WO2009157298A1 - Parking assistance device, and parking guidance apparatus employing the same - Google Patents

Parking assistance device, and parking guidance apparatus employing the same Download PDF

Info

Publication number
WO2009157298A1
WO2009157298A1 PCT/JP2009/060441 JP2009060441W WO2009157298A1 WO 2009157298 A1 WO2009157298 A1 WO 2009157298A1 JP 2009060441 W JP2009060441 W JP 2009060441W WO 2009157298 A1 WO2009157298 A1 WO 2009157298A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking
vehicle
distance
feature
distance image
Prior art date
Application number
PCT/JP2009/060441
Other languages
French (fr)
Japanese (ja)
Inventor
柿並俊明
里中久志
Original Assignee
アイシン精機株式会社
トヨタ自動車株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by アイシン精機株式会社, トヨタ自動車株式会社 filed Critical アイシン精機株式会社
Publication of WO2009157298A1 publication Critical patent/WO2009157298A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62D—MOTOR VEHICLES; TRAILERS
    • B62D15/00—Steering not otherwise provided for
    • B62D15/02—Steering position indicators ; Steering position determination; Steering aids
    • B62D15/027—Parking aids, e.g. instruction means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30264—Parking

Definitions

  • the present invention relates to a parking support device that supports parking of a vehicle and a parking guidance device that uses the parking support device.
  • parking assistance that assists the driver to smoothly park the vehicle in the target vehicle space when a driver with insufficient vehicle parking technology parks the vehicle or parks the vehicle in the first parking space.
  • devices for example, Patent Documents 1-4).
  • the parking type determination device described in Patent Document 1 automatically determines the parking type without depending on detailed instructions from the driver.
  • a signal indicating that the parking operation is being performed is sent from the parking intention acquisition unit to the surrounding state acquisition unit, and the surrounding state acquisition unit outputs a signal related to the surrounding state to the parking type determination unit.
  • the signal related to the surrounding situation includes a signal indicating whether or not the position of the own vehicle is on the road, a signal indicating the direction of the road edge or the angle between the road direction and the own vehicle direction (and the distance between the own vehicle and the road edge). ), And at least one of signals indicating the angle between the parking frame direction and the host vehicle direction (and the distance between the host vehicle and the parking frame center line).
  • the parking type determination means determines the parking type (parallel parking or parallel parking) based on the signal related to the surrounding situation output by the surrounding situation acquisition means, and outputs the parking type to a parking assistance system such as a voice guide.
  • the parking assist device described in Patent Document 2 recognizes an accurate parking area and parks the vehicle in the parking area.
  • the parking assist device uses a length detection device composed of an ultrasonic sensor to determine the total length of a parked vehicle that is already parked along the roadside and the length of a parking area that is formed behind the parked vehicle.
  • the full width of the parked vehicle is estimated from the detected total length of the parked vehicle. Based on the detected length of the parkable area, the total length of the parked vehicle, and the estimated full width of the parked vehicle, a driving operation necessary to park the vehicle in the parkable space is calculated and notified.
  • the obstacle detection device described in Patent Document 3 determines the distance between an obstacle such as a curb and the vehicle body and informs the driver so that the vehicle can clearly perform guidance such as side-by-side parking. Described for the device.
  • the obstacle detection device uses an ultrasonic distance sensor mounted near the left front wheel and the left rear wheel of the vehicle to determine the approach distance between the vehicle body and the curb in three stages: “safety”, “caution”, and “danger”. Judge with.
  • the vehicle retraction support apparatus described in Patent Document 4 is described with respect to a vehicle retraction support apparatus at the time of parallel parking, in which a driver grasps the timing and amount of steering when parallel parking is performed.
  • the vehicle reverse assist device operates the seesaw switch until the vertical guide line overlaps the target point that is the corner of the parking space frame on the screen at the stop position of the vehicle, and holds the handle until the vehicle space mark overlaps the parking space. Turn the vehicle backward while maintaining the steering angle of the steering wheel. Then, when the eye mark overlaps the parking space, the vehicle is stopped, and the vehicle is moved backward by maximizing the steering angle of the steering wheel in the opposite direction.
  • the parking type determination apparatus it is determined whether or not the vehicle is on the road by using information such as map data, gyroscope, and traveling locus, and the parking frame is automatically recognized by some method ( The content of automatic recognition is not disclosed at all). For example, if the vehicle is on the road and is within a predetermined angle with the direction of the road, the driver determines that parallel parking is desired, so the type of parking can be determined. However, since the structure of the road is not directly measured on an actual road, and the parking frame detection method is not disclosed at all, the direction of the own vehicle is accurately aligned with the direction of the road, and the cars are parked in an orderly manner. There is a problem that can not be.
  • the length of a parked vehicle and the parking possible area is measured using an ultrasonic sensor, The full width of the parked vehicle is estimated from the full length of the obtained parked vehicle, and parking space Is calculated.
  • the parked vehicles are not necessarily parked in order along the road, even if the parked vehicle is parked in the target parking position based on the position and direction of the parking space obtained here, orderly parking along the road There is a problem that can not be.
  • the distance between the left front wheel and the curb during forward driving and the left rear wheel and the curb during reverse travel The distance can be provided to the driver.
  • the road surface and curb are detected using an ultrasonic sensor, and the approaching distance to the obstacle is determined in three stages: “safety”, “caution”, and “danger”.
  • the azimuth resolution of an ultrasonic sensor is not high, the distance information can be used when an obstacle is approaching, but it is possible to detect the position and azimuth of a curb that is located several meters to 10 meters away. Can not. For this reason, there is a problem that it cannot be used as a sensor for orderly parking along the road.
  • the target parking frame on the screen is operated with a seesaw switch so that the parking space displayed on the image is matched with the position where parking is desired.
  • this system assumes that the vehicle is stopped parallel to the direction of the road. For this reason, when the stopped vehicle is not parallel to the road, the target parking position is not parallel to the direction of the road, and there is a problem that orderly parking cannot be performed along the road.
  • the objective is to provide the parking assistance apparatus which can park orderly in a parking space by using the sensor which can acquire a distance image.
  • a characteristic configuration of a parking assist device is to detect a distance between an edge of an object attached to a road surface on which the vehicle is located and the vehicle in order to assist parking of the vehicle. Based on the distance detection unit mounted on the vehicle and the distance between the object edge detected by the distance detection unit and the vehicle, whether the feature is a linear feature or a long feature And a feature specifying unit that creates feature information indicating the feature and a parking target specifying unit that specifies a parking target based on the feature information.
  • the distance detection unit is a distance image sensor that acquires a distance image including at least distance information from the vehicle to the edge.
  • the distance image sensor acquires a distance image including distance information, so that the distance from the vehicle to the edge can be easily detected. Therefore, the parking target can be easily identified based on the distance image.
  • the parking target specifying unit sets the parking target to be positioned in parallel to the feature based on the feature information.
  • the parking target can be parked in an orderly manner.
  • the feature is at least one of a curbstone, a gutter, a guard rail, a wheel stop block, and a structure.
  • the parking target can be easily specified.
  • the characteristic configuration of the empty vehicle guidance device according to the present invention is that the parking support device according to the present invention and parking guidance means for guiding the vehicle to the specified parking target are provided.
  • parking in the parking space can be performed easily and appropriately.
  • FIG. 1 is a block diagram schematically showing a schematic configuration of a parking guide device 2 provided with a parking assistance device 1 according to the present invention.
  • the parking assist device 1 has a function of assisting in orderly parking the vehicle 100 in the parking space when the vehicle 100 is parked in the parking space.
  • the parking guidance device 2 has a function of appropriately guiding the vehicle 100 to the parking space based on the result obtained by the parking assistance device 1. This embodiment demonstrates as an example in case the parking guidance apparatus 2 provided with the parking assistance apparatus 1 is provided in the vehicle 100.
  • FIG. 1 is a block diagram schematically showing a schematic configuration of a parking guide device 2 provided with a parking assistance device 1 according to the present invention.
  • the parking assist device 1 has a function of assisting in orderly parking the vehicle 100 in the parking space when the vehicle 100 is parked in the parking space.
  • the parking guidance device 2 has a function of appropriately guiding the vehicle 100 to the parking space based on the result obtained by the parking assistance device 1.
  • This embodiment demonstrates as an example in
  • the parking assistance device 1 includes a distance detection unit 10, a vehicle position detection unit 11, a series distance image generation unit 12, a road surface estimation unit 13, a feature determination unit 14, a feature specification unit 15, and a parking target specification unit 16.
  • the parking guide device 2 includes the parking support device 1 and the parking guide means 20 described above.
  • the parking assistance device 1 and the parking guidance device 2 are constructed with hardware or software or both of the functional units for performing various processes related to parking assistance and parking guidance with the CPU as a core member.
  • the structure of each part of the parking guidance apparatus 2 provided with this parking assistance apparatus 1 is demonstrated.
  • the distance detection unit 10 is mounted on the vehicle 100 so as to detect the distance between the edge E of the object attached to the road surface on which the vehicle 100 is located and the vehicle 100.
  • the road surface on which the vehicle 100 is located is the road surface on which the tire of the vehicle 100 is located.
  • the object attached to the road surface corresponds not only to an object that forms irregularities on the road surface (for example, curbstones or side grooves), but also to an object (for example, a guard rail) that is positioned along the road surface without contacting the road surface. Therefore, the edge E indicates an intersection formed by the road surface and the object or an end of the object.
  • the distance detection unit 10 is preferably a distance image sensor that acquires a distance image including at least distance information from the vehicle 100 to the edge E.
  • the distance image sensor of the active optical system will be described.
  • the distance image sensor measures, for each pixel, the time from when the light is irradiated from the distance image sensor until the light hits an object existing in the detection range and is reflected back. Based on this measurement result, it is possible to display each pixel constituting the image of the object by including distance information indicating the distance to the object. That is, the distance image that is output from the distance image sensor is an image obtained by arranging distance information as pixels.
  • the distance detection unit 10 will be described as the distance image sensor 10.
  • the distance image includes distance information. If there is an area in the distance image that has distance information that makes the distance away from the vehicle 100 at a certain rate, the area is identified as a plane. On the other hand, if there is a part having distance information in which the ratio changes in the area having distance information whose distance increases at a certain ratio, it is specified that the part has unevenness due to the object. In particular, the part that suddenly changes from the one in which the distance increasing distance is constant is identified as the edge E of the object.
  • the distance image sensor 10 acquires such a distance image. The acquired distance image is transmitted to a series of distance image generation unit 12 described later.
  • the distance image sensor 10 is provided in the vehicle 100 in order to detect a parking space for parking the vehicle 100.
  • This embodiment demonstrates as an example in the case of parking the vehicle 100 in parallel. Therefore, the distance image sensor 10 is provided on the side surface of the vehicle 100 as shown in FIG.
  • the distance image sensor 10 is provided on the side surface of the front bumper or the front fender. Further, the detection region R detected by the distance image sensor 10 has a surface spread of a predetermined angle ⁇ .
  • FIG. 2 an example in which the distance image sensor 10 is provided on the side surface of the front bumper of the vehicle 100 and a parking space in which the vehicle 100 is parked in parallel is detected.
  • FIG. 3A shows that the vehicle A and the vehicle B are parked on the end of the road L formed adjacent to the sidewalk W. Further, it is shown that the vehicle 100 is traveling along the arrow direction in order to detect a parking space where parallel parking is performed.
