JP2022125208A - Information processing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To estimate a degree of congestion of a parking lot based on information obtained by traveling of a vehicle.

SOLUTION: An information processing device acquires position information including a parking position from a moving object, and estimates parking lot information relating to a parking lot existing in an area outside a road based on the position information of the plurality of moving objects entering the area outside a road. An estimating unit estimates a degree of congestion of the entire parking lot based on the parking position.

SELECTED DRAWING: Figure 9

COPYRIGHT: (C)2022,JPO&INPIT

Description

The present invention relates to technology for collecting information about parking lots.

In the distribution of parking lot information, there is a case where parking lot full-occupancy information is distributed. When generating the fullness information, in the conventional method, a management device installed in the parking lot that manages entry and exit has generated based on information on the number of parking spaces, the number of entrances, and the number of exits. However, in a parking lot without a management device as described above, there is a problem that it is not possible to generate parking lot occupancy information, and it is not possible to distribute the congestion status of the parking lot such as the vacancy information.

According to Patent Document 1, when the speed of a vehicle among vehicles passing around a parking lot is reduced by a predetermined threshold or more and the vehicle passes through the entrance of the parking lot, the parking lot is full. It describes a method for determining

JP 2015-184820 A

However, the technique described in Patent Literature 1 has a problem in terms of accuracy because it is determined by the judgment of the user who is passing by the parking lot. In addition, the above technology can only determine the state of full occupancy, and cannot estimate the degree of congestion in a parking lot other than the state of full occupancy. In addition, there was no mention of congestion due to parking positions in the parking lot.

Examples of the problems to be solved by the present invention include the above. An object of the present invention is to estimate the degree of congestion in a parking lot based on information obtained from vehicle travel.

According to a first aspect of the present invention, there is provided an information processing apparatus comprising: an acquisition unit that acquires position information including a parking position from a moving body; an estimating unit that estimates parking lot information related to a parking lot that exists in an area outside the road, wherein the estimating unit estimates the degree of congestion of the entire parking lot based on the parking position.

1 shows a configuration of an information processing system according to an embodiment; An example of probe data is shown. An example of parking lot data is shown. It is a flowchart of a parking area estimation process. It is a flowchart of a parking lot identification process and an estimation process. It is a figure explaining off-road driving|running|working. It is a figure explaining the estimation method of a parking lot area|region. An example of estimating a parking lot area from a plurality of driving surfaces is shown. 10 is a flowchart of congestion degree estimation processing;

In one preferred embodiment of the present invention, the information processing device includes an acquisition unit that acquires position information including a parking position from a moving body, and based on the position information of a plurality of moving bodies that have entered the off-road area, the above-mentioned an estimating unit that estimates parking lot information related to a parking lot that exists in an area outside the road, wherein the estimating unit estimates the degree of congestion of the entire parking lot based on the parking position.

The above information processing apparatus acquires position information including parking positions from mobile bodies, and based on the position information of a plurality of mobile bodies that have entered the road area, parking lot information on parking lots that exist in the road area. presume. Here, the estimation unit estimates the degree of congestion of the entire parking lot based on the parking position. According to this information processing device, the degree of congestion in the parking lot can be estimated by analyzing the parking positions of the moving bodies in the area outside the road.

In one aspect of the information processing device described above, the estimation unit estimates the degree of congestion based on the degree of concentration of the distribution of the parking positions. In this aspect, the degree of congestion is estimated from the degree of concentration of the parking position distribution. Specifically, when the degree of concentration is high, it is estimated that the degree of congestion is low, and when the degree of concentration is low, it is estimated that the degree of congestion is high.

In another aspect of the information processing device, the estimation unit calculates the degree of concentration based on an area of a standard deviation ellipse of the parking position. In a preferred example, the estimation unit divides the parking position into a plurality of areas and calculates the area of the standard deviation ellipse for each area, thereby estimating the degree of congestion for each area. In another preferred example, the estimation unit estimates the degree of congestion for each of a plurality of areas based on parking positions in the entire parking lot.

