unmanned aerial vehicle It is related to technology that can analyze behavior and analyze the cause of traffic problems and improve based on the analyzed results.

Compared to the current limited road capacity, traffic demand is concentrated and continuously increased. Due to this, various traffic problems are continuously occurring, and in order to solve such traffic problems, traffic data collected from various vehicle detection devices installed on the road are used for traffic analysis.

In general, a vehicle detection system (VDS) is installed on the main line of a highway at approximately 1~2km intervals, and traffic data such as the number of vehicles passing through the installation point and passing speed are collected. In addition, a high-pass traffic information system based on DSRC (Dedicated Short Range Communication) that collects travel time based on the wireless communication time between the road-side antenna installed at intervals of 3~5km on the main line of the highway and the high-pass terminal installed in the vehicle was installed. Therefore, it is collecting vehicle traffic (flow) travel time data.

As described above, the existing traffic analysis method is a traffic information collection system mainly installed on the main line of a highway (e.g., a vehicle detection system (VDS), a travel time collection system based on DSRC (Dedicated Short Range Communication), etc.) It was a method of estimating traffic conditions on the road by spatio-temporal aggregation of the data collected through the process, or analyzing the cause and solving traffic problems based on theoretical models (including simulation).

However, this traffic data is collected by spatiotemporal aggregation or averaging data of the number of vehicles passing through the point at the point where the detection equipment is passing, rather than the driving behavior of individual vehicles. Since it relies on traffic theory and model rather than phosphorus analysis, there is a limitation that it cannot but be approached by analysis of causes by estimation, and there is a limitation that microscopic traffic analysis that analyzes the driving behavior of individual vehicles is virtually impossible.

In addition, in the existing vehicle detection system, it analyzes the driving behavior of individual vehicles in various sections, such as the confluence/classification section of the highway IC (Interchange)/JCT (Junction), the cross section, the end (up/down) slope change section, and the construction section. Empirical and microscopic traffic analysis based on data is very difficult.

Due to these limitations, since it is not clear problem solving even when solving traffic problems, there is a problem that not only a limitation occurs in improving traffic problems, but also the improvement effect decreases.

Therefore, in order to improve traffic problems, it is important to clarify and diagnose the exact problem occurrence point and cause through microscopic and empirical traffic analysis. Therefore, a technology that can analyze the empirical and clear traffic problem occurrence point and cause will be required. .

The present invention was created in view of the above circumstances, and an object to be reached in the present invention is to extract and analyze the driving behavior data of the vehicle through the analysis of the aerial image captured by the unmanned aerial vehicle. It is to provide a method to clearly and empirically diagnose the point of occurrence and cause of traffic problem factors.

A vehicle driving behavior analysis system using an unmanned aerial vehicle image for extracting and analyzing the driving behavior of a vehicle according to an embodiment of the present invention for achieving the above object is, by using an unmanned flight device, a lane in which the vehicle is traveling. For analyzing the driving behavior of the vehicle traveling on the road and the driving behavior of the vehicle in the lane based on the image input and output unit for photographing as an image and input and output of the captured image and the image output from the image input and output unit And an information setting unit, an extraction unit for extracting the driving behavior of the vehicle based on the driving behavior of the vehicle set by the information setting unit, and a storage unit for storing the driving behavior of the vehicle extracted from the extraction unit To do.

Specifically, the image input/output unit includes: an image photographing unit for capturing any one of the vehicle information and lane information as an image, an image input unit for inputting an image captured by the image capturing unit, and an image input to the image input unit It characterized in that it comprises an image correction unit for correcting the correction image for information analysis.

Specifically, the image capturing unit is a drone that photographs any one of information on the vehicle or lane information as an image at a fixed location.

Specifically, the information setting unit may include a lane setting unit for setting the type of the lane from the image input to the image input unit, and for setting a specific time for extracting the driving behavior of the vehicle from the image time taken by the image capturing unit. And a space setting unit for setting a space for extracting the driving behavior of the vehicle from among the images captured by the time setting unit and the image capturing unit.

