KR102450272B1 - Local visit information statistical processing method and apparatus - Google Patents

Abstract

Disclosed are a local visit information statistical processing method and a device thereof. The local visit information statistical processing method comprises: (a) a step of obtaining incoming vehicle information by analyzing a video photographing vehicles passing through an incoming point through a camera installed in each incoming point of a target area, wherein the incoming vehicle information includes an incoming vehicle number and incoming vehicle related information; (b) a step of obtaining outgoing vehicle information by analyzing a video photographing vehicles passing through an outgoing point through a camera installed in each outgoing point of the target area, wherein the outgoing vehicle information includes a vehicle number and outgoing vehicle related information; and (c) a step of estimating the number of entering and leaving people by using the incoming vehicle information and the outgoing vehicle information and estimating the number of entering and leaving people by reflecting a correcting value according to the incoming vehicle related information and the outgoing vehicle related information.

Description

LOCAL VISIT INFORMATION STATISTICAL PROCESSING METHOD AND APPARATUS

The present invention relates to a method and apparatus for statistical processing of local visit information.

Korean Patent Registration No. 10-1721041 (registered on March 23, 2017) discloses a movement pattern analysis system and method using a point of interest. In other words, the user's movement pattern can be analyzed using the beacon signal, and the crisis or abnormal situation of the target to be protected, such as children and women, can be immediately identified, and the user's wandering, or It is possible to detect whether there is a departure from the route that the user normally travels, and it is possible to determine whether the user is abnormal using a beacon signal based on the user's usual movement pattern. It is possible to provide a service that models a user's movement pattern using a WiFi access point (AP), etc.

However, when a beacon signal is used, it can be applied in a small and small place, and there is a problem in that it is difficult to cover a wide area between regions.

Republic of Korea Patent Publication No. 10-1721041 (2017.03.23.)

An object of the present invention is to provide a method and apparatus for statistical processing of local visit information based on image analysis.

Another object of the present invention is to provide a method and apparatus for statistical processing of local visit information capable of processing local visit information through vehicle number recognition.

According to one aspect of the present invention, there is provided a statistical processing method for local visit information based on image analysis.

According to an embodiment of the present invention, (a) analyzing an image of a vehicle passing through the entry point through a camera installed at each entry point of the target area to obtain entry vehicle information - the entry vehicle information is including the entering vehicle number and information relating to the entering vehicle; (b) analyzing an image of a vehicle passing through the exit point through a camera installed at each entry point in the target area to obtain exit vehicle information - The exit vehicle information includes vehicle number and exit vehicle related information included; and (c) estimating the number of inflows and outflows using the entering vehicle information and the exiting vehicle information, and estimating the inflow and outflow personnel by reflecting correction values according to the entering vehicle-related information and the exiting vehicle-related information. A method for processing visit information statistics may be provided.

In step (c), the number of vehicles passing through the entry point and the exit point is counted for a predetermined time using the entry vehicle information and the exit vehicle information, and then the number of inflows and exits is estimated by applying a correction value according to each vehicle type. can do.

The camera includes at least one of a first camera and the second camera, wherein the first camera is installed at the entry point and the exit point, respectively, and recognizes the number of a vehicle passing through the entry point and the exit point A line-of-sight camera, and the second camera is an infrared camera for obtaining the number of people in the vehicle.

In the step (c), a second correction value according to the purpose of inflow and outflow may be reflected in estimating the number of people in and out on the basis of the time and day at which the vehicle passed the entry point and the entry point.

The entry and exit purpose is at least one of commuting, passing vehicles, and tourism, but classifying the entry and exit purposes by referring to local events held in the target area and vehicle entry and exit history, wherein the vehicle entry and exit history includes the entry point and the entry for a predetermined period It may include entering vehicle information and exiting vehicle information for each vehicle that has passed the point.

The time when the vehicle passes the entry point and the exit point is the designated commuting time, and the vehicle that repeatedly enters and exits multiple times at a predetermined time and on a certain day by referring to the vehicle entry and exit history among vehicles on weekdays is the target It may be determined that the vehicle is a resident vehicle residing in the area or a vehicle passing through the target area.

In classifying the purpose of the inflow and outflow, information on an entry vehicle and information on an exit vehicle of an adjacent area of the target area, and event information on an adjacent area may be further used.

The method may further include estimating a stay period and number of people staying in the target area by obtaining a date when a specific vehicle entered the target area and a date when the specific vehicle entered the target area by referring to the vehicle entry/exit history.

According to another aspect of the present invention, an apparatus for statistical processing of local visit information based on image analysis is provided.

