JP2015068665A - Map matching device and navigation device including the same - Google Patents

Abstract

PROBLEM TO BE SOLVED: To calculate a traveling position of an own vehicle accurately on map information when a GPS signal has a low accuracy.SOLUTION: A control device 10 is provided that implements: a road characteristic determination function for determining the number of traffic lanes, a lane width, or a lateral width allowance on which an own vehicle is traveling according to an image captured by a camera 300; a peripheral characteristic determination function for determining a peripheral characteristic extracted from the captured image according to an image of an object present around the own vehicle; a road identification function for identifying a road on which the own vehicle is traveling by referring to road characteristic data 2032 within a search area set with reference to a current position, and when a plurality of roads have a correlation value with the determined road characteristic equal to or greater than a predetermined value, by referring to a peripheral characteristic data 2033 within the search area and determining a road having a correlation value with the determined peripheral characteristic equal to or greater than a predetermined value; and a map matching function for calculating the own vehicle's position on map information 2031 according to the map information 2031 including the identified road and an acquired current position.

Description

  The present invention relates to a map matching device that associates a current position of a host vehicle with a position on a map, and a navigation device including the map matching device.

  With regard to this type of device, there is known a traveling state determination device that detects a white line on a road from a captured image in front of the vehicle and determines a current traveling state of the vehicle based on an angle indicating the degree of inclination of the white line and the vehicle. (Patent Document 1).

Japanese Patent No. 4899351

  However, since the prior art method considers only the white line on the road and the angle of the host vehicle, the driving situation of the host vehicle can be determined if the vehicle is traveling on the specified lane. If the current position of the vehicle by the GPS signal deviates from the position in the road width direction, there is a problem that it is difficult to determine the traveling state of the host vehicle because the lane in which the vehicle is traveling cannot be accurately specified.

  The problem to be solved by the present invention is to accurately identify the lane in which the vehicle travels even if the current position of the vehicle based on the GPS signal is shifted in the road width direction with respect to the actual position. Is to accurately calculate the travel position of the host vehicle.

  The present invention determines a road characteristic including any one or more of the number of lanes, lane width, or side margin of a traveling road from a captured image in front of the vehicle, and determines each point and the number of lanes of the road including the point, the lane A plurality of roads whose correlation value with the determined road characteristic is equal to or greater than a predetermined value are extracted with reference to road characteristic data in advance associated with road characteristics including at least one of the width and the side margin. In this case, the peripheral feature extracted according to the image of the object existing around the host vehicle is determined from the captured image in front of the vehicle, and the peripheral feature according to the image of the object existing around each point. Is a road on which the vehicle travels on a road that includes a point that is associated with a peripheral feature whose correlation value with the determined peripheral feature is equal to or greater than a predetermined value. And map information including the identified road is detected. Based on the current position, by calculating the position of the vehicle on the map information, to solve the above problems.

  According to the present invention, even when the current position of the vehicle by the GPS signal is shifted in the road width direction with respect to the actual position, the lane in which the host vehicle is traveling is accurately specified, and the traveling position is determined as map information. Can be associated accurately. As a result, route guidance information based on the accurate current position of the vehicle can be provided to the driver.

It is a block block diagram of the apparatus for vehicles containing the navigation apparatus provided with the map matching apparatus of this embodiment which concerns on this invention. It is a flowchart which shows the control procedure of the route guidance process of the navigation apparatus of this embodiment. FIG. 3 is a flowchart for explaining a control procedure of a road narrowing process based on road characteristics shown in FIG. 2. FIG. FIG. 3 is a flowchart for explaining a control procedure of a road narrowing process based on surrounding features shown in FIG. 2. FIG. 3 is a flowchart illustrating an example of a control procedure of steps S11 to S13 illustrated in FIG.

  Hereinafter, a vehicle device 1000 including a map matching device 100 that calculates a traveling position of the host vehicle on map information and a navigation device 200 including the map matching device 100 will be described with reference to the drawings.

  FIG. 1 is a block configuration diagram of a vehicle device 1000 including a map matching device 100 and a navigation device 200 according to this embodiment of the present invention.