  • the distance image sensor 10 detects the side surface portion of the vehicle A as shown in FIG.
  • the detection region R has a surface spread of a predetermined angle ⁇ as described above, but also has a height spread of a predetermined angle ⁇ as shown in FIG. Therefore, the distance image sensor 10 acquires a distance image in the detection region R having a surface spread formed by the angle ⁇ and a height spread formed by the angle ⁇ .
  • the distance image sensor 10 detects the road L and the sidewalk W in the detection region R as shown in FIG.
  • the distance image includes the edge E of the curb C formed at the boundary between the road L and the sidewalk W.
  • the detection region R includes a side groove M located at the boundary between the road L and the sidewalk W
  • the distance image obtained by the distance image sensor 10 includes the road L and the sidewalk W. And an edge E of the side groove M formed at the boundary.
  • the distance image obtained by the distance image sensor 10 used in the present embodiment is not a continuous continuous image, but a set of still images acquired every predetermined time according to the movement of the vehicle 100. . That is, the distance image is acquired when the vehicle 100 is positioned at the position y and the distance image S at the acquisition time t1 acquired when the vehicle 100 is positioned at the position x, as shown in FIG. It consists of a distance image T at time t2 and a distance image U at acquisition time t3 acquired when it was located at position z. Each distance image includes a time stamp indicating an acquisition time, and is transmitted to a series of distance image generation unit 12 described later.
  • the own vehicle position detection unit 11 detects a position coordinate and an azimuth indicating the current position of the vehicle 100 every time the vehicle 100 moves a predetermined distance.
  • the own vehicle position detection unit 11 includes, for example, a GPS receiver 11a, a distance sensor 11b, and an orientation sensor 11c, and detects position information and orientation based on these output signals.
  • the GPS receiver 11 a is a device that receives a GPS signal from an artificial satellite every predetermined time, and the received signal is output to the vehicle position detection unit 11.
  • the own vehicle position detection unit 11 analyzes the GPS signal and calculates the latitude and longitude where the vehicle 100 exists.
  • the own vehicle position detection unit 11 can also detect the moving speed from the latitude and longitude before the predetermined time and the newly calculated latitude and longitude.
  • the distance sensor 11b includes, for example, a vehicle speed pulse sensor that outputs a pulse signal each time a drive shaft or wheel of the vehicle 100 rotates by a certain amount, a G sensor that detects acceleration received by the vehicle, an integration circuit, and the like.
  • the distance sensor 11b calculates a vehicle speed and a moving distance based on information obtained from these various sensors.
  • the direction sensor 11c is a sensor that detects the traveling direction of the vehicle 100. For example, a gyro sensor, a geomagnetic sensor, a rotation sensor disposed in a rotating part of a handle, a rotary variable resistor, and a wheel part are disposed. Angle sensor or the like.
  • the direction sensor 11c calculates a traveling direction based on sensor signals obtained from these sensors.
  • the own vehicle position detection unit 11 specifies the current position coordinates and direction of the vehicle 100 based on the outputs from the GPS receiver 11a, the distance sensor 11b, and the direction sensor 11c described above.
  • the output is transmitted to the series distance image generation unit 12 as an output.
  • the series distance image generation unit 12 generates a series of distance images from the detection result transmitted from the distance image sensor 10.
  • the distance image sensor 10 acquires a distance image every time the vehicle 100 moves for a predetermined time as described above. Therefore, the distance image transmitted from the distance image sensor 10 is not a continuous image but a still image for every predetermined time. That is, as shown in FIG. 7, the distance image S at the acquisition time t ⁇ b> 1 acquired when it was located at the position x, the distance image T at the acquisition time t ⁇ b> 2 acquired when it was located at the position y, It consists of the distance image U at the acquisition time t3 acquired when it was located at the position z.
  • Such a still image may have overlapping portions (Z1 and Z2 portions) between the distance image S, the distance image T, and the distance image U as shown in FIG.
  • the portions of Z1 and Z2 are, for example, the portion of Z1
  • the distance information of the overlapping portions of the distance image S and the distance image T is averaged
  • the portion of Z2 is the portion of Z2
  • the distance image T It is preferable to average the distance information of overlapping portions of the distance image U.
  • the distance information of only one of the overlapping portions of the distance image S and the distance image T is used, and if it is a portion of Z2, the overlap of the distance image T and the distance image U is used.
  • the distance information of only one of the parts to be used may be used.
  • the series of distance image generation unit 12 generates a series of distance images such as a panoramic image from such a still image state distance image.
  • a series of distance images generated by the series distance image generation unit 12 is transmitted to a road surface estimation unit 13 and a feature determination unit 14 described later.
  • the road surface estimation unit 13 estimates a road surface from a series of distance images transmitted from the series distance image generation unit 12. For this estimation, for example, an area having distance information that moves away at a constant rate as described above may be estimated as a road surface, or a plane area is extracted from a series of images by applying a known plane equation. Then, the plane area may be estimated as the road surface. In this way, information regarding the road surface estimated from the series of distance images is transmitted to the later-described feature determination unit 14 as road surface information.
  • the feature determination unit 14 arranges the objects in a straight line based on the road surface included in the road surface information transmitted from the road surface estimation unit 13 and the edge E included in the distance image acquired by the distance image sensor 10. It is determined whether it is a feature that has been made or a long feature.
  • the object is an object attached to the road surface on which the vehicle is located, and the distance image sensor 10 detects the distance between the edge E of the object and the vehicle 100.
  • the feature arranged in a straight line indicates a feature in which a linear shape is formed by arranging the object regardless of the shape of each object. Specifically, for example, a plurality of ring-stopping blocks arranged in a straight line corresponds.
  • the long feature corresponds to a curbstone, a gutter, a guardrail, or a structure.
  • the feature determination unit 14 has a portion having distance information in which the ratio suddenly changes (or changes greatly) in the area having the distance information such that the distance is increased at a certain rate.
  • the part is determined to be the edge E of the object. And when such an edge E is arrange
  • the feature in the present embodiment is preferably at least one of curb C, gutter M, guardrail, wheel stop block, and structure.
  • Each of these features has predetermined characteristics.
  • the curb stone C is formed with a predetermined height or more and a predetermined length or more.
  • the side groove M is formed to have a predetermined depth or more and a predetermined length or more.
  • a guardrail it has a predetermined height or more and a predetermined shape.
  • it is a ring stop block, it has a height more than predetermined and the length more than predetermined.
  • it is a structure it has a predetermined area.
  • the feature determination unit 14 applies the feature of the feature stored in the feature storage unit to the edge E in the distance image indicating the road surface, and the feature is a feature in which the object is arranged in a straight line or a long length. Judge whether it is a scale-like feature. This determination result is transmitted to the feature specifying unit 15 described later.
  • the feature is described as a curb C for ease of explanation. Therefore, the edge E will be described as the edge E of the curb C.
  • the feature specifying unit 15 specifies whether the feature is a linear feature or a long feature based on the distance between the object edge E detected by the distance image sensor 10 and the vehicle 100. To create (specify) feature information indicating the feature. The identification (determination) of whether or not it is a feature is determined by the above-described feature determination unit 14. Therefore, when the feature determination unit 14 determines that the object having the edge E in the distance image is the curb C, the feature information is specified.
  • the feature information is information including the position, size, and direction of the feature.
  • the feature is the curb C as described above. Therefore, the position is a position where the curb C exists on the road surface, and the size indicates the length, depth, and height of the curb C.
  • the direction indicates the direction in which the curb C is facing. This direction is shown as the direction in which the edge E in the longitudinal direction of the curb C faces.
  • the feature information is specified by the feature specifying unit 15 and transmitted to the parking target specifying unit 16 described later.
  • the feature determination unit 14 and the feature specification unit 15 are configured differently, but the feature specification unit 15 may perform a combination of the determination and specification.
  • the parking target specifying unit 16 specifies a parking target based on the feature information.
  • the feature information is transmitted from the feature specifying unit 15 described above.
  • the parking target is a target provided so that the vehicle 100 can be parked orderly when the vehicle 100 is parked in the parking space.
  • the feature is a curb C
  • a virtual reference line provided in parallel to the curb C can be used.
  • the parking target is a reference line provided in parallel to the curb C, as shown in FIG. 8, it has a predetermined distance margin (for example, 30 cm) from the curb C (the edge E of the curb C). And parallel to the curb C.
  • the curb C itself can be used as a parking target.
  • the parking target specifying unit 16 sets the parking target so as to be positioned in parallel with the feature based on the feature information. The parking target set in this way is transmitted to parking guidance means 20 described later.
  • Parking guidance means 20 guides vehicle 100 to the specified parking target.
  • the parking target is transmitted from the parking target specifying unit 16 described above, and has a predetermined distance margin from the curb C and is set in parallel with the curb C in the present embodiment.
  • the parking guide means 20 guides the vehicle 100 to park along the parking target.
  • Such parking guidance means 20 is configured using a known technique (for example, a technique for performing voice guidance or performing automatic operation). Therefore, detailed description is omitted.
  • a known technique for example, a technique for performing voice guidance or performing automatic operation. Therefore, detailed description is omitted.
  • parallel parking is described as an example of the parking mode of the vehicle 100.
  • the scope of application of the present invention is not limited to this. Even when the parking form is garage parking, it is naturally possible to apply the present invention. In such a case, it is preferable to provide the distance image sensor 10 with the rear of the vehicle facing the rear bumper of the vehicle. By providing the distance image sensor 10 in this manner, the vehicle 100 can be appropriately parked by setting a wheel stop block, a hedge, or the like parallel to the rear bumper of the vehicle 100 as a parking target.
  • the distance image sensor 10 described in the above embodiment need not always be operated. For example, it is naturally possible to adopt a configuration in which detection is started when the driver of the vehicle 100 presses the start switch.
  • the detection region R of the distance image sensor 10 has been described as having a surface spread formed by the predetermined angle ⁇ and a height spread formed by the predetermined angle ⁇ .
  • the predetermined angle ⁇ and the predetermined angle ⁇ can be appropriately changed.
  • the present invention can be preferably implemented by using a vehicle that can detect the positional relationship between the vehicle 100 and the road surface and the features of the road surface, and by setting the installation direction thereof.
  • the feature is described as the curb C.
  • the scope of application of the present invention is not limited to this.
  • the feature is a gutter M
  • the intersection of the road surface and the recess becomes the edge E
  • the feature is a guard rail
  • the end (upper end) of the guard rail becomes the edge E.
  • the feature is a ring stop block or a structure, an intersection formed by the road surface and these features is an edge E.
  • the parking support device 1 has been described as including the own vehicle position detection unit 11 and the series distance image generation unit 12.
  • the scope of application of the present invention is not limited to this.
  • the vehicle position detection unit 11 if the distance image sensor 10 is configured to acquire a distance image so that the distance image to be acquired is a continuous image or a still image even if it is a still image, the vehicle position detection unit 11
  • the series distance image generation unit 12 can be omitted.
  • the parking target specifying unit 16 has been described as setting a reference line as a parking target.
  • the scope of application of the present invention is not limited to this.
  • it may be a reference point. It is naturally possible to park the vehicle 100 in the parking space in an orderly manner based on such a reference point.
  • the distance detection unit 10 has been described as the distance image sensor 10.
  • the scope of application of the present invention is not limited to this.
  • the present invention can be used for a parking support device that supports parking of a vehicle and a parking guidance device using the parking support device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