Specifically, the time setting unit may set a derivation start time and a derivation end time based on a point in time at which a certain number of vehicles or more are operated on the lane.

Specifically, the time setting unit may set an extraction time unit for analyzing the driving behavior of the vehicle from the image captured by the image capturing unit.

In more detail, the space setting unit may set one of an area of interest among an area in which the vehicle travels and a lane of interest among an area in which the vehicle travels.

Specifically, the space setting unit may set an actual distance of a designated lane among lanes on which the vehicle travels.

Specifically, the image input/output unit includes vehicle type information of the specific individual vehicle driving the lane, the driving speed of the specific individual vehicle, information about the lane in which the specific individual vehicle travels, the location and number of lane changes of the specific individual vehicle, An object detection unit that detects any one of distance between the specific individual vehicle and other specific individual vehicle adjacent to the specific vehicle, and vehicle head time information, and an object calculation unit that calculates the driving behavior of the specific individual vehicle detected by the object detection unit. It features.

According to the vehicle driving behavior analysis system using the image of the unmanned aerial vehicle of the present invention, spatial constraints on the road section in which traffic problems occur, such as the main line of the highway, the confluence of IC (Interchange)/JCT (Junction), the classification unit, and the intersection Images can be taken without restrictions such as section, longitudinal (upward, downward) slope change section, construction section, etc., and vehicle driving behavior for the problem section can be extracted through analysis of the captured image.

In particular, since microscopic empirical traffic analysis based on the driving behavior of individual vehicles is performed, it is possible to diagnose problems clearly in the target road section, and by deriving an accurate improvement plan, the traffic improvement effect can be maximized.

1 is a diagram schematically showing a vehicle driving behavior analysis system according to an embodiment of the present invention.
2 is a block diagram showing a configuration of an image input/output unit according to an embodiment of the present invention.
3 is a block diagram illustrating a configuration of an information setting unit according to an embodiment of the present invention.
4 is a block diagram showing a configuration of an individual vehicle information setting unit according to an embodiment of the present invention.
5 is a view showing an embodiment in which a driving behavior and an analysis progress direction of a vehicle analyzed through a vehicle driving behavior analysis system using a drone according to an embodiment of the present invention are classified.

It should be noted that the technical terms used in the present specification are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present specification should be interpreted as generally understood by those of ordinary skill in the technical field to which the present invention belongs, unless otherwise defined in the present specification, and excessively comprehensive It should not be construed as a human meaning or an excessively reduced meaning. In addition, when a technical term used in the present specification is an incorrect technical term that does not accurately express the spirit of the present invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. In addition, general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted as an excessively reduced meaning.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of the reference numerals, and redundant descriptions thereof will be omitted. In addition, in describing the present invention, when it is determined that a detailed description of a related known technology may obscure the subject matter of the present invention, a detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present specification will be described with reference to the accompanying drawings.

1 is a diagram schematically showing a vehicle driving behavior analysis system according to an embodiment of the present invention, and FIG. 2 is a block diagram showing a configuration of an image input/output unit according to an embodiment of the present invention. 3 is a block diagram showing the configuration of an information setting unit according to an embodiment of the present invention.

As shown in the drawing, the vehicle driving behavior analysis system 10 using an unmanned aerial vehicle image to which the present invention is applied includes an image input/output unit 120, an information setting unit 140, an extraction unit 160, and a storage unit. It is comprised of 180.

The image input/output unit 120 may include an image capture unit 122, an image input unit 124, and an image correction unit 126.

Specifically, the image capturing unit 122 is a component for photographing a vehicle traveling on a lane or lane in the air. To this end, the image photographing unit 122 may use an unmanned aerial vehicle. Hereinafter, the unmanned aerial vehicle according to an embodiment of the present invention is described as an example of a drone as shown in FIG. 1. It goes without saying that it can be any one of the devices that can shoot.