  As shown in FIG. 1, the vehicular device 1000 includes a navigation device 200 and a camera 300. Each device exchanges information with each other via a CAN (Controller Area Network), other in-vehicle LAN, or a wireless communication line.

  The camera 300 is configured using an image pickup device such as a CCD (Charge Coupled Devices), and is installed at different positions outside the vehicle V to capture images around the vehicle. It is preferable to arrange the camera 300 of the present embodiment so that it can capture an image ahead of the vehicle in the traveling direction. Although not particularly limited, the camera 300 of the present embodiment is provided at a predetermined position in front of the vehicle such as the front grille portion, a predetermined position on the left side of the vehicle such as the left side mirror portion, and a right side of the vehicle such as the right side mirror portion. It can be arranged at a predetermined position at a predetermined position in a rear (rear) portion of the vehicle such as a rear finisher portion or a roof spoiler portion. The camera 300 sends the captured image to the map matching apparatus 10 described later. The camera 300 may be provided with a wireless communication function to send a captured image to the outside. The map matching apparatus 100 acquires a captured image captured by the camera 300 via a wireless or wired communication network. The image captured by each camera 300 is given an identifier corresponding to the arrangement (address) of each camera 300, and the map matching apparatus 300 can identify each captured image based on each identifier.

  The navigation device 200 of the present embodiment includes a current position detection device 201, a route search device 202, a storage device 203, an output device 204, and a map matching device 100. Hereinafter, each device will be described.

  The current position detection device 201 of the present embodiment includes a GPS (Global Positioning System) 2011 including a receiver that receives positioning radio waves from a plurality of artificial satellites, and detects the current host vehicle and the traveling direction of the vehicle. And a sensor 2012 for detecting the current position of the host vehicle. The detected current position is sent to the route search device 202 and the map matching device 100.

  The route search device 202 of this embodiment searches for a route from the detected current position or the actual travel position calculated by the map matching device 100 to the destination, and displays the searched route information on the display 2041 and / or the speaker. The data is output via an output device 204 such as 2042. The route search method and the output method of the searched route are not particularly limited, and various methods known at the time of filing can be applied.

  The storage device 203 of the present embodiment stores map information 2031, road characteristic data 2032, and peripheral feature data 2033 in a readable state.

  In the map information 2031, point information, road information, facility information, and the like are associated with a predetermined map coordinate system. The map information 2031 may include road characteristic data 2032 and peripheral feature data 2033 described later.

  In the road characteristic data 2032 of this embodiment, each point and a road characteristic including any one or more of the number of lanes of the road including each point, the lane width, or the side margin width (the width of the roadside belt) are associated in advance. Information. That is, when a certain point is specified, the road to which the point belongs can be specified, and road characteristics including the number of lanes, the lane width, and / or the side margin can be acquired. Conversely, with reference to the road characteristic data 2032, when a road characteristic including the number of lanes, the lane width, and / or the side margin is specified, the correlation between the road characteristic and a predetermined value or more ( It is possible to specify a point on the road having similarity.

  The peripheral feature data 2033 of this embodiment is information in which each point on the road is associated with a peripheral feature corresponding to an image of an object existing around each point in advance. In other words, when an object such as a road sign that can be seen from that point, a road installation such as a signboard, or a sign indicating a facility such as a store is imaged when a certain point is identified, the image derived from the image of the object Can be acquired as peripheral features. Conversely, with reference to the peripheral feature data 2033, when a peripheral feature on an image derived from an image of an object around the host vehicle extracted from a captured image around the host vehicle is specified, It is possible to specify the location of a road having a correlation (similarity) equal to or greater than the value and the road to which the location belongs.

  Next, the map matching apparatus 100 of this embodiment is demonstrated. The map matching device 100 of this embodiment includes a control device 10 that controls a calculation process of the position of the host vehicle on the map information 2031. The control device 10 of the present embodiment executes a ROM (Read Only Memory) 12 in which a program for executing processing for calculating the position of the host vehicle on the map information 2031 is stored, and a program stored in the ROM 12 Thus, a CPU (Central Processing Unit) 11 as an operation circuit that functions as the map matching device 100 and a RAM (Random Access Memory) 13 that functions as an accessible storage device are provided.