Disclosed is a parking assistance device that employs a sensor able to acquire distance images to establish a target parking location and allow parking in an orderly manner along a roadside kerb. This vehicle parking assistance device includes a distance detector mounted in the vehicle for detecting the distance between the vehicle and the edge of objects lying on the road surface where the vehicle is located, a feature identifier for identifying features as either linearly arranged or longitudinal in shape, based on the distance between the vehicle and the edge of the object detected by the distance detector to produce feature information denoting these features, and a parking target identifier for identifying a parking target on the basis of this feature information.

Description

駐車支援装置と、当該駐車支援装置を用いた駐車案内装置Parking assistance device and parking guidance device using the parking assistance device
　本発明は、車両の駐車を支援する駐車支援装置と、当該駐車支援装置を用いた駐車案内装置に関する。 The present invention relates to a parking support device that supports parking of a vehicle and a parking guidance device that uses the parking support device.
　例えば、車両の駐車技術が十分でない運転者が駐車する場合や、初めての駐車スペースに車両を駐車する場合等に、目的の車両スペースに円滑に車両を駐車させるように運転者を支援する駐車支援装置がある（例えば、特許文献１－４）。 For example, parking assistance that assists the driver to smoothly park the vehicle in the target vehicle space when a driver with insufficient vehicle parking technology parks the vehicle or parks the vehicle in the first parking space. There are devices (for example, Patent Documents 1-4).
　特許文献１に記載の駐車種類判定装置は、運転者の詳細な指示によらずに駐車種類を自動判定する。当該駐車種類判定装置は、駐車意志取得手段から駐車操作中であることを示す信号が周辺状況取得手段に送られ、当該周辺状況取得手段は周辺状況に関する信号を駐車種類判定手段に出力する。当該周辺状況に関する信号は、自車両の位置が道路上であるか否かを示す信号、道路端の方向又は道路方向と自車両方向のなす角度を示す信号（及び自車両と道路端との距離）、駐車枠方向と自車両方向のなす角度を示す信号（及び自車両と駐車枠中心線との距離）のうち、少なくとも１つ以上からなる。駐車種類判定手段は、周辺状況取得手段が出力する周辺状況に関する信号に基づいて、駐車種類（縦列駐車或いは並列駐車）を判定し、音声ガイド等駐車支援システムに出力する。 The parking type determination device described in Patent Document 1 automatically determines the parking type without depending on detailed instructions from the driver. In the parking type determination device, a signal indicating that the parking operation is being performed is sent from the parking intention acquisition unit to the surrounding state acquisition unit, and the surrounding state acquisition unit outputs a signal related to the surrounding state to the parking type determination unit. The signal related to the surrounding situation includes a signal indicating whether or not the position of the own vehicle is on the road, a signal indicating the direction of the road edge or the angle between the road direction and the own vehicle direction (and the distance between the own vehicle and the road edge). ), And at least one of signals indicating the angle between the parking frame direction and the host vehicle direction (and the distance between the host vehicle and the parking frame center line). The parking type determination means determines the parking type (parallel parking or parallel parking) based on the signal related to the surrounding situation output by the surrounding situation acquisition means, and outputs the parking type to a parking assistance system such as a voice guide.
　特許文献２に記載の駐車アシスト装置は、正確な駐車可能領域の認識を行い、この駐車可能領域に車両を駐車させる。当該駐車アシスト装置は、超音波センサからなる長さ検出装置により、車両が、既に道路脇に沿って駐車している駐車車両の全長及び当該駐車車両の後方に形成されている駐車可能領域の長さを検出し、検出された駐車車両の全長から駐車車両の全幅を推定する。そして、検出された駐車可能領域の長さと、駐車車両の全長と、推定した駐車車両の全幅とに基づいて駐車可能空間に車両を駐車するために必要な運転操作を演算し、報知する。 The parking assist device described in Patent Document 2 recognizes an accurate parking area and parks the vehicle in the parking area. The parking assist device uses a length detection device composed of an ultrasonic sensor to determine the total length of a parked vehicle that is already parked along the roadside and the length of a parking area that is formed behind the parked vehicle. The full width of the parked vehicle is estimated from the detected total length of the parked vehicle. Based on the detected length of the parkable area, the total length of the parked vehicle, and the estimated full width of the parked vehicle, a driving operation necessary to park the vehicle in the parkable space is calculated and notified.
　特許文献３に記載の障害物検出装置は、縁石等の障害物と車体との距離を判断してドライバに知らせ、幅寄せ駐車等の誘導を明確に行わせるようにする車両用の障害物検出装置に関して記載されている。当該障害物検出装置は、車両の左前輪及び左後輪の近くに取り付けられた超音波距離センサにより、車体と縁石との接近距離を、「安全」、「注意」、「危険」の３段階で判断する。 The obstacle detection device described in Patent Document 3 determines the distance between an obstacle such as a curb and the vehicle body and informs the driver so that the vehicle can clearly perform guidance such as side-by-side parking. Described for the device. The obstacle detection device uses an ultrasonic distance sensor mounted near the left front wheel and the left rear wheel of the vehicle to determine the approach distance between the vehicle body and the curb in three stages: “safety”, “caution”, and “danger”. Judge with.
　特許文献４に記載の車両後退支援装置は、運転者が縦列駐車する際の操舵のタイミングと操舵量とを把握する縦列駐車時の車両後退支援装置に関して記載されている。当該車両後退支援装置は、車両の停止位置において、画面上で縦列ガイド線が駐車スペースの枠のコーナーである目標点に重なるまでシーソースイッチを操作し、車両スペースマークが駐車スペースに重なるまでハンドルを切り、ハンドルの操舵角を保持しつつ車両を後退させる。そして、アイマークが駐車スペースに重なったところで車両を停止させ、据え切りでハンドルの操舵角を反対方向へ最大にして車両を後退させる。 The vehicle retraction support apparatus described in Patent Document 4 is described with respect to a vehicle retraction support apparatus at the time of parallel parking, in which a driver grasps the timing and amount of steering when parallel parking is performed. The vehicle reverse assist device operates the seesaw switch until the vertical guide line overlaps the target point that is the corner of the parking space frame on the screen at the stop position of the vehicle, and holds the handle until the vehicle space mark overlaps the parking space. Turn the vehicle backward while maintaining the steering angle of the steering wheel. Then, when the eye mark overlaps the parking space, the vehicle is stopped, and the vehicle is moved backward by maximizing the steering angle of the steering wheel in the opposite direction.
特開２００３－２５２１５０号公報JP 2003-252150 A 特開平６－２８５９８号公報JP-A-6-28598 特開平７－９２２６３号公報JP 7-92263 A 特開２００１－３１５６０４号公報JP 2001-315604 A
　特許文献１に係る駐車種類判定装置では、地図データ、ジャイロ、走行軌跡等の情報を用い、自車が道路上にあるか否かを判定し、また、何らかの方法で駐車枠を自動認識する（自動認識の内容は全く開示されていない）。例えば、自車が道路上に存在し、道路の方向と所定角度以内であれば、運転者は縦列駐車を所望していると判断するので、駐車の種類を判断することができるとしている。しかしながら、現実の道路において道路の構造を直接測定していない為、また、駐車枠の検出方法が全く開示されていないことから、道路の方向に正確に自車の方向を合わせて整然と縦列駐車させることができないという問題がある。 In the parking type determination apparatus according to Patent Document 1, it is determined whether or not the vehicle is on the road by using information such as map data, gyroscope, and traveling locus, and the parking frame is automatically recognized by some method ( The content of automatic recognition is not disclosed at all). For example, if the vehicle is on the road and is within a predetermined angle with the direction of the road, the driver determines that parallel parking is desired, so the type of parking can be determined. However, since the structure of the road is not directly measured on an actual road, and the parking frame detection method is not disclosed at all, the direction of the own vehicle is accurately aligned with the direction of the road, and the cars are parked in an orderly manner. There is a problem that can not be.
　また、特許文献２に係る駐車アシスト装置では、超音波センサを使って、駐車車両と駐車可能領域の長さを測定し、得られた駐車車両の全長から駐車車両の全幅を推定して駐車空間を計算している。しかしながら、駐車車両が道路に沿って整然と駐車しているとは限らないため、ここで得られた駐車空間の位置及び方向に基づいた目標駐車位置に駐車させても、道路に沿って整然とした駐車はできないという問題がある。 Moreover, in the parking assistance apparatus which concerns on patent document 2, the length of a parked vehicle and the parking possible area is measured using an ultrasonic sensor, The full width of the parked vehicle is estimated from the full length of the obtained parked vehicle, and parking space Is calculated. However, because the parked vehicles are not necessarily parked in order along the road, even if the parked vehicle is parked in the target parking position based on the position and direction of the parking space obtained here, orderly parking along the road There is a problem that can not be.
　そして、特許文献３に係る障害物検出装置では、縁石や溝に沿って幅寄せや縦列駐車を行う場合に、前進運転時には左前輪と縁石との距離、また後進時には左後輪と縁石との距離をドライバに提供することができる。超音波センサを用いて路面と縁石とを検出し、障害物までの接近距離が、「安全」、「注意」、「危険」の３段階で判定されるように構成している。しかしながら、超音波センサは方位分解能が高くないため、障害物が接近している場合にはその距離情報は利用できるが、数ｍから１０ｍ程度遠方に存在する縁石の位置や方位を検出することができない。このため、道路に沿って整然とした駐車をさせるためのセンサとしては利用できないという問題がある。 In the obstacle detection device according to Patent Document 3, when performing width alignment or parallel parking along the curb or groove, the distance between the left front wheel and the curb during forward driving and the left rear wheel and the curb during reverse travel The distance can be provided to the driver. The road surface and curb are detected using an ultrasonic sensor, and the approaching distance to the obstacle is determined in three stages: “safety”, “caution”, and “danger”. However, since the azimuth resolution of an ultrasonic sensor is not high, the distance information can be used when an obstacle is approaching, but it is possible to detect the position and azimuth of a curb that is located several meters to 10 meters away. Can not. For this reason, there is a problem that it cannot be used as a sensor for orderly parking along the road.