According to an embodiment of the present invention, a memory for storing at least one instruction; and a processor that executes the instructions stored in the memory, wherein the instructions executed by the processor analyze an image of a vehicle passing through the entry point through a camera installed at each entry point of the target area to analyze an entry vehicle obtaining information, wherein the entering vehicle information includes an entering vehicle number and entering vehicle-related information; analyzing an image of a vehicle passing through the entry point through a camera installed at each entry point in the target area to obtain exit vehicle information; and estimating the number of inflows and outflows using the entry vehicle information and the exit vehicle information, reflecting correction values according to the entry vehicle-related information and the exit vehicle-related information to estimate the number of inflows and exits. An analytical device may be provided.

By providing a method and apparatus for statistical processing of local visit information based on image analysis in an embodiment of the present invention, there is an advantage in that it is possible to statistically process local visit information by analyzing an image captured by a camera installed on each road.

1 is a block diagram schematically illustrating a system configuration for statistical processing of local visit information according to an embodiment of the present invention.
2 is a flowchart illustrating a method for statistical processing of local visit information according to an embodiment of the present invention.
3 is a block diagram schematically illustrating an internal configuration of an analysis device according to an embodiment of the present invention.

As used herein, the singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or various steps described in the specification, some of which components or some steps are It should be construed that it may not include, or may further include additional components or steps. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram schematically illustrating a system configuration for statistical processing of local visit information according to an embodiment of the present invention.

Referring to FIG. 1 , a system 100 for statistical processing of local visit information according to an embodiment of the present invention includes a plurality of cameras 110 and 120 and an analysis device 130 .

The plurality of cameras 110 and 120 are respectively installed at the first point and the second point.

The first point is a point on the road for entering the target area, and there may be a plurality of points. That is, one point on a plurality of roads that can enter the target area will be collectively referred to as a first point or an entry point, respectively. When there are two roads that can enter the target area, the first point or entry point may be two, and if there are three roads, the first point or entry point may be three.

The second point may be a plurality of points on a road for advancing from the target area to the adjacent area. Like the first point, the second point may be one point on a plurality of roads for advancing from the target area to the adjacent area.

The first point and the second point may be opposite to each other on the road.

Each of the plurality of cameras 110 and 120 may include only a line-of-sight camera, or may include a line-of-sight camera and an infrared camera according to an implementation method.

The plurality of cameras 110 and 120 may be respectively installed at the first point and the second point, respectively, and may photograph a vehicle passing through the first point and the second point and transmit it to the analysis device 130 .

The analysis device 130 obtains images of vehicles passing through the first and second points for entering or exiting the target area from the cameras 110 and 120, respectively, and analyzes them to process local visit statistical information is a means to

The analysis device 130 may estimate the number of inflows/outflows by analyzing images captured by vehicles passing through the first point and the second point for entering or exiting the target area, respectively. In addition, the analysis device 130 may analyze an image of a vehicle passing through the first point and the second point for entering or exiting the target area, respectively, to classify the purpose of entry/exit, and estimate the number of inflows/outflows.

In addition, the analysis apparatus 130 may further use vehicle information of a neighboring area adjacent to the target area to identify vehicle information passing through the target area and perform statistical processing.

A method of processing local visit statistics by analyzing images of vehicles passing through the first point and the second point for entering or exiting the target area, respectively, will be described in more detail with reference to FIG. 2 .

2 is a flowchart illustrating a method for statistical processing of local visit information according to an embodiment of the present invention.

In step 210 , the analysis device 130 obtains entry vehicle information by analyzing an image captured by a vehicle passing through the first point through a camera installed at the first point entering the target area.

Here, the first point is a specific point on each road that can be entered into the target area, and may be a plurality of points that can be entered into the target area.

That is, each camera is installed at each road point that can enter the target area, and information on the vehicle entering the target area can be generated by analyzing an image of a vehicle passing through each entry point. Here, the entering vehicle information may be a vehicle number (entry vehicle number) and information related to the entering vehicle.

The information related to the approaching vehicle may be different depending on the type of installed camera.

For example, when only the line-of-sight camera is installed at the first point, the entering vehicle-related information may be acquired as the entering vehicle-related information by checking the vehicle model and whether the passenger is seated in the passenger seat.

As another example, it is assumed that the installed camera types are a line-of-sight camera and an infrared camera.

In this case, the entering vehicle-related information may be obtained as the entering vehicle-related information, not only the vehicle number, but also the vehicle model and the number of passengers recognized through the infrared camera.

In step 215 , the analysis device 130 obtains information on the vehicle entering the target area by analyzing an image captured by a vehicle passing through the second point through a camera installed at the second point entering the target area. The second point is a specific point on each road accessible from the target area, and may be a plurality of points. Here, the outgoing vehicle information may be a vehicle number (entry vehicle number) and information related to the entering vehicle.

Like the entering vehicle information, the outgoing vehicle information may also be different depending on the installed camera type.

Since this is the same as described above, the overlapping description will be omitted.