  The control device 10 of the map matching apparatus 100 according to the present embodiment includes a current position acquisition function, a captured image acquisition function, a road characteristic determination function, a surrounding feature determination function, a road identification function, and a map matching function. Computer. The map matching apparatus 100 realizes each function by cooperation of software for realizing the above function and the above-described hardware.

  Below, each function which the control apparatus 10 of a map matching apparatus implement | achieves is each demonstrated.

  First, the current position acquisition function will be described. The control device 10 of the map matching device 100 according to the present embodiment acquires the current position detected by the current position detection device 201 described above via a communication network.

  Next, the captured image acquisition function will be described. The control device 10 of the map matching apparatus 100 according to the present embodiment acquires a captured image captured by the camera 300 described above via a communication network. The captured image includes an image ahead of the host vehicle. The “front of the host vehicle” in the present embodiment includes not only the front surface but also the left and right side regions of the front surface (traveling direction).

  The road characteristic determination function will be described. The control device 10 of the map matching apparatus 100 according to the present embodiment determines road characteristics including any one or more of the number of lanes, the lane width, and the side margin width of the road on which the host vehicle travels from the acquired captured image.

  First, the control device 10 determines whether or not a road is included in the captured image. For example, if road-specific features such as lane markers and road markings that distinguish lanes are extracted from the captured image, it can be determined that the captured image includes a road image. Even if lane markers and road markings that divide the lane are not extracted, if there are linear edge groups extending along the direction of travel at the left and right edges of the captured image, both side edges of the road corresponding to the edge groups exist. Therefore, it can be determined that the captured image includes a road image.

  Then, the control device 10 performs predetermined image processing such as extracting edge information from the acquired captured image, lane markers (white line, yellow line, etc.) for distinguishing the edge of the road and the lane on the road, road markings ( Crossing pavement, temporary stop, etc.) are detected, and lanes, lane widths, and road surface signs divided by a pair of lane markers are identified based on the detected pattern of the map, and road characteristics including these are determined. The determined road characteristic is used in a road specifying process described later.

  Further, the control device 10 stores the number of a pair of lane markers that divides the lane in which the host vehicle travels over time, and detects the timing at which the number of lanes divided by the lane marker changes. When the lane increases, it can be predicted that there is a merging lane on the traveling road of the own vehicle, and when the lane decreases, a branch lane exists on the traveling road of the own vehicle. When it is determined from the captured image that there is an increase or decrease in the number of lanes on the road, the control device 10 determines the number of lanes on the road on which the host vehicle is traveling before the increase or decrease is detected. This is because the road on which the host vehicle travels is selected based on the number of lanes before the merge branch of the road occurs. The determined road characteristic is used in a road specifying process described later.

  As described above, the control device 10 determines a road characteristic including one or more of the presence or absence of a road, the number of lanes of the road, the lane width, or the side margin width from the feature extracted from the captured image. . In addition, when there is an increase or decrease in the number of lanes, the control device 10 according to the present embodiment determines the number of lanes before the increase or decrease as road characteristics.

  Next, the peripheral feature determination function will be described. The control device 10 of the map matching device 100 according to the present embodiment determines peripheral features extracted from the acquired captured image according to the image of an object existing around the host vehicle.

  The control device 10 determines whether the captured image includes an image of an object such as a road sign that can be seen from the point, a road sign such as a signboard, a sign indicating a facility such as a store, and the like that serves as a landmark of the position. . For example, if features such as road signs, road installations, and store signs are extracted from the captured image, the captured images include images of solid objects such as road signs, road installations, and store signs. It can be determined that there is an object having characteristics such as a road sign, a road installation, a three-dimensional object such as a store signboard around the vehicle. The determined peripheral feature is used in a road specifying process described later.

  Then, the control device 10 performs predetermined image processing such as extracting edge information from the acquired captured image, and detects an image of an object such as a road sign, a road installation such as a signboard, or a sign indicating a facility such as a store. Then, the type of the object (road sign, road installation, facility sign) is identified based on the detected shape pattern.