　更に、特許文献４に係る車両後退支援装置では、画面上の目標駐車枠をシーソースイッチで操作することにより、画像上に映し出されている駐車スペースの駐車したい位置に合うように操作する。しかしながら、このシステムでは、車両は道路の方向に平行に停止していることを前提としている。このため、停止車両が道路に対して平行でない場合は、目標駐車位置も道路の方向に平行とはならず、道路に沿って整然とした駐車はできないという問題がある。 Furthermore, in the vehicle retreat support device according to Patent Document 4, the target parking frame on the screen is operated with a seesaw switch so that the parking space displayed on the image is matched with the position where parking is desired. However, this system assumes that the vehicle is stopped parallel to the direction of the road. For this reason, when the stopped vehicle is not parallel to the road, the target parking position is not parallel to the direction of the road, and there is a problem that orderly parking cannot be performed along the road.
　このように、目標駐車位置を駐車動作前に設定した後に駐車支援動作を開始する装置において、ドライバが期待するように、道路端に沿って整然と車両を駐車させることは容易ではない。本発明は、上記の問題に鑑みてなされたものであり、その目的は、距離画像を取得できるセンサを用いることにより、駐車スペースに整然と駐車できる駐車支援装置を提供することにある。 As described above, in the device that starts the parking support operation after setting the target parking position before the parking operation, it is not easy to park the vehicle orderly along the road edge as the driver expects. This invention is made | formed in view of said problem, The objective is to provide the parking assistance apparatus which can park orderly in a parking space by using the sensor which can acquire a distance image.
　上記目的を達成するための本発明に係る駐車支援装置の特徴構成は、車両の駐車を支援するために、前記車両が位置する路面に付属する物体のエッジと前記車両との距離を検出すべく前記車両に搭載された距離検出部と、前記距離検出部によって検出された前記物体のエッジと前記車両との距離に基づき、直線状に配置された地物、若しくは長尺状の地物か否かを特定して、前記地物を示す地物情報を作成する地物特定部と、前記地物情報に基づいて、駐車目標を特定する駐車目標特定部と、を備えた点にある。 In order to achieve the above object, a characteristic configuration of a parking assist device according to the present invention is to detect a distance between an edge of an object attached to a road surface on which the vehicle is located and the vehicle in order to assist parking of the vehicle. Based on the distance detection unit mounted on the vehicle and the distance between the object edge detected by the distance detection unit and the vehicle, whether the feature is a linear feature or a long feature And a feature specifying unit that creates feature information indicating the feature and a parking target specifying unit that specifies a parking target based on the feature information.
　例えば、撮影画像に対する画像認識により直線状に配置された地物、若しくは長尺状の地物か否かを特定する方法が考えられる。しかしながら、この種の方法にあっては、車両を駐車する駐車スペースの奥行きを算出する場合に、更に複雑な演算処理が必要となる。本特徴構成であれば、距離検出部により物体のエッジと車両との距離を測定するため、車両を駐車する駐車スペースの奥行きを容易に特定することが可能となる。また、直線状に配置された地物、若しくは長尺状の地物の地物情報に基づいて、駐車スペースに対する駐車目標を特定するため、駐車スペースに整然と駐車させることができる。 For example, a method of specifying whether or not the feature is linearly arranged or a long feature by image recognition on the captured image is conceivable. However, this type of method requires a more complicated calculation process when calculating the depth of the parking space where the vehicle is parked. With this feature configuration, since the distance between the edge of the object and the vehicle is measured by the distance detection unit, the depth of the parking space where the vehicle is parked can be easily specified. Moreover, since the parking target with respect to the parking space is specified based on the feature information of the linearly arranged feature or the long feature, the parking space can be parked orderly.
　また、前記距離検出部が、少なくとも前記車両から前記エッジまでの距離情報を含む距離画像を取得する距離画像センサであると好適である。 Further, it is preferable that the distance detection unit is a distance image sensor that acquires a distance image including at least distance information from the vehicle to the edge.
　このような構成であれば、距離画像センサは、距離情報を含んだ距離画像を取得するため、車両からエッジまでの距離を容易に検出することができる。したがって、この距離画像に基づいて駐車目標の特定が容易になる。 With such a configuration, the distance image sensor acquires a distance image including distance information, so that the distance from the vehicle to the edge can be easily detected. Therefore, the parking target can be easily identified based on the distance image.
　また、前記駐車目標特定部は、前記地物情報に基づいて、駐車目標を地物に対して平行に位置するように設定すると好適である。 Further, it is preferable that the parking target specifying unit sets the parking target to be positioned in parallel to the feature based on the feature information.
　このような構成とすれば、例えば自車を駐車させようとしている駐車目標の前後に位置する駐車スペースにおいて、当該駐車スペース内で車両が傾いて駐車している場合であっても、自車を駐車目標に整然と駐車させることが可能となる。 With such a configuration, for example, in a parking space located before and after a parking target for which the vehicle is to be parked, even if the vehicle is tilted and parked in the parking space, The parking target can be parked in an orderly manner.
　また、前記地物が、縁石、側溝、ガードレール、輪止めブロック、構造物のうち少なくとも一つであると好適である。 Further, it is preferable that the feature is at least one of a curbstone, a gutter, a guard rail, a wheel stop block, and a structure.
　このような構成とすれば、容易に駐車目標を特定することができる。 With such a configuration, the parking target can be easily specified.
　また、本発明に係る空車案内装置の特徴構成は、本発明に係る駐車支援装置と、前記特定した駐車目標に前記車両を案内する駐車案内手段と、を備えた点にある。 The characteristic configuration of the empty vehicle guidance device according to the present invention is that the parking support device according to the present invention and parking guidance means for guiding the vehicle to the specified parking target are provided.
　このように本発明に係る駐車支援装置により特定した駐車目標を用いて駐車案内を行うと、容易に且つ適切に駐車スペースに駐車することができる。 As described above, when parking guidance is performed using the parking target specified by the parking assist device according to the present invention, parking in the parking space can be performed easily and appropriately.
本発明に係る駐車支援装置を備えた駐車案内装置の概略構成を模式的に示すブロック図である。It is a block diagram which shows typically schematic structure of the parking guidance apparatus provided with the parking assistance apparatus which concerns on this invention. 距離画像センサの取り付け場所及び検出領域の一例を示す図である。It is a figure which shows an example of the attachment location and detection area | region of a distance image sensor. 検出領域に他の車両が存在する場合の例を示す図である。It is a figure showing an example in case other vehicles exist in a detection field. 検出領域に縁石が存在する場合の例を示す図である。It is a figure which shows the example in case a curb exists in a detection area. 検出領域に側溝が存在する場合の例を示す図である。It is a figure which shows the example in case a side groove exists in a detection area. 距離画像の取得に関して示す図である。It is a figure shown regarding acquisition of a distance image. 距離画像の重複部分に関して示す図である。It is a figure shown regarding the overlapping part of a distance image. 駐車基準に関して示す図である。It is a figure shown about a parking standard. 駐車スペースに車両が整然と駐車されていない場合の例を示す図である。It is a figure which shows the example in case the vehicle is not parked orderly in a parking space. 駐車スペースに車両が整然と駐車されている場合の例を示す図である。It is a figure which shows the example in case a vehicle is parked orderly in a parking space.
　以下、本発明の実施形態について図面に基づいて説明する。図１は、本発明に係る駐車支援装置１を備えた駐車案内装置２の概略構成を模式的に示したブロック図である。駐車支援装置１は、車両１００を駐車スペースに駐車する際に、当該駐車スペースに整然と車両１００を駐車させることを支援する機能を備えている。また、駐車案内装置２は、駐車支援装置１により得られた結果に基づいて、適切に駐車スペースに車両１００を案内する機能を備えている。本実施形態では、駐車支援装置１を備えた駐車案内装置２が車両１００に備えられている場合の例として説明する。 Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram schematically showing a schematic configuration of a parking guide device 2 provided with a parking assistance device 1 according to the present invention. The parking assist device 1 has a function of assisting in orderly parking the vehicle 100 in the parking space when the vehicle 100 is parked in the parking space. In addition, the parking guidance device 2 has a function of appropriately guiding the vehicle 100 to the parking space based on the result obtained by the parking assistance device 1. This embodiment demonstrates as an example in case the parking guidance apparatus 2 provided with the parking assistance apparatus 1 is provided in the vehicle 100. FIG.
　駐車支援装置１は、距離検出部１０、自車位置検出部１１、一連距離画像生成部１２、路面推定部１３、地物判定部１４、地物特定部１５、駐車目標特定部１６から構成される。また、駐車案内装置２は、上述の駐車支援装置１、及び駐車案内手段２０から構成される。ここで、本駐車支援装置１及び駐車案内装置２は、ＣＰＵを中核部材として駐車支援及び駐車案内に関する種々の処理を行うための前記機能部をハードウェア又はソフトウェア或いはその両方で構築されている。以下、本駐車支援装置１を備えた駐車案内装置２の各部の構成について説明する。 The parking assistance device 1 includes a distance detection unit 10, a vehicle position detection unit 11, a series distance image generation unit 12, a road surface estimation unit 13, a feature determination unit 14, a feature specification unit 15, and a parking target specification unit 16. The The parking guide device 2 includes the parking support device 1 and the parking guide means 20 described above. Here, the parking assistance device 1 and the parking guidance device 2 are constructed with hardware or software or both of the functional units for performing various processes related to parking assistance and parking guidance with the CPU as a core member. Hereinafter, the structure of each part of the parking guidance apparatus 2 provided with this parking assistance apparatus 1 is demonstrated.