In another aspect of the information processing apparatus, the acquisition unit acquires time information corresponding to the location information from the moving body, and the estimation unit estimates the congestion degree for each time period. In this aspect, the congestion degree of the parking lot can be estimated for each time period.

In another preferred embodiment of the present invention, an information processing method executed by an information processing apparatus includes an acquisition step of acquiring position information including a parking position from a mobile object, and an estimating step of estimating parking lot information related to the parking lot existing in the area outside the road based on the location information of the parking lot, and to estimate According to this information processing method, the degree of congestion in the parking lot can be estimated by analyzing the parking positions of the moving bodies in the area outside the road.

In another preferred embodiment of the present invention, a program executed by an information processing apparatus including a computer includes an acquisition unit that acquires position information including a parking position from a mobile object, a plurality of mobile objects that have entered an off-road area, The computer functions as an estimating unit that estimates parking lot information about a parking lot that exists in the area outside the road based on the position information of the parking lot, and the estimating unit estimates the entire parking lot based on the parking position Estimate the degree of congestion of By executing this program on a computer, the above information processing apparatus can be realized. This program can be stored in a storage medium and handled.

Preferred embodiments of the present invention will be described below with reference to the drawings.
[System configuration]
FIG. 1A shows the configuration of an information processing system to which the present invention is applied. The information processing system includes a server 10 and a navigation device 20 mounted on the vehicle 3 . The server 10 and the navigation device 20 are configured to be wirelessly communicable. Although only one vehicle 3 is shown in FIG. 1 for convenience of explanation, a large number of vehicles 3 actually communicate with the server 10 .

FIG. 1B shows the configuration of the server 10. As shown in FIG. The server 10 includes a communication unit 11 , a control unit 12 , a map database (hereinafter “database” is abbreviated as “DB”) 13 , and a probe DB 14 .

The communication unit 11 receives probe data from the navigation device 20 . The probe data is generated by the navigation device 20 as the vehicle 3 travels. The map DB 13 stores map data. As map data, in addition to link data indicating links corresponding to roads and node data corresponding to intersections, parking lot data relating to parking lots are stored. The probe DB 14 stores probe data received from many navigation devices 20 .

The control unit 12 controls the entire server 10 . The control unit 12 is configured by a computer such as a CPU, and executes a predetermined process by executing a program prepared in advance. Specifically, the control unit 12 executes a process of receiving probe data from the navigation device 20, a process of estimating the parking lot area based on the probe data accumulated in the probe DB 14, and the like.

[Probe data]
Next, probe data will be explained. FIG. 2 shows an example of probe data. The probe data is generated by the navigation device 20 every predetermined time (for example, every few seconds) as the vehicle 3 travels. The example in FIG. showing. As shown, the probe data includes "mileage", "latitude", "longitude", "date and time", "speed", "traveling direction", "road type" and "back flag".

The "distance traveled" is the traveled distance of the vehicle 3, and the accumulated traveled distance by the odometer is used. “Latitude” and “longitude” indicate the latitude and longitude of the position of the vehicle 3 . "Date and time" indicates the date and time when each probe data was generated. "Speed" indicates the speed of the vehicle 3 at the time of measurement. "Direction of travel" indicates the direction of travel of the vehicle 3 at the time of measurement. Note that the direction of travel is indicated by an azimuth with the north direction as 0 degrees.

"Road type" is information indicating the type of road on which the vehicle 3 is traveling. is determined as "5". In this embodiment, the navigation device 20 sets the road type to "-1" when the vehicle 3 is traveling in an area outside the road. Therefore, when the road type is "-1", the vehicle 3 is traveling off the road.

The "back flag" is a flag indicating whether or not the vehicle 3 is backing (reversing). A back flag "0" indicates forward movement, and a "1" indicates backward movement. Note that the reverse flag is generated based on whether or not the gear of the vehicle 3 is in the reverse position.

[Parking data]
Next, the parking lot data will be explained. FIG. 3 shows an example of parking lot data. Parking lot data is prepared for each entrance of the parking lot. Therefore, when one parking lot has a plurality of entrances, a plurality of parking lot data are prepared for the one parking lot. As shown, the parking lot data includes "ID", "latitude", "longitude", "direction" and "name".