  Next, the road identification function will be described. The control device 10 of the map matching apparatus 100 of the present embodiment narrows down the road on which the host vehicle travels based on the road characteristics, and if one road cannot be specified, the host vehicle further travels based on the surrounding features. Identify the road.

  First, the control device 10 sets a search range on the map information 2031 that can be referred to based on the acquired current position. A range within a predetermined distance from the current position may be set as the search range, or a range within a predetermined distance from the current position in the traveling direction may be set as the search range.

  Second, the control device 10 reads road characteristic data 2032 associated with a position within the search range. The road characteristic data 2032 is information in which each point and a road characteristic including any one or more of the number of lanes of the road including the point, the lane width, or the side margin width are associated in advance. The control device 10 refers to the road characteristic data 2032 of the read search range, and selects a road whose correlation value with the road characteristic determined based on the captured image is a predetermined value or more. The correlation value is calculated based on the difference in the number of lanes, the difference in lane width, and the difference in side margin width. In this example, the correlation is defined such that the smaller the value of the difference in the number of lanes, the difference in the lane width, and the difference in the lateral margin width, the higher the correlation value.

  Third, when a plurality of roads are selected in the above process, the control device 10 reads the peripheral feature data 2033 associated with the position within the search range. The peripheral feature data 2033 is information in which each point on the road and a peripheral feature corresponding to an image of an object existing around the point are associated in advance. The image of the object includes an image of text written on the object. For example, place names and road names described in road signs installed at intersections are also included in the peripheral features.

  The control device 10 according to the present embodiment refers to the read surrounding feature data 2033 within the search range, and the host vehicle travels on a road whose correlation value with the surrounding feature determined based on the captured image is a predetermined value or more. Identify the road to be. The correlation value is the commonality of the presence or absence of objects existing around the host vehicle, the commonality of the number of existing objects, the commonality of the information (text, graphics) indicated by the existing objects, the position of the existing objects Calculate based on commonality. The method for extracting the image of the object included in the captured image, the method for counting the number of extracted objects, the method for detecting the position of the extracted object, and the method for recognizing text information and graphic information appearing on the surface of the object are known at the time of filing. Various methods can be applied as appropriate. For example, in a situation where a road sign indicating information on the name of the road and the traveling direction is installed in front of the host vehicle, the camera 300 captures the vicinity of the front of the host vehicle including the road sign. The control device 10 extracts an edge from the captured image of the camera 300, extracts the shape, size, and position on the image of the road sign, and recognizes characters / graphics described on the road sign.

  The peripheral feature data 203 of this embodiment stores text information of each point on the road and an object installed at a peripheral position visible from each point. The control device 10 acquires the text information described in the road sign acquired from the captured image of the camera 300 mounted on the host vehicle, and evaluates the degree of coincidence with the text information of the road sign stored in the peripheral feature data 2033. Then, it is determined that there is a high possibility that the vehicle travels on the road to which the position of the road sign having a high degree of coincidence with the text information described on the road sign belongs.

  Based on the result of the above processing, the control device 10 identifies the road on which the host vehicle travels. Road on which the vehicle travels with weighting for each item of road characteristics including the number of lanes, lane width, lateral margin, shape, position and number of surrounding solid objects, and displayed text and graphics May be specified. In this example, the correlation is defined so that the higher the commonality between the road characteristics and the surrounding features, the higher the correlation value.

  In the present embodiment, the control device 10 stops the road specifying process when the road characteristic determination function described above determines that no road feature is extracted from the captured image. A road feature is a feature on an image peculiar to a road generally observed when a road is imaged by an in-vehicle camera. If no road feature is extracted, it is determined that there is a high possibility that the vehicle is not traveling on the road. In this case, since there is a possibility that the map matching process cannot be executed accurately, the road specifying process is stopped.

  Finally, the map matching function will be described. The control device 10 of the map matching apparatus 100 according to the present embodiment calculates the position of the host vehicle on the map information 2031 based on the road specified in the map information 2031 and the acquired current position. The current position of the host vehicle is mapped on the road identified as the host vehicle traveling (corresponding to map information 2031). Thereby, the position where the host vehicle is traveling can be mapped on the map information 2031 with reference to the road on which the host vehicle is actually traveling.