　距離検出部１０は、車両１００が位置する路面に付属する物体のエッジＥと車両１００との距離を検出すべく車両１００に搭載される。車両１００が位置する路面とは、車両１００のタイヤが位置する路面である。路面に付属する物体とは、路面に対して凹凸を形成する物体のみならず（例えば縁石や側溝）、路面に接触しなくとも路面に沿って位置する物体（例えばガードレール）が相当する。したがって、エッジＥとは、路面と物体とにより形成される交点や、物体の端部を示すものである。 The distance detection unit 10 is mounted on the vehicle 100 so as to detect the distance between the edge E of the object attached to the road surface on which the vehicle 100 is located and the vehicle 100. The road surface on which the vehicle 100 is located is the road surface on which the tire of the vehicle 100 is located. The object attached to the road surface corresponds not only to an object that forms irregularities on the road surface (for example, curbstones or side grooves), but also to an object (for example, a guard rail) that is positioned along the road surface without contacting the road surface. Therefore, the edge E indicates an intersection formed by the road surface and the object or an end of the object.
　ここで、距離検出部１０は、少なくとも車両１００からエッジＥまでの距離情報を含む距離画像を取得する距離画像センサであると好適である。ここでは、アクティブ光学方式の距離画像センサで説明する。当該距離画像センサは、当該距離画像センサから光が照射されてから、当該光が検出範囲内に存在する物体に当たって反射して返ってくるまでの時間を画素毎に測定する。この測定結果に基づき、物体の画像を構成する画素毎に、当該物体までの距離を示す距離情報を含ませて表示することができる。つまり、距離画像センサの出力となる距離画像は、距離情報を画素として並べたものを画像化したものである。以降の説明では、距離検出部１０は、距離画像センサ１０であるとして説明する。 Here, the distance detection unit 10 is preferably a distance image sensor that acquires a distance image including at least distance information from the vehicle 100 to the edge E. Here, the distance image sensor of the active optical system will be described. The distance image sensor measures, for each pixel, the time from when the light is irradiated from the distance image sensor until the light hits an object existing in the detection range and is reflected back. Based on this measurement result, it is possible to display each pixel constituting the image of the object by including distance information indicating the distance to the object. That is, the distance image that is output from the distance image sensor is an image obtained by arranging distance information as pixels. In the following description, the distance detection unit 10 will be described as the distance image sensor 10.
　上述のように、距離画像には距離情報が含まれる。距離画像中に、車両１００から一定の割合で距離が遠ざかるような距離情報を有する領域があれば、当該領域は平面であると特定される。一方、一定の割合で距離が遠ざかるような距離情報を有する領域の中で、その割合が変わる距離情報を有する部分があれば、その部分には物体に起因する凹凸があると特定される。特に、距離が遠ざかる割合が一定であったものから急に変わる部分が、物体のエッジＥであると特定される。距離画像センサ１０は、このような距離画像を取得する。この取得された距離画像は、後述の一連距離画像生成部１２に伝達される。 As described above, the distance image includes distance information. If there is an area in the distance image that has distance information that makes the distance away from the vehicle 100 at a certain rate, the area is identified as a plane. On the other hand, if there is a part having distance information in which the ratio changes in the area having distance information whose distance increases at a certain ratio, it is specified that the part has unevenness due to the object. In particular, the part that suddenly changes from the one in which the distance increasing distance is constant is identified as the edge E of the object. The distance image sensor 10 acquires such a distance image. The acquired distance image is transmitted to a series of distance image generation unit 12 described later.
　距離画像センサ１０は、車両１００を駐車するための駐車スペースを検出するために車両１００に備えられる。本実施形態では、車両１００を縦列駐車させる場合の例として説明する。したがって、距離画像センサ１０は、図２に示されるように車両１００の側面に備えられる。特に、縦列駐車に係る駐車スペースを早期に検出するために、当該距離画像センサ１０は、フロントバンパの側面、又はフロントフェンダ内等に備えると好適である。また、距離画像センサ１０により検出される検出領域Ｒは、所定角度αからなる面広がりを有してなる。 The distance image sensor 10 is provided in the vehicle 100 in order to detect a parking space for parking the vehicle 100. This embodiment demonstrates as an example in the case of parking the vehicle 100 in parallel. Therefore, the distance image sensor 10 is provided on the side surface of the vehicle 100 as shown in FIG. In particular, in order to detect a parking space related to parallel parking at an early stage, it is preferable that the distance image sensor 10 is provided on the side surface of the front bumper or the front fender. Further, the detection region R detected by the distance image sensor 10 has a surface spread of a predetermined angle α.
　図２に示されるように、距離画像センサ１０が車両１００のフロントバンパの側面に備えられ、当該車両１００を縦列駐車させる駐車スペースを検出している場合の例について説明する。図３（ａ）には、歩道Ｗが隣接して形成された道路Ｌの路端に車両Ａ及び車両Ｂが駐車しているが示されている。また、車両１００が、縦列駐車を行う駐車スペースを検出するために、矢印方向に沿って走行していることが示されている。 As shown in FIG. 2, an example in which the distance image sensor 10 is provided on the side surface of the front bumper of the vehicle 100 and a parking space in which the vehicle 100 is parked in parallel is detected. FIG. 3A shows that the vehicle A and the vehicle B are parked on the end of the road L formed adjacent to the sidewalk W. Further, it is shown that the vehicle 100 is traveling along the arrow direction in order to detect a parking space where parallel parking is performed.
　図３（ａ）の場合には、検出領域Ｒ内に車両Ａが位置しているため、距離画像センサ１０は、図３（ｂ）に示されるように車両Ａの側面部を検出する。なお、検出領域Ｒは、上述のように所定角度αからなる面広がりを有しているが、図３（ｂ）に示されるように所定角度βからなる高さ広がりも有している。したがって、距離画像センサ１０は、角度αからなる面広がりと、角度βからなる高さ広がりとからなる検出領域Ｒ内の距離画像を取得する。 In the case of FIG. 3A, since the vehicle A is located in the detection region R, the distance image sensor 10 detects the side surface portion of the vehicle A as shown in FIG. Note that the detection region R has a surface spread of a predetermined angle α as described above, but also has a height spread of a predetermined angle β as shown in FIG. Therefore, the distance image sensor 10 acquires a distance image in the detection region R having a surface spread formed by the angle α and a height spread formed by the angle β.
　次に、車両が矢印方向に沿って移動し、図４（ａ）で示される位置に到達したとする。この場所では、検出領域Ｒ内に車両Ａも車両Ｂも位置していない。したがって、距離画像センサ１０は図４（ｂ）に示されるように道路Ｌと歩道Ｗとを検出領域Ｒに含んで検出する。このような検出領域Ｒを検出した場合には、距離画像に道路Ｌと歩道Ｗとの境界に形成される縁石ＣのエッジＥが含まれる。 Next, it is assumed that the vehicle moves along the direction of the arrow and reaches the position shown in FIG. In this place, neither the vehicle A nor the vehicle B is located in the detection region R. Therefore, the distance image sensor 10 detects the road L and the sidewalk W in the detection region R as shown in FIG. When such a detection region R is detected, the distance image includes the edge E of the curb C formed at the boundary between the road L and the sidewalk W.
　或いは、図５に示されるように、検出領域Ｒ内に道路Ｌと歩道Ｗとの境界に位置する側溝Ｍが含まれる場合、距離画像センサ１０により得られる距離画像には、道路Ｌと歩道Ｗとの境界に形成される側溝ＭのエッジＥが含まれる。 Alternatively, as shown in FIG. 5, when the detection region R includes a side groove M located at the boundary between the road L and the sidewalk W, the distance image obtained by the distance image sensor 10 includes the road L and the sidewalk W. And an edge E of the side groove M formed at the boundary.
　ここで、本実施形態において使用される、距離画像センサ１０により得られる距離画像は、連続する連続画像ではなく、車両１００の移動に応じて、所定時間毎に取得された静止画像の集合である。即ち、距離画像は、図６に示されるように、車両１００が、位置ｘに位置していた時に取得された取得時間ｔ１における距離画像Ｓと、位置ｙに位置していた時に取得された取得時間ｔ２における距離画像Ｔと、位置ｚに位置していた時に取得された取得時間ｔ３における距離画像Ｕとからなる。各距離画像は、取得時間を示すタイムスタンプを含んで後述の一連距離画像生成部１２に伝達される。 Here, the distance image obtained by the distance image sensor 10 used in the present embodiment is not a continuous continuous image, but a set of still images acquired every predetermined time according to the movement of the vehicle 100. . That is, the distance image is acquired when the vehicle 100 is positioned at the position y and the distance image S at the acquisition time t1 acquired when the vehicle 100 is positioned at the position x, as shown in FIG. It consists of a distance image T at time t2 and a distance image U at acquisition time t3 acquired when it was located at position z. Each distance image includes a time stamp indicating an acquisition time, and is transmitted to a series of distance image generation unit 12 described later.
　自車位置検出部１１は、車両１００が所定距離移動する毎に、車両１００の現在位置を示す位置座標と方位とを検出する。自車位置検出部１１は、例えば、ＧＰＳ受信機１１ａ、距離センサ１１ｂ、方位センサ１１ｃから構成され、これらの出力信号に基づいて、位置情報と方位とを検出する。具体的には、ＧＰＳ受信機１１ａは、人工衛星からのＧＰＳ信号を所定時間毎に受信する装置であり、受信された信号は自車位置検出部１１に出力される。自車位置検出部１１は、ＧＰＳ信号を解析し、車両１００が存在する緯度及び経度の演算を行う。更に、所定時間前の緯度及び経度と新しく演算された緯度及び経度から車両１００の方位（進行方位）を検出することも可能である。この自車位置検出部１１は、上述の所定時間前の緯度及び経度と、新しく演算された緯度及び経度とから移動速度を検出することも可能である。 The own vehicle position detection unit 11 detects a position coordinate and an azimuth indicating the current position of the vehicle 100 every time the vehicle 100 moves a predetermined distance. The own vehicle position detection unit 11 includes, for example, a GPS receiver 11a, a distance sensor 11b, and an orientation sensor 11c, and detects position information and orientation based on these output signals. Specifically, the GPS receiver 11 a is a device that receives a GPS signal from an artificial satellite every predetermined time, and the received signal is output to the vehicle position detection unit 11. The own vehicle position detection unit 11 analyzes the GPS signal and calculates the latitude and longitude where the vehicle 100 exists. Furthermore, it is possible to detect the azimuth (traveling azimuth) of the vehicle 100 from the latitude and longitude before the predetermined time and the newly calculated latitude and longitude. The own vehicle position detection unit 11 can also detect the moving speed from the latitude and longitude before the predetermined time and the newly calculated latitude and longitude.