The image capturing unit 122 may be equipped with a camera, a moving picture capturing device, etc. to take pictures while driving in a lane or lane. The image capturing unit 122 equipped with a photographing device may photograph a road and a vehicle traveling on the road at a fixed position. In this case, the image captured by the image capturing unit 122 may be a format such as AVI or MP4, and a high-resolution image of 4K (UHD level) or higher.

On the other hand, the image capture unit 122 formed of a drone can adjust the spatial range of roads in the image according to the flight altitude (eg, shooting height), and can shoot in various places regardless of the type, shape, or location of the target road. Therefore, there is an advantage that it is possible to extract the driving behavior of all individual vehicles through road image analysis.

The image input unit 124 is a component for inputting an image captured by the image capturing unit 122. In addition to the image, the image input unit 124 may store data in which a captured image is imaged.

The image correction unit 126 is a component that corrects an image to obtain various information from an image and an image input to the image input unit 124.

Specifically, the image correction unit 126 may correct a minute shake of an image captured by the input image capturing unit 122.

Through the image corrected by the image correction unit 126, detailed image information of the lane, image information in which vehicle colors are displayed differently according to the speed of the vehicle being driven, image information expressing the movement trajectory of the vehicle in a specific lane, and the vehicle being driven It is possible to obtain image information indicating the point where the change occurred in the lane.

The acquired information can become basic data that can analyze the driving behavior of the vehicle driving on the road, and the cause of the traffic problem can be analyzed and improved through the driving behavior of the vehicle analyzed through the acquired information. .

Meanwhile, the image captured and corrected by the image input/output unit 120 may set information necessary for outputting the driving behavior of the vehicle through the information setting unit 140.

To this end, the information setting unit 140 may be configured to include a lane setting unit 142, a time setting unit 144, and a space setting unit 146.

Specifically, the lane setting unit 142 may distinguish a lane on which the vehicle travels from an image photographed and corrected by the image input/output unit 120 and set information such as a type of the lane.

At this time, the classification of the lane means information on the classification of the lane on which the vehicle is traveling, that is, whether the vehicle is driving in which lane among lanes such as 1st, 2nd, and 3rd.

In addition, the type of lane is the type of road to which the lane belongs in the information necessary to derive the driving behavior of the vehicle. For example, a main line section of a highway, a combined classification section in which two or more expressways formed by lanes in the same direction are joined or separated, an IC/JC connecting route section connecting two or more highways formed by lanes in the same direction, and a road of a long section. It is any one of the types of information such as a cross section, which is a section in which traffic flows in the same direction alternate and lanes change while following.

The time setting unit 144 may select a specific time for outputting the driving behavior of the vehicle from the image time captured by the image input/output unit 120.

Specifically, the time setting unit 144 may exclude unnecessary images from the image captured by the image input/output unit 120 and select an image of a time period necessary for deriving the driving behavior of the vehicle. In particular, in order to analyze the driving behavior of the vehicle more clearly from the extracted data, it is possible to set the driving behavior of the vehicle from the captured image and the driving behavior of the vehicle.

Alternatively, the time setting unit 144 may set a time unit for extracting a vehicle driving behavior for traffic analysis from an image captured by the image input/output unit 120.

In detail, the time setting unit 144 may set a time unit for storing an image necessary for deriving a driving behavior of the vehicle from the captured image. For example, assuming that the captured image is 24 frames per second (24 frames/sec), the image captured by the image capturing unit 122 can be set to 6 frames, and the captured image will be stored in increments of 0.25 seconds. I can. The set extraction time unit may be used as information for extracting the vehicle speed and acceleration.

Meanwhile, the space setting unit 146 may set a space required for deriving a vehicle driving behavior among images captured by the image input/output unit 120.

In detail, the space setting unit 146 may set one of a region of interest among a section in which the vehicle is traveling and a lane of interest among a lane in which the vehicle is traveling. The region of interest and lane of interest may be a road section or lane in which traffic problems occur frequently, and the set region of interest and lane of interest may be changed according to the conditions of the user. The set region of interest and lane of interest can be used as information to analyze and extract the density relationship of the vehicle.