  In general navigation, when there is an error in the position information of the acquired GPS signal, the position of the host vehicle may be mapped to a road different from the road that is actually running. On the other hand, the map matching apparatus 100 according to the present embodiment has road characteristics such as the number of road lanes, the lane width, and the side margin width (the width of the roadside belt) extracted from the captured image of the camera 300 installed in the vehicle. If the road on which the vehicle is traveling is narrowed down, and if one road cannot be identified, the road on which the vehicle is traveling is identified based on the surrounding features included in the captured image. Even if there is an error in the position information, the traveling road of the host vehicle can be accurately determined.

  The position information of the host vehicle on the map information 2031 is output to the route search device 202, and a route search based on the position information is executed. A position on the map information 2031 of the host vehicle is indicated via the output device 204.

  Subsequently, the control procedure of the map matching process of the present invention will be described with reference to FIGS.

  FIG. 2 is a flowchart showing a control procedure of the entire process up to route guidance including the map matching process.

  First, in step S <b> 10, the control device 10 of the map matching device 100 acquires a captured image of the camera 300. In step S11, the control device 10 narrows down the traveling road based on the road characteristics. In step S12, the control device 10 specifies a traveling road based on the surrounding features. In step S <b> 13, the control device 10 of the map matching device 100 outputs specific information for specifying the traveling road to the navigation device 200. In step S14, the route search device 202 of the navigation device 200 maps the traveling position of the host vehicle on the identified traveling road on the map information 2031. In step S <b> 15, the route search device 202 of the navigation device 200 searches for a route using the mapped travel position as a reference, and outputs the route guidance information via the output device 204.

  Hereinafter, based on FIGS. 3, 4, and 5, each process shown in FIG. 2 will be described in detail. FIG. 3 is a flowchart for explaining the control procedure of the travel road narrowing process based on the road characteristics, and FIG. 4 is a flowchart for explaining the control procedure of the travel road narrowing process based on the surrounding features.

The flowchart of FIG. 3 shows the subroutine of step S11 shown in FIG.
In step S11, a process of narrowing down the traveling road is performed based on the road characteristics acquired from the acquired captured image.

  In step S100 of FIG. 3, the control device 100 performs image processing such as edge extraction on the captured image. In step S <b> 101, the control device 100 determines whether a lane marker such as a white line or a yellow line exists from a captured image including a video of the vehicle front area acquired by the camera 300. Lane markers are formed on the road. If there is a lane marker, it can be determined that there is a road, and therefore it can be determined whether or not the host vehicle exists on the road by the processing in step S101.

  If there is a lane marker in step S101, the process proceeds to step S102, and it is further determined whether or not the lane marker including a white line or a yellow line is interrupted. In this process, if it is determined that the lane marker is interrupted, it can be estimated that the host vehicle is traveling on a single road without an intersection or the like. If the lane marker is not interrupted in the process of step S102, the process proceeds to step S103, and the number of lanes that are classified from the number of lane markers extracted from the captured image is acquired as road characteristics.

  If it is determined in step S102 that the lane marker is interrupted in the middle, the process proceeds to step S108, and further, it is determined whether the number of lane markers is changed in the middle. If the number of lane markers is changed by this process, it can be estimated that the traveling road of the host vehicle is likely to include a branched or merged lane.

  If the number of lane markers does not change in step S108 and there is no branching / merging lane, the process proceeds to step S103, and the number of lanes is acquired from the number of lane markers.

  If the number of lane markers has changed in step S108, the number of lane markers before the change is acquired, and the process proceeds to step S103, where the number of lanes determined from the number of lane markers before the change is Obtained as the number of lanes of road characteristics. For example, when the number of lane markers increases, the traveling road may include a branch lane. The number of lanes classified by the lane marker is acquired as the road characteristic from the number of lane markers with a small number (before change) before another lane branches from the lane in which the host vehicle travels. On the other hand, when the number of lane markers decreases, the traveling road may include a merge lane. The number of lanes classified by the lane marker is acquired as the road characteristic from the number of lane markers having a large number (before change) before the other lanes merge with the lane in which the host vehicle is traveling. Thereby, the road characteristic before the form of a road changes can be extracted from a captured image.