　距離センサ１１ｂは、例えば車両１００のドライブシャフトやホイール等が一定量回転する毎にパルス信号を出力する車速パルスセンサ、車両が受ける加速度の検出を行うＧセンサ及び積分回路等により構成される。距離センサ１１ｂは、これらの各種センサから得られた情報に基づいて車速及び移動距離を演算する。また、方位センサ１１ｃは、車両１００の進行方位を検出するセンサであり、例えば、ジャイロセンサ、地磁気センサ、ハンドルの回転部に配設された回転センサや回転型の可変抵抗、車輪部に配設された角度センサ等からなる。方位センサ１１ｃは、これらのセンサから得られたセンサ信号に基づいて進行方位を演算する。 The distance sensor 11b includes, for example, a vehicle speed pulse sensor that outputs a pulse signal each time a drive shaft or wheel of the vehicle 100 rotates by a certain amount, a G sensor that detects acceleration received by the vehicle, an integration circuit, and the like. The distance sensor 11b calculates a vehicle speed and a moving distance based on information obtained from these various sensors. The direction sensor 11c is a sensor that detects the traveling direction of the vehicle 100. For example, a gyro sensor, a geomagnetic sensor, a rotation sensor disposed in a rotating part of a handle, a rotary variable resistor, and a wheel part are disposed. Angle sensor or the like. The direction sensor 11c calculates a traveling direction based on sensor signals obtained from these sensors.
　自車位置検出部１１は、上述のＧＰＳ受信機１１ａや距離センサ１１ｂや方位センサ１１ｃからの出力に基づいて、車両１００の現在の位置座標と方位とを特定し、自車位置検出部１１の出力として一連距離画像生成部１２に伝達する。 The own vehicle position detection unit 11 specifies the current position coordinates and direction of the vehicle 100 based on the outputs from the GPS receiver 11a, the distance sensor 11b, and the direction sensor 11c described above. The output is transmitted to the series distance image generation unit 12 as an output.
　一連距離画像生成部１２は、距離画像センサ１０から伝達される検出結果から、一連の距離画像を生成する。距離画像センサ１０は、上述のように車両１００が所定時間移動する毎に距離画像を取得する。したがって、距離画像センサ１０から伝達される距離画像は、連続画像ではなく、所定時間毎の静止画像である。即ち、図７に示されるような、位置ｘに位置していた時に取得された取得時間ｔ１における距離画像Ｓと、位置ｙに位置していた時に取得された取得時間ｔ２における距離画像Ｔと、位置ｚに位置していた時に取得された取得時間ｔ３における距離画像Ｕとからなる。このような静止画像は、図７に示されるように距離画像Ｓと、距離画像Ｔと、距離画像Ｕとの間で重複する部分（Ｚ１及びＺ２の部分）が存在する場合がある。 The series distance image generation unit 12 generates a series of distance images from the detection result transmitted from the distance image sensor 10. The distance image sensor 10 acquires a distance image every time the vehicle 100 moves for a predetermined time as described above. Therefore, the distance image transmitted from the distance image sensor 10 is not a continuous image but a still image for every predetermined time. That is, as shown in FIG. 7, the distance image S at the acquisition time t <b> 1 acquired when it was located at the position x, the distance image T at the acquisition time t <b> 2 acquired when it was located at the position y, It consists of the distance image U at the acquisition time t3 acquired when it was located at the position z. Such a still image may have overlapping portions (Z1 and Z2 portions) between the distance image S, the distance image T, and the distance image U as shown in FIG.
　このような場合には、Ｚ１及びＺ２の部分は、例えばＺ１の部分であれば、距離画像Ｓ及び距離画像Ｔの重複する部分の距離情報を平均化し、Ｚ２の部分であれば、距離画像Ｔ及び距離画像Ｕの重複する部分の距離情報を平均化すると好適である。或いは、例えばＺ１の部分であれば、距離画像Ｓ及び距離画像Ｔの重複する部分のうちいずれか一方のみの距離情報を使用し、Ｚ２の部分であれば、距離画像Ｔ及び距離画像Ｕの重複する部分のうちいずれか一方のみの距離情報を使用しても良い。一連距離画像生成部１２は、このような静止画状態の距離画像から、パノラマ画像のような一連の距離画像を生成する。一連距離画像生成部１２により生成された一連の距離画像は、後述の路面推定部１３及び地物判定部１４に伝達される。 In such a case, if the portions of Z1 and Z2 are, for example, the portion of Z1, the distance information of the overlapping portions of the distance image S and the distance image T is averaged, and if the portion of Z2 is the portion of Z2, the distance image T It is preferable to average the distance information of overlapping portions of the distance image U. Alternatively, for example, if it is a portion of Z1, the distance information of only one of the overlapping portions of the distance image S and the distance image T is used, and if it is a portion of Z2, the overlap of the distance image T and the distance image U is used. The distance information of only one of the parts to be used may be used. The series of distance image generation unit 12 generates a series of distance images such as a panoramic image from such a still image state distance image. A series of distance images generated by the series distance image generation unit 12 is transmitted to a road surface estimation unit 13 and a feature determination unit 14 described later.
　路面推定部１３は、一連距離画像生成部１２から伝達される一連の距離画像から、路面を推定する。この推定は、例えば上述のように一定の割合で遠ざかるような距離情報を有する領域を路面として推定しても良いし、公知の平面方程式に当てはめることにより、一連の画像の中から平面領域を抽出し、当該平面領域を路面として推定しても良い。このようにして、一連の距離画像の中から推定された路面に関する情報は、路面情報として後述の地物判定部１４に伝達される。 The road surface estimation unit 13 estimates a road surface from a series of distance images transmitted from the series distance image generation unit 12. For this estimation, for example, an area having distance information that moves away at a constant rate as described above may be estimated as a road surface, or a plane area is extracted from a series of images by applying a known plane equation. Then, the plane area may be estimated as the road surface. In this way, information regarding the road surface estimated from the series of distance images is transmitted to the later-described feature determination unit 14 as road surface information.
　地物判定部１４は、路面推定部１３から伝達される路面情報に含まれる路面と、距離画像センサ１０により取得された距離画像に含まれるエッジＥとに基づいて、物体が、直線状に配置された地物、若しくは長尺状の地物か否かを判定する。物体とは、車両が位置する路面に付属する物体であり、距離画像センサ１０により、その物体が有するエッジＥと車両１００との距離を検出された物体である。直線状に配置された地物とは、夫々の物体の形状に拘らず、その物体を配置することにより、直線形状が形成されている地物を示す。具体的には、例えば直線状に配置された複数の輪止めブロック等が該当する。また、長尺状の地物とは、縁石や側溝やガードレールや構造物が相当する。 The feature determination unit 14 arranges the objects in a straight line based on the road surface included in the road surface information transmitted from the road surface estimation unit 13 and the edge E included in the distance image acquired by the distance image sensor 10. It is determined whether it is a feature that has been made or a long feature. The object is an object attached to the road surface on which the vehicle is located, and the distance image sensor 10 detects the distance between the edge E of the object and the vehicle 100. The feature arranged in a straight line indicates a feature in which a linear shape is formed by arranging the object regardless of the shape of each object. Specifically, for example, a plurality of ring-stopping blocks arranged in a straight line corresponds. Further, the long feature corresponds to a curbstone, a gutter, a guardrail, or a structure.
　地物判定部１４は、上述のように、一定の割合で距離が遠ざかるような距離情報を有する領域の中で、その割合が急に変わる（或いは大きく変わる）距離情報を有する部分があれば、当該部分を物体のエッジＥであると判定する。そして、このようなエッジＥが、直線状に配置されている場合には、直線状に配置された地物であると判定し、エッジＥが長尺状である場合には、長尺状の地物であると判定する。 As described above, the feature determination unit 14 has a portion having distance information in which the ratio suddenly changes (or changes greatly) in the area having the distance information such that the distance is increased at a certain rate. The part is determined to be the edge E of the object. And when such an edge E is arrange | positioned linearly, it determines with the feature arrange | positioned linearly, and when the edge E is elongate, it is elongate Judge as a feature.
　ここで、本実施形態における地物とは、縁石Ｃ、側溝Ｍ、ガードレール、輪止めブロック、構造物のうちの少なくとも一つであると好適である。これらの地物は、夫々所定の特徴を有している。縁石Ｃであれば、所定以上の高さと所定以上の長さとを有して形成される。また、側溝Ｍであれば、所定以上の深さと所定以上の長さとを有して形成される。また、ガードレールであれば、所定以上の高さと所定の形状とを有して形成される。また、輪止めブロックであれば、所定以上の高さと所定以上の長さとを有して形成される。更に、構造物であれば、所定面積を有して形成される。これらの地物は、車両１００からの距離や位置も特徴として有している。このような地物毎の特徴は、地物判定部１４が備える図示しない特徴格納部に格納される。 Here, the feature in the present embodiment is preferably at least one of curb C, gutter M, guardrail, wheel stop block, and structure. Each of these features has predetermined characteristics. In the case of the curb C, the curb stone C is formed with a predetermined height or more and a predetermined length or more. Further, the side groove M is formed to have a predetermined depth or more and a predetermined length or more. Moreover, if it is a guardrail, it has a predetermined height or more and a predetermined shape. Moreover, if it is a ring stop block, it has a height more than predetermined and the length more than predetermined. Furthermore, if it is a structure, it has a predetermined area. These features are also characterized by their distance and position from the vehicle 100. Such features for each feature are stored in a feature storage unit (not shown) included in the feature determination unit 14.
　地物判定部１４は、路面を示す距離画像の中にあるエッジＥを、地物格納部に格納される地物の特徴を当てはめて、物体が、直線状に配置された地物、若しくは長尺状の地物か否かを判定する。この判定結果は、後述の地物特定部１５に伝達される。なお、以降の説明では、説明を容易とするために、地物は縁石Ｃであるとして説明する。したがって、エッジＥは縁石ＣのエッジＥとして説明する。 The feature determination unit 14 applies the feature of the feature stored in the feature storage unit to the edge E in the distance image indicating the road surface, and the feature is a feature in which the object is arranged in a straight line or a long length. Judge whether it is a scale-like feature. This determination result is transmitted to the feature specifying unit 15 described later. In the following description, the feature is described as a curb C for ease of explanation. Therefore, the edge E will be described as the edge E of the curb C.
　地物特定部１５は、距離画像センサ１０によって検出された物体のエッジＥと車両１００との距離に基づき、直線状に配置された地物、若しくは長尺状の地物か否かを特定して、地物を示す地物情報を作成（特定）する。地物か否かの特定（判定）は、上述の地物判定部１４により判定される。したがって、地物判定部１４により距離画像の中にあるエッジＥを有する物体が、縁石Ｃであると判定された場合に、地物情報を特定する。ここで、地物情報とは、地物の位置、大きさ、方位を含む情報である。本実施形態では、上述のように地物は縁石Ｃとしている。したがって、位置とは路面において縁石Ｃが存在する位置であり、大きさとは縁石Ｃの長さ、奥行き、高さを示す。また、方位とは縁石Ｃが向いている方角を示す。この方角は、縁石Ｃの長手方向のエッジＥが向く方角として示される。このようにして地物情報が、地物特定部１５により特定され、後述の駐車目標特定部１６に伝達される。