In step 220 , the analysis device 130 performs statistical processing of local visits by using the entering vehicle information and the exiting vehicle information.

This will be described in more detail.

The analysis device 130 analyzes the image captured by the camera installed at the first point to obtain information (entry vehicle information) on the vehicle that has passed the first point, and then obtains the first point (entry point) for a predetermined time. It is possible to count the number of vehicles passing through.

The analysis device 130 may further acquire the vehicle model and whether the passenger is in the passenger seat as information on the vehicle entering the vehicle by analyzing the image captured by the camera installed at the first point.

Accordingly, the analysis apparatus 130 may estimate the number of inflows by applying the first correction value according to the vehicle type to the number of vehicles passing the first point for a predetermined time. Here, the first correction value may be an average number of passengers according to each vehicle type. In addition, in applying the first correction value, whether or not the first correction value is applied may be determined by further considering whether the passenger is in the passenger seat. If a person is seated in the passenger seat, the influx of people may be estimated by applying the first correction value for each vehicle type to the vehicle that has passed the first point for a predetermined time.

However, when no person is in the passenger seat, the first correction value may not be applied because it is determined that the passenger is riding alone.

The same can be applied to the estimation of the number of leaked persons. That is, the analysis apparatus 130 may estimate the number of outflows by applying the first correction value according to the vehicle type to the number of vehicles passing the second point (entry point) for a predetermined time. Similarly, in applying the first correction value for estimating the number of leaked persons, whether to apply the first correction value may be determined by further considering whether the passenger is in the passenger seat.

For another example, the analysis device 130 classifies the purpose of inflow and outflow according to the time and day that the vehicle passed the first point or/and the second point, and estimates the number of people in and out by applying a second correction value according to the purpose of the inflow and out. You may.

For example, the analysis device 130 may determine that the time the vehicle passes through the first point and/or the second point is the commuting time, and when the day of the week is on a weekday, the corresponding vehicle moves for commuting. In this case, it is determined that the owner of the vehicle is a local resident, and thus the number of inflows and outflows may be estimated according to the purpose of the inflow and outflow.

The purpose of inflow and out may be at least one of commuting, passing vehicles, and tourism.

According to an embodiment of the present invention, instead of applying only time and day of the week to distinguish the purpose of inflow and outflow, local event information (eg, local festival, local event, etc.) may be considered.

In addition, the vehicle entry and exit history may be further referenced. For example, the vehicle entry/exit history may include information (vehicle number, vehicle model, etc.) about a vehicle that has passed the first point and the second point in the target area for a predetermined period of time.

Therefore, the analysis device 130 further refers to the vehicle entry/exit history to determine that the vehicle is a commuting vehicle if it is a vehicle that periodically or repeatedly moves the first point/second point during the weekday commuting time through vehicle number analysis. may be

In addition, the analysis apparatus 130 may determine whether a vehicle passing through the target area through interlocking of the entering vehicle information and the outgoing vehicle information for an adjacent area of the target area.

Also, the analysis device 130 may classify the purpose of inflow and outflow by further considering event information (festival, event, etc.) in the neighboring region of the target region.

As another example, the analysis device 130 may estimate the length of stay and the number of people staying in the target area according to each vehicle number with reference to the vehicle entry/exit history.

As another example, when the cameras installed at the first point/second point are a line-of-sight camera and an infrared camera, the analysis device 130 may obtain not only the vehicle number but also the occupant information as vehicle information through the corresponding camera. .

In this case, the analysis device 130 may calculate the number of people in and out by counting the number of passengers by obtaining the vehicle number and the number of passengers that have passed the first point/second point for a predetermined time without applying a separate correction value.

For another example, the analysis device 130 analyzes an image captured by a camera installed on a road around a tourist destination in a specific area to recognize a vehicle number, stores it in a buffer, and then recognizes a vehicle number recognized on a road around each tourist destination can also be analyzed to analyze the movement of tourists (and the number of visitors) over time.

For example, it is assumed that the vehicle number of the first vehicle is recognized in Jeonju Hanok Village and stored in a buffer. It is assumed that the time stored in the corresponding buffer was 10 am.

Thereafter, it is assumed that the license plate number of the first vehicle is recognized near Mireuksaji Temple in Iksan. The analysis device 130 may determine whether the vehicle number of the first vehicle is stored by checking the buffer. Since there is a record in which the first vehicle is recognized around Jeonju Hanok Village at 10 am in the buffer, the analysis device 130 visits Jeonju Hanok Village in the morning through the vehicle number recognition of the first vehicle, and then near Mireuksaji Temple in Iksan in the afternoon. It is possible to estimate and analyze the movement of tourists based on their visit.

As described above, according to an embodiment of the present invention, after obtaining vehicle information by analyzing an image captured by a camera installed on each road in a target area, it is possible to analyze and statistically process local visit information by using it.