  If the vehicle's traveling road is a single road and the vehicle's traveling road does not include a merge / branch lane, the number of lanes is obtained from the number of lane markers extracted from the captured image captured at the current timing. To do. Further, when the traveling road of the host vehicle includes a merge / branch lane, the number of lanes is acquired from the number of lane markers extracted from the captured image before the branch / merging lane imaged at the past timing appears.

  Returning to step S101, when the image of the lane marker cannot be extracted from the captured image, the control device 10 proceeds to step S106 and determines whether an edge exists on the captured image. This is because if the vehicle is present on the road, edges caused by structures such as both ends of the road, side grooves on the road, blocks, guardrails and the like should be detected.

  In step S104, the control device 10 acquires the lane width from the distance between the pair of lane markers extracted from the captured image.

  If no road lane marker is detected from the captured image in step S101 and no edge derived from the road is detected in step S106, it is assumed that the host vehicle does not exist on the road. Stop processing related to road identification such as comparison and evaluation with characteristic data. This is because map matching processing cannot be performed accurately when the host vehicle is not present on the road but is present in a store or a parking lot. When a road lane marker is not detected from the captured image, the processing relating to the road identification may be stopped immediately.

  In step S <b> 106, when there is an edge due to the road, it can be estimated that the host vehicle may exist on a road where the lane marker is not drawn on the road surface. In this case, the process proceeds to step S107, and the lane width is acquired as the road characteristic from the distance between the edge groups corresponding to the left and right ends of the road. Then, the process proceeds to step S105.

  In step S105, the control device 10 acquires a side margin from the distance between the pair of lane markers extracted from the captured image and the edge group (straight line) corresponding to the road edge image. Through the processing up to step S105, the control device 10 acquires the road characteristics of the road on which the host vehicle travels based on the actually captured image.

  In subsequent step S106, the control device 10 refers to the road specifying data 2032 created and stored in advance. In the present embodiment, the control device 10 reads the road specifying data 2032 corresponding to the search range set with reference to the current position detected by the current position detecting device 201 in the road specifying data 2032. This is because the amount of data to be referred to is reduced to reduce the load of subsequent matching processing.

  In step S107, the control device 10 calculates the degree of correlation between the road characteristics acquired from the captured image of the camera 300 mounted on the host vehicle and the road characteristics data 2032 created in advance. Within the search range, the control device 10 narrows down roads in which the correlation value between the road characteristics acquired from the actual captured image and the road identification data 2032 is equal to or greater than a predetermined value as candidates for the road on which the host vehicle is actually traveling. .

The flowchart of FIG. 4 shows a subroutine of step S12 shown in FIG.
In step S12, a process of narrowing down the traveling road is performed based on the peripheral features acquired from the acquired captured image.

  In step S200 of FIG. 4, the control device 100 performs image processing such as edge extraction on the captured image. In step S <b> 201, the control device 100 extracts image features corresponding to objects such as road signs, store signs, traffic signs, and the like installed at intersections from an image ahead of the vehicle acquired by the camera 300.

  In step S202, the control device 100 refers to the peripheral feature data 2033 created and stored in advance. In the present embodiment, the control device 10 reads peripheral feature data 2033 corresponding to the search range set based on the current position detected by the current position detection device 201 among the peripheral feature data 2033. This is to reduce the load of subsequent matching processing.

  In step S203, the control device 10 calculates the degree of correlation between the peripheral feature acquired from the captured image of the camera 300 mounted on the host vehicle and the peripheral feature data 2033 created in advance. The control device 10 refers to the peripheral feature data in which each point on the road in the search range and the peripheral feature corresponding to the image of the object existing around the point are associated in advance, and correlates with the determined peripheral feature. A road including a point associated with a peripheral feature whose value is equal to or greater than a predetermined value is identified as a road on which the vehicle is traveling. The control device 10 according to the present embodiment evaluates the degree of coincidence between the text information written on the road sign and the text information on the road sign stored in the surrounding feature data, and the degree of coincidence with the text information written on the road sign is The road to which the high road sign position belongs is determined as the road on which the host vehicle is traveling. The control device 10 excludes the road to which the position of the road sign having a low degree of coincidence with the text information written on the road sign belongs to the candidate road for map matching, assuming that the road is not the road on which the vehicle is traveling.