　尚、上記説明では、地物判定部１４と地物特定部１５とを異なる構成としたが、地物特定部１５がこれらの判定及び特定を総合して行う構成であっても良い。 The feature specifying unit 15 specifies whether the feature is a linear feature or a long feature based on the distance between the object edge E detected by the distance image sensor 10 and the vehicle 100. To create (specify) feature information indicating the feature. The identification (determination) of whether or not it is a feature is determined by the above-described feature determination unit 14. Therefore, when the feature determination unit 14 determines that the object having the edge E in the distance image is the curb C, the feature information is specified. Here, the feature information is information including the position, size, and direction of the feature. In this embodiment, the feature is the curb C as described above. Therefore, the position is a position where the curb C exists on the road surface, and the size indicates the length, depth, and height of the curb C. Further, the direction indicates the direction in which the curb C is facing. This direction is shown as the direction in which the edge E in the longitudinal direction of the curb C faces. In this way, the feature information is specified by the feature specifying unit 15 and transmitted to the parking target specifying unit 16 described later.
In the above description, the feature determination unit 14 and the feature specification unit 15 are configured differently, but the feature specification unit 15 may perform a combination of the determination and specification.
　駐車目標特定部１６は、地物情報に基づいて、駐車目標を特定する。地物情報は、上述の地物特定部１５から伝達される。駐車目標とは、車両１００を駐車スペースに駐車する際に、整然と駐車することが可能なように設けられる目標である。具体的には、地物が縁石Ｃであれば、当該縁石Ｃに対して平行に設けられる仮想的な基準線とすることが可能である。駐車目標を縁石Ｃに対して平行に設けられる基準線とする場合には、図８に示されるように、縁石Ｃ（縁石ＣのエッジＥ）から所定の距離マージン（例えば、３０ｃｍ）を有して、縁石Ｃに対して平行に設定される。また、縁石Ｃ自体を駐車目標とすることも当然に可能である。このように、駐車目標特定部１６は、地物情報に基づいて、駐車目標を地物に対して平行に位置するように設定すると好適である。このようにして設定された駐車目標は、後述の駐車案内手段２０に伝達される。 The parking target specifying unit 16 specifies a parking target based on the feature information. The feature information is transmitted from the feature specifying unit 15 described above. The parking target is a target provided so that the vehicle 100 can be parked orderly when the vehicle 100 is parked in the parking space. Specifically, if the feature is a curb C, a virtual reference line provided in parallel to the curb C can be used. When the parking target is a reference line provided in parallel to the curb C, as shown in FIG. 8, it has a predetermined distance margin (for example, 30 cm) from the curb C (the edge E of the curb C). And parallel to the curb C. Of course, the curb C itself can be used as a parking target. As described above, it is preferable that the parking target specifying unit 16 sets the parking target so as to be positioned in parallel with the feature based on the feature information. The parking target set in this way is transmitted to parking guidance means 20 described later.
　駐車案内手段２０は、特定した駐車目標に車両１００を案内する。駐車目標は、上述の駐車目標特定部１６から伝達され、本実施形態においては縁石Ｃから所定の距離マージンを有し、縁石Ｃに平行して設定される。駐車案内手段２０は、車両１００が、駐車目標に沿って駐車するように案内する。このような駐車案内手段２０は、公知の技術（例えば、音声案内をしたり、自動操作を行ったりする技術）を用いて構成される。このため、詳細説明は省略する。このように、当該駐車目標に沿って車両１００を駐車させると、図９に示されるように、車両１００を駐車させる駐車スペースの前後に駐車されている車両（車両Ａ及び車両Ｂ）に沿って、車両１００も傾いて駐車させてしまうことがなく、図１０に示されるように駐車スペース内に整然と駐車することが可能となる。 Parking guidance means 20 guides vehicle 100 to the specified parking target. The parking target is transmitted from the parking target specifying unit 16 described above, and has a predetermined distance margin from the curb C and is set in parallel with the curb C in the present embodiment. The parking guide means 20 guides the vehicle 100 to park along the parking target. Such parking guidance means 20 is configured using a known technique (for example, a technique for performing voice guidance or performing automatic operation). Therefore, detailed description is omitted. Thus, when the vehicle 100 is parked along the parking target, as shown in FIG. 9, along the vehicles (vehicle A and vehicle B) parked before and after the parking space where the vehicle 100 is parked. The vehicle 100 is not tilted and parked, and the vehicle 100 can be parked orderly in the parking space as shown in FIG.
〔その他の実施形態〕
　上記実施形態では、車両１００の駐車形態として縦列駐車を例として説明した。しかしながら、本発明の適用範囲は、これに限定されるものではない。駐車形態を車庫入れ駐車とした場合でも、本発明を適用することは、当然に可能である。係る場合には、距離画像センサ１０は、車両のリヤバンパに車両後方を向けて設けると好適である。このように距離画像センサ１０を設けることにより、車両１００のリヤバンパに平行した輪止めブロックや生垣等を駐車目標として設定することにより、適切に車両１００を駐車させることが可能である。 [Other Embodiments]
In the above embodiment, parallel parking is described as an example of the parking mode of the vehicle 100. However, the scope of application of the present invention is not limited to this. Even when the parking form is garage parking, it is naturally possible to apply the present invention. In such a case, it is preferable to provide the distance image sensor 10 with the rear of the vehicle facing the rear bumper of the vehicle. By providing the distance image sensor 10 in this manner, the vehicle 100 can be appropriately parked by setting a wheel stop block, a hedge, or the like parallel to the rear bumper of the vehicle 100 as a parking target.
　上記実施形態で説明した距離画像センサ１０は、常に動作させておく必要はない。例えば、車両１００の運転者により起動スイッチが押下されることにより、検出を開始するような構成とすることも当然に可能である。 The distance image sensor 10 described in the above embodiment need not always be operated. For example, it is naturally possible to adopt a configuration in which detection is started when the driver of the vehicle 100 presses the start switch.
　上記実施形態では、距離画像センサ１０の検出領域Ｒは、所定角度αからなる面広がりと、所定角度βからなる高さ広がりとからなるとして説明した。この所定角度α及び所定角度βは、適宜変更することは可能である。また、車両１００と路面との位置関係や、路面の地物を検出することが可能なものを使用し、また、その設置方向を設定することにより、本発明は好適に実施できる。 In the above embodiment, the detection region R of the distance image sensor 10 has been described as having a surface spread formed by the predetermined angle α and a height spread formed by the predetermined angle β. The predetermined angle α and the predetermined angle β can be appropriately changed. In addition, the present invention can be preferably implemented by using a vehicle that can detect the positional relationship between the vehicle 100 and the road surface and the features of the road surface, and by setting the installation direction thereof.
　上記実施形態では、地物は縁石Ｃであるとして説明した。しかしながら、本発明の適用範囲は、これに限定されるものではない。上記実施形態で例示したように、縁石Ｃ以外に、側溝Ｍ、ガードレール、輪止めブロック、構造物等を地物として検出することは当然に可能である。このようにして検出された地物に基づいて、駐車基準を設定することにより、整然と駐車スペースに車両１００を駐車させることは当然に可能である。 In the above embodiment, the feature is described as the curb C. However, the scope of application of the present invention is not limited to this. As exemplified in the above-described embodiment, it is naturally possible to detect the side groove M, the guard rail, the ring stop block, the structure, and the like as the feature other than the curb C. It is naturally possible to park the vehicle 100 in an orderly parking space by setting a parking reference based on the features detected in this way.
　例えば、地物が側溝Ｍであれば、路面と凹部との交点がエッジＥとなり、地物がガードレールであれば、ガードレールの端部（上端部）がエッジＥとなる。また、地物が輪止めブロックや構造物であれば、路面とこれらの地物とにより形成される交点がエッジＥとなる。 For example, if the feature is a gutter M, the intersection of the road surface and the recess becomes the edge E, and if the feature is a guard rail, the end (upper end) of the guard rail becomes the edge E. If the feature is a ring stop block or a structure, an intersection formed by the road surface and these features is an edge E.
　上記実施形態では、本駐車支援装置１は、自車位置検出部１１及び一連距離画像生成部１２を備えているとして説明した。しかしながら、本発明の適用範囲は、これに限定されるものではない。例えば、距離画像センサ１０が、取得する距離画像が連続的な画像であったり、或いは静止画像であっても重複しないように距離画像を取得したりする構成であれば、自車位置検出部１１及び一連距離画像生成部１２を省略することが可能である。 In the above embodiment, the parking support device 1 has been described as including the own vehicle position detection unit 11 and the series distance image generation unit 12. However, the scope of application of the present invention is not limited to this. For example, if the distance image sensor 10 is configured to acquire a distance image so that the distance image to be acquired is a continuous image or a still image even if it is a still image, the vehicle position detection unit 11 In addition, the series distance image generation unit 12 can be omitted.
　上記実施形態では、駐車目標特定部１６は、駐車目標として基準線を設定するとして説明した。しかしながら、本発明の適用範囲は、これに限定されるものではない。例えば、基準点であっても良い。このような基準点に基づいて、整然と車両１００を駐車スペースに駐車することは、当然に可能である。 In the above embodiment, the parking target specifying unit 16 has been described as setting a reference line as a parking target. However, the scope of application of the present invention is not limited to this. For example, it may be a reference point. It is naturally possible to park the vehicle 100 in the parking space in an orderly manner based on such a reference point.
　上記実施形態では、距離検出部１０は距離画像センサ１０であるとして説明した。しかしながら、本発明の適用範囲は、これに限定されるものではない。距離画像センサ１０にかえて、距離情報を取得できる距離検出部１０を用いることにより、本発明を実施することは、当然に可能である。 In the above embodiment, the distance detection unit 10 has been described as the distance image sensor 10. However, the scope of application of the present invention is not limited to this. Of course, it is possible to implement the present invention by using the distance detection unit 10 capable of acquiring distance information instead of the distance image sensor 10.
　本発明は、車両の駐車を支援する駐車支援装置と、当該駐車支援装置を用いた駐車案内装置に利用可能である。 The present invention can be used for a parking support device that supports parking of a vehicle and a parking guidance device using the parking support device.