3 is a block diagram schematically illustrating an internal configuration of an analysis apparatus according to an embodiment of the present invention.

Referring to FIG. 3 , the analysis apparatus 130 according to an embodiment of the present invention includes a communication unit 310 , a memory 320 , and a processor 330 .

The communication unit 310 may transmit/receive data to and from other devices (eg, a camera) through a communication network.

The memory 320 stores instructions (program codes) for performing a method for statistical processing of local visit information based on vehicle image analysis according to an embodiment of the present invention.

The processor 330 is a means for controlling internal components (eg, the communication unit 310 , the memory 320 , etc.) of the analysis device 130 according to an embodiment of the present invention.

The processor 330 may execute instructions stored in the memory 320 . The instructions executed by the processor 330 analyze an image captured by a plurality of cameras installed on the road of the target area to obtain vehicle information (entry vehicle information, exit vehicle information), and analyze this to analyze the target for a predetermined period of time. It is possible to estimate the number of people in and out of the area. Since this is the same as that described with reference to FIG. 2 , the overlapping description will be omitted.

Up to now, the present invention has been looked at focusing on the embodiments thereof. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention may be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

100: system
110, 120: camera
130: analysis device

Claims (10)

(a) analyzing an image of a vehicle passing through the entry point through a camera installed at each entry point in the target area to obtain entry vehicle information - The entry vehicle information includes an entry vehicle number and entry vehicle-related information included;
(b) analyzing an image of a vehicle passing through the exit point through a camera installed at each entry point in the target area to obtain exit vehicle information - The exit vehicle information includes a vehicle number and vehicle-related information included; and
(c) estimating the number of people entering and leaving by using the entry vehicle information and the exit vehicle information, and estimating the number of people in and out by reflecting correction values according to the entry vehicle-related information and the exit vehicle-related information,
Step (c) is,
Based on the time and day of the week at which the vehicle passed the entry point and the exit point, a second correction value according to the purpose of inflow and outflow is reflected in the estimation of the number of people in and out of, the method of processing local visit information statistically.
According to claim 1,
Step (c) is,
Local visit, characterized in that the number of vehicles passing the entry point and the exit point is counted for a predetermined time using the entry vehicle information and the exit vehicle information, and then a correction value according to each vehicle type is applied to estimate the number of people entering and leaving How information statistics are processed.
According to claim 1,
The camera comprises at least one of a first camera and a second camera,
The first camera is a line-of-sight camera that is installed at the entry point and the exit point, respectively, and recognizes the number of a vehicle passing through the entry point and the exit point,
The second camera is an infrared camera for acquiring the number of people in the vehicle.
delete According to claim 1,
The purpose of the inflow and out is at least one of commuting, passing vehicles, and tourism,
Classify the purpose of entry and exit by referring to regional events and vehicle entry and exit history held in the target area,
The vehicle entry/exit history includes entry vehicle information and exit vehicle information for each vehicle passing through the entry point and the entry point for a predetermined period.
6. The method of claim 5,
The time when the vehicle passes the entry point and the exit point is the designated commuting time, and the vehicle that repeatedly enters and exits multiple times at a predetermined time and on a certain day by referring to the vehicle entry and exit history among vehicles on weekdays is the target A method for statistical processing of local visit information, characterized in that it is determined that the vehicle is a resident vehicle residing in the area or a vehicle passing through the target area.
6. The method of claim 5,
The method for processing local visit information, characterized in that, when classifying the purpose of inflow and outflow, further using information on vehicles entering and exiting a region adjacent to the target region, and information on events in adjacent regions.
6. The method of claim 5,
Local visit information statistical processing further comprising the step of estimating a stay period and number of guests in the target area by obtaining a date when a specific vehicle entered the target area and a date that a specific vehicle entered the target area by referring to the vehicle entry/exit history Way.
A computer-readable recording medium having recorded thereon a program code for performing the method according to any one of claims 1 to 3 and 5 to 8.
a memory storing at least one instruction; and
A processor for executing instructions stored in the memory,
The instructions executed by the processor are
Obtaining entry vehicle information by analyzing an image of a vehicle passing through the entry point through a camera installed at each entry point of the target area - The entry vehicle information includes an entry vehicle number and entry vehicle-related information;
analyzing an image of a vehicle passing through the entry point through a camera installed at each entry point in the target area to obtain exit vehicle information; and
Estimating the number of inflows and outflows by using the entry vehicle information and the exit vehicle information, reflecting correction values according to the entry vehicle-related information and the exit vehicle-related information to estimate the number of inflows and exits;
In the estimating of the number of inflows and outflows, the second correction value according to the purpose of the inflow and outflow is reflected in the estimation of the number of inflows and outs based on the time and day of the week when the vehicle passed the entry point and the exit point.

Images