In addition, the space setting unit 146 may set an actual distance of a designated lane among driving lanes.

Among the driving behavior of the vehicle extracted from the captured image, it may be a travel speed for each vehicle, a degree of acceleration/deceleration of the vehicle, a movement trajectory, a distance between vehicles, a road density, and the like. In order to extract such information, the user designates two points for which the actual distance (m) is known, and then converts the two designated points to the actual distance (m) through pixels/distance (m) and sets them.

When a spatiotemporal region is set in the information setting unit 140 as described above, the driving behavior of the vehicle may be extracted based on the spatiotemporal region set in the extraction unit 160.

The driving behavior of the vehicle to be extracted includes, for example, vehicle type, vehicle speed/acceleration, and driving lane, and through these data, traffic flow characteristics, driving trajectories of specific individual vehicles, and mutual driving characteristics between two or more specific individual vehicles Etc. can be extracted.

In detail, in the case of a vehicle type, small, medium, and large can be classified and extracted based on the length of the vehicle according to the number of pixels, and the vehicle speed is determined based on the information set in the information setting unit 140 above. You can calculate the driving speed and acceleration. The driving lane identifies the lane in which the vehicle is traveling, and the driving lane location can be calculated using the vehicle location information and the lane classification information (1st, 2nd, and 3rd lanes) set by the user.

Meanwhile, when extracting the driving behavior of the vehicle, the driving behavior of the vehicle of a specific individual vehicle selected from among vehicles traveling on the road may also be extracted. In detail, a plurality of individual vehicles may be selected, and vehicle density of a road may be extracted by the selected specific individual vehicles. At this time, the calculation formula for extracting the vehicle density is as follows.

Vehicle density (k) = traffic volume (q) / average speed (u)

That is, based on the conditions set by the information setting unit 140, the average speed of the passing vehicles within the time and space range is calculated, and the number of passing vehicles per unit time is calculated from the information necessary for deriving the driving behavior of the vehicle. Thus, it is possible to calculate the vehicle density from information necessary for deriving the driving behavior of the vehicle.

Meanwhile, based on the driving behavior of the vehicle set by the information setting unit 140, the driving behavior of the individual vehicle may be extracted. To this end, the extraction unit 160 may include an object detection unit 162 and an object calculation unit 164 and may be configured.

The driving behavior of individual vehicles detected by the object detection unit 162 may be a driving behavior of a plurality of individual vehicles selected from images captured by the image input/output unit 120. In detail, it may be the vehicle type of the individual vehicle, the driving speed of the individual vehicle and the lane being driven, the number of times the individual vehicle has changed the lane while driving and the location of the change, and the inter-vehicle distance between the individual vehicle and other adjacent individual vehicles.

When the object detection unit 162 detects the information of the individual vehicle, the driving behavior of the individual vehicle may be calculated based on the information detected by the object calculation unit 164. As described above, the vehicle type of the individual vehicle selected, the driving speed of the individual vehicle, the driving lane, the number of times the individual vehicle has changed the lane while driving and the location of the change, the individual vehicle and the individual vehicle distance between adjacent individual vehicles, etc. Vehicle driving behavior can be detected.

The calculated driving behavior of the vehicle may be stored in the storage unit 180, and the stored data may be used as basic data to derive traffic problems on the road and analyze the cause to establish a solution.

Hereinafter, with reference to FIG. 5, the driving behavior of the vehicle analyzed by the vehicle driving behavior analysis system 10 according to an embodiment of the present invention and the analysis progress direction will be described.

5 is a view showing an embodiment in which a driving behavior and an analysis progress direction of a vehicle analyzed through a vehicle driving behavior analysis system using a drone according to an embodiment of the present invention are classified.