"ID" is an identification number that uniquely indicates the entrance of the parking lot. "Latitude" and "longitude" are the latitude and longitude of the parking lot entrance. "Azimuth" indicates the traveling direction when the vehicle 3 enters from the entrance of the parking lot. For example, if the entrance of the parking lot faces north, the vehicle 3 enters from the north side of the parking lot in the south direction, so the direction of the entrance is the south direction. In this example, the azimuth is indicated by an angle with the north at 0 degree.

"Name" is the name of the parking lot. In the example of FIG. 3, parking lot data is prepared for each parking lot entrance, but instead, parking lot data may be prepared for each parking lot. However, even in this case, the parking lot data includes the latitude, longitude and direction of the entrance of the parking lot. That is, information indicating the position and direction of the entrance of the parking lot (if there are multiple entrances) is included.

[Parking Area Acquisition Processing]
Next, the parking area acquisition process will be described. The parking lot area acquisition process is executed by the server 10 and is a process of estimating the area of the parking lot based on the probe data obtained from many vehicles 3 . This processing is mainly executed by the control unit 12 of the server 10 . It should be noted that, in practice, a computer such as a CPU that constitutes the control unit 12 executes a program prepared in advance.

First, the server 10 receives probe data by wireless communication from many vehicles 3 (step S10). The server 10 stores the received probe data in the probe DB 14 .

Next, the server 10 performs parking lot identification (step S11). Parking lot identification processing is processing for identifying a parking lot from probe data and parking lot data in map data. Details of the parking lot identification process are shown in FIG. First, the server 10 detects the start point of off-road travel based on the probe data (step S21).

FIG. 6 is a diagram for explaining off-road travel. As shown in the figure, a plurality of roads intersect, and a plurality of sections (sites) are formed by roads extending north and south and roads extending east and west. A vehicle mark X indicates the position of the vehicle 3 indicated by the probe data. A white vehicle mark X indicates a position on a prefectural road, and the probe data at this position includes "4 (prefectural road)" as the road type. A vehicle mark X with diagonal hatching indicates a position on a city road, and the probe data at this position includes "5 (city road)" as the road type. A black vehicle mark X indicates a position outside the road, and the probe data at this position includes "-1 (outside the road)" as the road type.

Now, as shown in the figure, a vehicle 3 is traveling west on road R3 (prefectural road), turns left at the intersection of roads R2 and R3, enters road R2 (city road), and turns left again to enter a section with a parking lot. 50, drive in the parking lot, and finally park the vehicle 3 toward the west (see dashed line 62). In this case, the server 10 refers to the probe data indicating the travel locus shown in FIG. Determined as the starting point of travel.

Next, the server 10 refers to the parking lot data in the map DB 13 and searches for a parking lot having an entrance within a predetermined threshold range from the coordinates of the start point of off-road travel obtained in step S21 (step S22). ). Then, the server 10 selects the closest entrance from among the plurality of parking lots obtained by the search, the direction of the entrance of which matches the traveling direction of the vehicle 3 at the start point of off-road travel and which is closest to the off-road travel start point. is identified (step S23). The process then returns to the main routine shown in FIG.

Next, the server 10 determines whether or not the parking lot has been identified in the parking lot identification process of step S11, that is, whether or not the corresponding parking lot has been found (step S12). If no corresponding parking lot is found (step S12: No), the server 10 determines that the parking lot indicated by the probe data obtained this time has not yet been registered in the map DB 13, and adds that parking lot to the map DB 13. Register (step S13). Specifically, the server 10 generates new parking lot data and registers it in the map DB 13 . At this time, in the new parking lot data, a new ID is assigned, the coordinates of the start point of off-road travel are set to "latitude" and "longitude," and the traveling direction of the vehicle 3 at the start point of off-road travel is is set as "azimuth", and the name of the facility closest to the start point of off-road driving is set as "name".

Thus, when the parking lot is newly registered in step S13, or when it is determined that the parking lot has been identified in step S12, the server 10 extracts off-road driving data from the probe data, (step S14). In the example of FIG. 2, the data of the point where the road type is "-1" is saved as off-road travel data.