  The map matching apparatus 100 according to the present embodiment refers to the road characteristic data 2032 and the peripheral feature data 3033 within the search range based on the road characteristics and the peripheral features extracted from the captured image, and identifies the traveling road of the host vehicle. .

  The flowchart of FIG. 5 shows an example of the control procedure of steps S11 to S13 shown in FIG.

  As shown in FIG. 5, first, in step S <b> 301, the control device 10 acquires the current position detected by the current position detection device 201. In step S302, a search range including a road candidate that is considered to be traveling by the host vehicle, store candidates that exist around the road, and intersection candidates is set based on the current position. In step S303, the control device 100 refers to the road characteristic data 2032 of the area corresponding to the search range. In step S304, the control device 10 compares the road characteristic acquired from the captured image with the road characteristic data 2032 within the search range, calculates the degree of correlation, and selects a road having a degree of correlation equal to or greater than a predetermined value. Is extracted as a candidate for a road on which the vehicle travels.

  In step S305, the control apparatus 10 determines whether or not there is one road (candidate) associated with the extracted road, that is, the road characteristic acquired from the captured image and the road characteristic indicating a degree of correlation greater than or equal to a predetermined value. Judging. If there is only one road candidate, it can be estimated that the road is a road on which the host vehicle travels, and therefore the process proceeds to step S301, and the road candidate is specified as the traveling road of the host vehicle. The road specific information is sent to the route search device 202 of the navigation device 200.

  On the other hand, when there are two or more road candidates in step S305, the control device 10 proceeds to step S306. In steps S306 and S307, the control device 10 acquires the current position detected by the current position detection device 201, and sets a search range. This position information may be acquired in the process of step S301. Further, the search range may be set in step S302.

  In step S308, the control device 10 refers to the peripheral feature data 2033 of the area corresponding to the search range. In step S309, the control device 10 compares the peripheral characteristics acquired from the captured image with the peripheral feature data 2033 in the search range, calculates the correlation, and the peripheral features with a correlation greater than or equal to a predetermined value are supported. The road to which the attached point belongs is specified as the road on which the vehicle travels. The road specific information is sent to the route search device 202 of the navigation device 200.

  There is a high possibility that a point having a feature having a correlation degree equal to or higher than a predetermined value in both road characteristics and surrounding features and a road to which the point belongs are roads on which the host vehicle is traveling. In the present embodiment, the shape of the object extracted from the captured image, the position, and the display content (text) are limited to the case where the candidate of the traveling road of the own vehicle is first narrowed down by the road characteristics and one road is not specified. Since the traveling road of the own vehicle is specified based on the map, the load of the entire map matching process can be reduced.

  The map matching device 100 and the navigation device 200 configured and functioning as described above have the following effects.

  [1] According to the map matching apparatus 100 according to the present embodiment of the present invention, the lane in which the vehicle travels even when the current position of the vehicle by the GPS signal is shifted in the road width direction from the actual position. Can be accurately identified, the actual traveling position of the host vehicle on the map information 2031 can be calculated, and the traveling position can be accurately associated with the map information. As a result, route guidance information based on the accurate current position of the vehicle can be provided to the driver.

[2] According to the map matching apparatus 100 according to the present embodiment of the present invention, when the road feature is not extracted from the captured image, the road specifying process is stopped, so that the host vehicle is traveling on the road. It is possible to prevent the map matching process from being performed when there is not. In other words, since the map matching process can be performed only when the host vehicle is not traveling on the road, the accuracy of the map matching process can be improved.
Can.

  [3] According to the map matching apparatus 100 according to the present embodiment of the present invention, when it is determined from the captured image that there is an increase or decrease in the number of lanes on the road, the lane of the road on which the host vehicle travels before the increase Since the number is used as the determination result, the road characteristics can be evaluated based on the exact number of lanes before the lane is alternating or branched. As a result, the accuracy of selecting the road on which the host vehicle is traveling can be improved, and the map matching process can be performed accurately.