Referring to the drawing, a road is photographed through the image input/output unit 120. It is possible to correct the minute shake that occurs in the process of capturing the captured image. Through the corrected image, detailed image information of the lane, image information that displays the vehicle color differently for each speed of the vehicle being driven, image information that expresses the vehicle's movement trajectory in a specific lane, and an image that displays the point of change in the lane of the vehicle being driven. Information, etc. can be obtained.

When an image is captured, information necessary for outputting the driving behavior of the vehicle can be set. For example, the user may preferentially select a reference point, which is one of a region of interest and a lane of interest, referenced by the user, and then divide it by section according to the selected reference point. In this case, the length of the divided sections may be equally divided, but differently, the length may be set differently according to the purpose and need, and the number of divided sections may also be changed according to conditions.

Data can be extracted according to the type of lane from the information necessary to derive the driving behavior of the divided vehicle.

First, as shown in (a) of FIG. 5, the main line 1 and the main line 1 and the main line 1 and the main line 1 and the main line 1 of the road are joined in the same direction.

The confluence lane is a section in which the confluence connecting road 2 at the point of confluence is connected to the main line 1, and it is necessary to secure the driving rights of the vehicles on the main road 1 and the incoming vehicles in the confluence connecting route 2. It is a road where interactions can occur. Traffic congestion can be caused because a conflict between vehicles occurs in such a converging lane, and the traffic analysis items to solve this problem are as follows.

First, it is possible to compare the converging traffic volume of the main line 1 and the confluence connecting road 2. To this end, it is possible to derive the driving behavior of the vehicle by setting a congestion time for a large amount of vehicle traffic and a non-congestion time for a small amount of vehicle traffic on the road (coupling part lane) photographed by the image photographing unit 122. At this time, in order to set a specific time zone, the time setting unit 144 sets the derivation start time and the derivation end time.

In addition, traffic variables that affect the confluence of vehicles according to the characteristics of the confluence lane include the amount of traffic between the main line 1 and the confluence connecting road 2, the number of changes to the vehicle lane, the driving speed of the vehicle, and the density. .

On the other hand, according to the derived driving behavior of the vehicle, it is possible to analyze the amount of traffic that affects the formation of congestion in the congestion section between the main line 1 and the confluence connecting road 2. Based on the analyzed results, it is possible to derive a solution to problems such as adjusting the position of the section where the lane is reduced.

Meanwhile, a lane extracted from an image captured by the image input/output unit 120 may be a structure of a classification unit lane.

That is, the sorting section lane shown in Fig. 5(b) is a section in which the sorting section connection path 3 is discharged to the outside of the main line 1 from the main road line 1, and is trying to escape to the sorting section connection path 3 Is a road in which traffic congestion occurs due to frequent changes to the vehicle lane due to the large number of vehicles.

It is possible to analyze the driving behavior of the vehicle in the lane of the classification unit and derive a solution to the traffic problem based on the analyzed result.

Meanwhile, a lane extracted from an image captured by the image input/output unit 120 may be a cross section.

That is, as shown in (c) of FIG. 5, the cross section refers to a section in which traffic flows in the same direction are alternated and lanes are changed while following a long section of road without the help of a traffic control facility.

For example, in the intersecting section, both the confluence connection path 2 and the splitter connection path 3 may be formed along the main line 1. In such an intersecting section, since both the vehicles flowing in from the confluence section connection path 2 and the vehicle flowing out of the classification section connection path 3 are running, frequent lane changes may occur and congestion may occur.

Since traffic congestion, which is a traffic problem, occurs due to the crossing of vehicles in such a cross section, the traffic analysis items to solve this problem are as follows.

First, it is possible to compare the converging traffic volume of the main line 1 and the confluence connecting road 2. To this end, it is possible to analyze the driving behavior of the vehicle by setting a congestion time and a non-congestion time in which the vehicle passes a lot on the road taken by the image capturing unit 122 (the converging section lane). At this time, in order to set a specific time zone, the time setting unit 144 sets the derivation start time and the derivation end time.

In addition, it is possible to analyze a traffic problem different from the number of vehicle changes by comparing the number of changes to the lane of the vehicle introduced from the confluence unit connection path 2 and the vehicle discharged from the classification unit connection path 3.