Next, the server 10 uses the off-road travel data to execute an estimation process (step S15). FIG. 5B is a flowchart of estimation processing. First, the server 10 acquires off-road travel data obtained for the same parking lot from the probe DB 14 (step S31). Next, the server 10 generates a driving surface based on each off-road driving data (step S32). Here, the "driving surface" is a surface having a certain distance centered on the coordinates included in the off-road driving data. Now, assuming that off-road travel data has a trajectory 42 shown in FIG. A running surface 44 having a width of about the width is generated. The server 10 generates such a driving surface 44 for each off-road driving data.

Then, the server 10 spatially combines the plurality of running surfaces 44 generated in step S32 to estimate the parking lot area (step S33). FIG. 8 shows an example of estimating a parking lot area from a plurality of driving surfaces 44, showing a plurality of driving surfaces 44 obtained in the same parking lot. In this example, an area where the vehicle 3 is moving linearly to some extent and an area where the vehicle 3 turns and parks can be distinguished. Therefore, the server 10 estimates an area where the vehicle 3 is parked after changing direction as the parking area 51, and estimates an area where the vehicle 3 is moving linearly to some extent as the traveling area 52b. In addition, in the example of FIG. 8, two parking areas 51a and 51b are obtained, and corresponding two driving areas 52a and 52b are obtained.

In general, when a vehicle is parked, it moves to a parking position at a certain speed, but when the vehicle is parked after changing direction, the speed of the vehicle is sufficiently low. Therefore, not only the positional coordinates of the vehicle 3 but also the vehicle speed in off-road travel data may be taken into account to distinguish between the parking area 51 and the travel area 52 .

Also, by combining one or more parking areas 51 and one or more driving areas 52 thus obtained, the shape of the entire parking lot can be estimated. In the example of FIG. 8, the overall shape of the parking lot is approximately the shape indicated by dashed line 48 . When the parking area is estimated in this manner, the parking area estimation process ends.

As described above, according to this embodiment, the parking lot area can be estimated based on the probe data of a plurality of vehicles, that is, the travel histories. In addition to the overall shape of the parking lot area, it is also possible to distinguish between a driving area and a parking area within the parking lot area.

[Estimation of degree of congestion]
Next, a method for estimating the degree of congestion of a parking lot based on the distribution of parking positions within the parking lot area will be described. By dividing the parking position of the vehicle for each time zone, the distribution of the parking position for each time zone is obtained. Basically, when a parking lot is empty, drivers tend to park their vehicles in convenient areas of the parking lot. For example, in a parking lot attached to a facility such as a store, parking spaces often fill up from the area closer to the facility. On the other hand, when the parking lot is congested, most convenient areas are already full, so drivers are forced to park their vehicles in other areas, i.e., in randomly generated vacant spaces. I don't get it. As a result, the parking positions of vehicles tend to be highly random and dispersed throughout the parking lot. Therefore, by analyzing the distribution of parking positions of vehicles in the parking lot, it can be estimated that the parking lot is empty when the parking positions of the vehicles are concentrated in a part of the area. On the other hand, when the parking positions of the vehicles are dispersed throughout the parking lot, it can be estimated that the parking lot is congested.

FIG. 9 is a flowchart of processing for analyzing the degree of congestion based on parking positions of vehicles. This processing is performed by the server 10 . First, the server 10 receives probe data from the navigation device 20 of the vehicle 3 (step S41).

Next, the server 10 acquires the coordinates of the parking position of the vehicle 3 for each time period from the probe data (step S42). For example, the server 10 divides a day into three periods of morning, noon, and night, and acquires the coordinates of the parking position of the vehicle for each time period. Then, the server 10 calculates the degree of concentration of the parking positions based on the acquired coordinates of the parking positions, and estimates the degree of congestion for each time zone (step S43). Then the process ends. As a result, the degree of congestion of the parking lot can be obtained for each time period.

Next, a method for calculating the degree of concentration of parking positions will be described. The degree of concentration of parking positions can be calculated by any of the following first to third methods.