  [4] The navigation device 200 according to the present embodiment of the present invention can perform an accurate route search based on the corrected position information calculated by the map matching device 100 of the present embodiment.

  The embodiment described above is described for facilitating the understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  In this specification, the map matching apparatus 100 will be described as an example of the map matching apparatus according to the present invention, but the present invention is not limited to this.

  In this specification, the navigation apparatus 100 will be described as an example of the navigation apparatus according to the present invention, but the present invention is not limited to this.

  In this specification, as an example of the map matching device according to the present invention, the map matching device 100 including the control device 10 (computer) having the CPU 11, the ROM 12, and the RAM 13 will be described as an example. However, the present invention is not limited thereto. It is not something.

  In the present specification, one aspect of a map matching apparatus including a current position acquisition unit, a captured image acquisition unit, a road characteristic determination unit, a surrounding feature determination unit, a road identification unit, and a map matching unit according to the present invention. As an example, a map matching device 100 including a control device 10 that executes a current position acquisition function, a captured image acquisition function, a road characteristic determination function, a peripheral feature determination function, a road identification function, and a map matching function is taken as an example. However, the present invention is not limited to this.

  In this specification, as one aspect of the map matching device according to the present invention, the above-described map matching device 100 is connected to the navigation device 200 and the camera 300 via an in-vehicle LAN or a wireless communication network, and is mounted on a vehicle. Although the example which comprises the apparatus 1000 is demonstrated, a map matching apparatus can be comprised as a portable apparatus which can be taken in or taken out from a vehicle. In this case, the map matching device includes wired or wireless communication means capable of exchanging information with each device mounted on the vehicle.

1000 ... Vehicle device 100 ... Map matching device 10 ... Control device 11 ... CPU
12 ... ROM
13 ... RAM
DESCRIPTION OF SYMBOLS 200 ... Navigation apparatus 201 ... Current position detection apparatus 202 ... Route search apparatus 203 ... Memory | storage device 2031 ... Map information 2032 ... Road characteristic data 2033 ... Peripheral feature data 204 ... Output apparatus 300 ... Camera 400 ... Output apparatus

Claims (4)

Current position acquisition means for acquiring the current position of the host vehicle;
Captured image acquisition means for acquiring captured images around the host vehicle;
Road characteristic determining means for determining road characteristics including any one or more of the number of lanes, lane width, or side margin of the road on which the host vehicle travels from the acquired captured image;
Peripheral feature determination means for determining peripheral features extracted according to an image of an object existing around the host vehicle from the acquired captured image;
Within the search range set in the map information based on the acquired current position, road characteristics including any one or more of the number of lanes, the lane width, or the side margin width of each point and the road including the point; Is selected in advance with reference to the road characteristic data, the road characteristic determined by the road characteristic determining means and the correlation value is a predetermined value or more,
When the selected road is one, the extracted road is specified as a road on which the host vehicle is traveling, and when there are a plurality of the selected roads, the search range The peripheral feature data that correlates each point on the road with the peripheral feature corresponding to the image of the object existing around the point is correlated with the peripheral feature determined by the peripheral feature determining means. Road identifying means for identifying a road including a point associated with a peripheral feature whose value is equal to or greater than a predetermined value as a road on the map information on which the vehicle travels;
Map matching means for calculating the position of the vehicle on the map information based on the identified road and the acquired current position;
A map matching device.   The map matching apparatus according to claim 1, wherein the road specifying unit stops the road specifying process when a road feature is not extracted from the captured image.   When it is determined from the captured image that the number of road lanes has increased or decreased, the road characteristic determining means uses the number of lanes of the road on which the host vehicle travels before the increase as a determination result. The map matching apparatus according to claim 1 or 2. The map matching device according to any one of claims 1 to 3,
A route search means for searching for a route to a destination based on the position of the host vehicle calculated by the map matching means;
A navigation device comprising output means for outputting the route.

Images