In addition, by analyzing vehicle speed, density, and acceleration for each section of each lane, it is possible to analyze sections in which congestion and accidents occur frequently in intersecting lanes.

Depending on the traffic problem analyzed at the intersection as described above, for example, the width of the road for accessing the main line (1) to the classification unit linkage (3), or from the main line (1) to the classification unit linkage (3). Traffic problems can be solved by improving roads such as the ability to advance dotted road markings when entering.

Through such a solution to the problem, it is possible to derive the effect of securing driving visibility of drivers and preventing safety accidents when driving on a cross lane.

Meanwhile, the lane extracted from the image captured by the image input/output unit 120 may be a lane between the inclined section.

Referring to FIG. 5 (d), the lane of the inclined section is a vertical inclined section that is inclined from the side of the road in the vertical direction with respect to the horizontal line of the road and the road is cut in the horizontal direction with respect to the horizontal line of the road. It can be said to be a lane composed of a horizontal section inclined in plane.

In these inclined lanes, vehicle driving is greatly influenced by the terrain conditions, and in particular, heavy vehicles (for example, large vehicles, vans, etc.) are affected by the driving speed than passenger vehicles and can reduce vehicle congestion across the road. Can cause.

In other words, it can be seen that the deceleration of the vehicle appears as the slope and the slope length increase in the lane of the slope section. Specifically, when the vehicle moves a length of 1000 m on roads with different 4% inclination angles, when the vehicle moves 1000 m on a road with a speed reduction width (A) of the vehicle and 9% inclination angle When comparing the speed deceleration width (B) of the vehicle, the reduction width in the case (B) is larger than that in the case (A). Accordingly, it can be seen that the vehicle's driving speed, such as when the weight of the vehicle increases or the road slope is high, affects the vehicle driving behavior in the lane of the slope section.

In this way, if the vehicle driving behavior on the inclined lane is derived and the traffic problem is analyzed based on the derived result, for example, by installing an inclined display plate, the vehicle speed deceleration is caused in advance, or from before the inclined point. It is believed that improvement measures such as installing a lane change guidance system that informs the vehicle's lane change will be needed.

According to this improvement plan, it is possible to minimize the occurrence of accidents and congestion due to the change of the vehicle lane in the sloped lane.

Meanwhile, the lane extracted from the image captured by the image input/output unit 120 may be a non-repetitive congestion-causing section road.

Referring to (e) of FIG. 5, a non-repetitive congestion-causing section in which traffic congestion does not occur repeatedly, or where congestion is predictable or impossible, is occupied by a lane for a specific reason, such as a construction section and an accident section. It can be said that it is a section that restricts vehicle traffic. Hereinafter, in the embodiment of the present invention, an example in which a non-repetitive congestion-causing section occurs due to a construction section will be described.

When such a non-repetitive congestion-causing section (4) occurs on the road, the vehicle running at a high speed and a constant speed slows down due to the non-repetitive congestion-causing section (4), securing driving rights such as frequent lane changes. There is a congestion for this.

In order to solve the problem that occurred, information such as traffic volume within the construction section, distribution of lane changes within the main line (1), and general vehicle information (speed, density, acceleration, etc.) 4) Can suggest a method for solving traffic problems.

In addition to the aforementioned roads, it is also possible to analyze vehicle driving behavior in various sections such as tunnel entry section, drowsiness shelter section, and speed camera installation section, and solve problems such as stability of vehicle driving and reduction of congestion sections based on the analyzed data. have.

The vehicle driving behavior analysis system can selectively photograph an image of a road where a traffic problem occurs, and the microscopic driving behavior of the vehicle at a point where the problem occurs can be checked through the photographed image.