(First method)
A first method of calculating the degree of concentration utilizes a standard deviation ellipse. That is, the server 10 obtains the standard deviation ellipse based on the coordinates of the parking position obtained in step S42, and calculates the area of the predetermined ratio. For example, find the area of 90% of the standard deviation ellipse. Basically, when the parking positions are concentrated, the area of the standard deviation ellipse is small, and when the parking positions are scattered, the area of the standard deviation ellipse is large. Therefore, the server 10 compares the area of a predetermined percentage of the standard deviation ellipse with a predetermined threshold, and if it is smaller than the threshold, the degree of concentration is high, that is, it is estimated that the parking lot is vacant, and if it is larger than the threshold, assumes that the concentration is low, i.e., the parking lot is congested. Thus, the degree of congestion for each time period can be estimated based on the coordinates of the parking position for each time period.

In the above example, one threshold is used to classify the degree of parking lot congestion into two categories: "empty" and "congested." The congestion degree of the parking lot may be classified into three or more levels. For example, two thresholds may be used to classify the congestion degree of the parking lot into three levels: "empty", "normal", and "congested".

In addition, since the method using the area of the standard deviation ellipse is a method of calculating the degree of concentration in one location in the entire parking lot, if there are multiple concentration points in the entire parking lot, cannot be applied. However, if the entire parking lot is divided into multiple parking areas and the area of the standard deviation ellipse is calculated for each parking area, it can also be applied when parking locations are concentrated in multiple locations in the entire parking lot. It is possible.

(Second method)
A second method of calculating the degree of concentration uses the nearest neighbor distance method, which is one of spatial analysis techniques. The nearest neighbor distance method is a method of classifying point distributions from the standpoint of distributed type and concentrated type, and obtains an "average nearest neighbor distance W" from distributions of a plurality of points. Here, the average nearest neighbor distance W is the average value of the distances from each point to the closest point, and is obtained by the following formula.

である。 Here, as a classification criterion for each distribution, consider a case where points are randomly distributed on a plane of area S (follow uniform Poisson distribution). The expected value of the average nearest neighbor distance W at this time is

is.

と判断すればよい。なお、この手法は１つの駐車場内に複数の集中地点が存在する場合でも適用することができる。 Therefore,

should be judged. It should be noted that this method can be applied even when a plurality of concentration points exist within one parking lot.

(Third method)
A third method for calculating the degree of concentration uses the K-function method, which is one of spatial analysis techniques. The K-function method is a technique for identifying distributions that cannot be discriminated by the nearest neighbor distance method, and the K-function K(h) is obtained from the distribution of a plurality of points using the following formula.

である。 By using the K-function, it is possible to determine on what scale (spatial range) the points are concentrated/dispersed. If the points are randomly distributed, the expected value of the K-function is

is.

と判断すればよい。なお、この手法は１つの駐車場内に複数の集中地点が存在する場合でも適用することができる。 Therefore, on a scale of the order of a circle of radius h,

should be judged. It should be noted that this method can be applied even when a plurality of concentration points exist within one parking lot.

In the above example, one day is divided into morning, noon, and night as time zones, but application of the present invention is not limited to this. For example, one day may be divided into daytime and nighttime, or may be divided into hourly intervals. Also, one week may be divided into seven days from Monday to Sunday. Furthermore, one year may be divided into monthly units, or one year may be divided into four seasons. The term "time zone" in the present invention is a concept that includes not only cases where a certain period is divided by time, but also cases where it is divided by days of the week and months.

Also, in the above example, the congestion degree is estimated for each time period, but the congestion degree may be estimated without limiting the time period.

3 Vehicle 10 Server 12 Control Unit 13 Map DB
14 Probe DB
20 Navigation device

Claims (1)

an acquisition unit that acquires position information including a parking position from a mobile object;
an estimating unit for estimating parking lot information related to a parking lot existing in the off-road area based on position information of a plurality of moving bodies that have entered the off-road area;
with
The estimation unit is an information processing device that estimates the degree of congestion of the entire parking lot based on the parking position.

Images