As described above, according to the vehicle driving behavior analysis system using the image of the unmanned aerial vehicle of the present invention, spatial constraints on the road section where traffic problems occur, for example, the main line of the highway, the confluence of IC (Interchange) / JCT (Junction), Images can be photographed without restrictions such as classification unit, cross section, vertical (upward, downward) slope change section, construction section, etc., and vehicle driving behavior for the problem section can be extracted through analysis of the captured image.

In particular, since microscopic empirical traffic analysis based on the driving behavior of the vehicle is performed, it is possible to diagnose problems clearly in the target road section, and by deriving an accurate improvement plan, it is possible to maximize the effect of traffic improvement.

Meanwhile, the functional operations and implementations of the subject described in this specification are implemented as digital electronic circuits, or computer software, firmware, or hardware including the structures disclosed in this specification and structural equivalents, or one or more of them. It can be implemented in combination. Implementations of the subject matter described herein are one or more computer program products, i.e., one or more modules relating to computer program instructions encoded on a tangible program storage medium for controlling or executing by the control system. Can be implemented.

The computer-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of materials that affect a machine-readable radio wave signal, or a combination of one or more of them.

In the present specification, the term "system" or "device" encompasses all devices, devices and machines for controlling data, including, for example, a programmable processor, a computer, or multiple processors or computers. The control system may include, in addition to hardware, code that forms an execution environment for a computer program upon request, such as a code constituting a processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. .

Computer programs (also known as programs, software, software applications, scripts, or code) can be written in any form of a compiled or interpreted language or a programming language, including a priori or procedural language, and can be written as a standalone program or module, It can be deployed in any form, including components, subroutines, or other units suitable for use in a computer environment. Computer programs do not necessarily correspond to files in the file system. A program may be in a single file provided to the requested program, or in multiple interactive files (e.g., files that store one or more modules, subprograms, or portions of code), or part of a file that holds other programs or data. (Eg, one or more scripts stored within a markup language document). The computer program may be deployed to run on one computer or multiple computers located at one site or distributed across a plurality of sites and interconnected by a communication network.

On the other hand, computer-readable media suitable for storing computer program instructions and data include, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, such as magnetic disks such as internal hard disks or external disks, magneto-optical disks, and CDs. -May contain all types of nonvolatile memory, media and memory devices, including ROM and DVD-ROM disks. The processor and memory can be supplemented by special purpose logic circuits or incorporated into it.

Implementations of the subject matter described in this specification include a backend component such as, for example, a driving behavior server of a vehicle, or include a middleware component such as an application server, or, for example, a web browser that allows a user to interact with the subject matter implementation described herein. It may be implemented in a front-end component, such as a client computer with a graphical user interface, or a computing system that includes all combinations of one or more of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital vehicle driving behavior communication, for example a communication network.

While this specification includes details of a number of specific implementations, these should not be construed as limiting to the scope of any invention or claim, but rather as a description of features that may be peculiar to a particular embodiment of a particular invention. It must be understood. Likewise, certain features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination. Furthermore, although features operate in a particular combination and may be initially described as so claimed, one or more features from a claimed combination may in some cases be excluded from the combination, and the claimed combination may be a subcombination. Or sub-combination variations.

In addition, although the present specification describes the operations in the drawings in a specific order, it is not understood that such operations must be performed in the specific order or sequential order shown in order to obtain a desirable result, or that all illustrated operations must be performed. Can not be done. In certain cases, multitasking and parallel processing can be advantageous. In addition, separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the program components and systems described are generally integrated together into a single software product or packaged in multiple software products. Understand that you can

As such, this specification is not intended to limit the invention to the specific terms presented. Accordingly, although the present invention has been described in detail with reference to the above-described examples, those skilled in the art can make modifications, changes, and modifications to these examples without departing from the scope of the present invention. The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

According to the vehicle driving behavior analysis system of the present invention, by analyzing road traffic problems using an unmanned flight device, in terms of realizing a technology that enables a service to clearly diagnose the point of occurrence and reason of the problem factor, etc. However, it is an invention that has industrial applicability because it exceeds the limitations of the existing technology, so that not only the use of the related technology, but also the possibility of marketing or sales of the applied device is sufficient, and it can be practically clearly implemented.

10: Vehicle driving behavior analysis system
120: video input/output unit
140: information setting unit
160: extraction unit
180: storage unit

Claims (9)

In the vehicle driving behavior analysis system using an image of an unmanned flight device for diagnosing a cause of a traffic problem by extracting the driving behavior of the vehicle,
An image input/output unit for photographing a lane on which the vehicle travels as an image using an unmanned aerial vehicle, and inputting and outputting the captured image;
An information setting unit configured to set information for outputting a driving behavior of the vehicle traveling in the lane based on the image output from the image input/output unit;
An extracting unit for extracting the driving behavior of the vehicle based on the information set by the information setting unit; And
A storage unit for storing the driving behavior of the vehicle extracted by the extraction unit; Including,
The image input and output unit,
An image photographing unit for photographing any one of the vehicle information and the lane information as an image;
An image input unit for inputting an image captured by the image capturing unit; And _
Image information in which the color of the vehicle is displayed differently for each vehicle speed by correcting the image input to the image input unit, image information representing the movement trajectory of the vehicle in a specific lane, and a lane change in which the vehicle being driven changes the lane An image correction unit for obtaining image information indicating an occurrence point; Vehicle driving behavior analysis system using an unmanned aerial vehicle image comprising a. delete The method of claim 1,
The image capture unit,
A vehicle driving behavior analysis system using an image of an unmanned aerial vehicle, characterized in that it is a drone that photographs any one of information on the vehicle or lane information at a fixed location. The method of claim 1,
The information setting unit,
A lane setting unit for setting information on at least one of a type of a lane on which the vehicle travels and a type of lane on which the vehicle travels in the image captured by the image input/output unit;
A time setting unit for setting a specific time required for deriving the driving behavior of the vehicle from the image captured by the image input/output unit;
In order to derive the driving behavior of the vehicle from the image captured by the image capturing unit, one of a region of interest among a section in which the vehicle is traveling, a lane of interest among a lane in which the vehicle is traveling, and an actual distance of a designated lane among the lanes in which the vehicle is traveling A space setting unit for setting any one; Vehicle driving behavior analysis system using an unmanned aerial vehicle image comprising a. The method of claim 4,
The time setting unit,
A vehicle driving behavior analysis system using an unmanned aerial vehicle image, characterized in that the analysis start time and the analysis end time are set based on a time point at which more than a certain number of vehicles operate on the lane. The method of claim 4,
The time setting unit
A vehicle driving behavior analysis system using an unmanned aerial vehicle image, characterized in that setting a time unit for extracting the driving behavior of the vehicle from the image captured by the image input/output unit. The method of claim 4,
The lane setting unit,
The lane on which the vehicle runs is a main line section of a highway, a combined classification section in which two or more expressways formed by lanes in the same direction are joined or separated, an IC/JC connection route section connecting two or more highways formed by lanes in the same direction, and a long A vehicle driving behavior analysis system using an unmanned aerial vehicle image, characterized in that it sets any one of types of information, such as a cross section, which is a section in which traffic flows in the same direction alternate and lanes are changed while following a road of a section. The method of claim 1,
The extraction unit,
Extracted based on the vehicle type extracted based on the length of the vehicle extracted by the number of pixels extracted from the image captured by the image input/output unit, the vehicle speed and acceleration, the vehicle location, and the set classification information of the lane Extracts information on any one of the driving lanes on which the vehicle is driven, and extracts any one of traffic flow characteristics, a driving trajectory of a specific individual vehicle, and mutual driving characteristics between two or more specific individual vehicles based on the extracted information Vehicle driving behavior analysis system using an unmanned aerial vehicle image, characterized in that. The method of claim 8,
The extraction unit,
A vehicle driving behavior analysis system using an unmanned aerial vehicle image, characterized in that the vehicle density of a road on which the vehicle is traveling is extracted by a specific individual vehicle selected from among the vehicles traveling in the lane.

Images