Claims (5)

  1. 　車両の駐車を支援する駐車支援装置であって、
    　前記車両が位置する路面に付属する物体のエッジと前記車両との距離を検出すべく前記車両に搭載された距離検出部と、
    　前記距離検出部によって検出された前記物体のエッジと前記車両との距離に基づき、直線状に配置された地物、若しくは長尺状の地物か否かを特定して、前記地物を示す地物情報を作成する地物特定部と、
    　前記地物情報に基づいて、駐車目標を特定する駐車目標特定部と、
    を備えた駐車支援装置。     A parking assistance device for assisting parking of a vehicle,
    A distance detection unit mounted on the vehicle to detect a distance between an edge of an object attached to a road surface on which the vehicle is located and the vehicle;
    Based on the distance between the edge of the object detected by the distance detection unit and the vehicle, it is specified whether the feature is a linear feature or a long feature, and the feature is indicated. A feature identification unit for creating feature information;
    A parking target specifying unit for specifying a parking target based on the feature information;
    Parking assistance device with
  2. 　前記距離検出部が、少なくとも前記車両から前記エッジまでの距離情報を含む距離画像を取得する距離画像センサである請求の範囲第１項に記載の駐車支援装置。 The parking assistance device according to claim 1, wherein the distance detection unit is a distance image sensor that acquires a distance image including at least distance information from the vehicle to the edge.
  3. 　前記駐車目標特定部は、前記地物情報に基づいて、駐車目標を地物に対して平行に位置するように設定する請求の範囲第１項又は第２項に記載の駐車支援装置。 The parking support device according to claim 1 or 2, wherein the parking target specifying unit sets the parking target to be positioned in parallel with the feature based on the feature information.
  4. 　前記地物が、縁石、側溝、ガードレール、輪止めブロック、構造物のうち少なくとも一つである請求の範囲第１項から第３項のいずれか一項に記載の駐車支援装置。 The parking assistance device according to any one of claims 1 to 3, wherein the feature is at least one of a curb, a gutter, a guardrail, a wheel stopper block, and a structure.
  5. 　請求の範囲第１項から第４項のいずれか一項に記載の駐車支援装置と、
    　前記特定した駐車目標に前記車両を案内する駐車案内手段と、
    を備えた駐車案内装置。     The parking assistance device according to any one of claims 1 to 4,
    Parking guidance means for guiding the vehicle to the identified parking target;
    Parking guidance device with
PCT/JP2009/060441 2008-06-26 2009-06-08 Parking assistance device, and parking guidance apparatus employing the same WO2009157298A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2008-167808 2008-06-26
JP2008167808 2008-06-26

Publications (1)

Publication Number Publication Date
WO2009157298A1 true WO2009157298A1 (en) 2009-12-30

Family

ID=41444367

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2009/060441 WO2009157298A1 (en) 2008-06-26 2009-06-08 Parking assistance device, and parking guidance apparatus employing the same

Country Status (1)

Country Link
WO (1) WO2009157298A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014174676A1 (en) * 2013-04-26 2014-10-30 トヨタ自動車 株式会社 Parking assist device
JP2019125131A (en) * 2018-01-16 2019-07-25 株式会社豊田自動織機 Unmanned carrier and control method thereof
CN110709910A (en) * 2017-06-07 2020-01-17 三菱电机株式会社 Free space notification device, free space notification system, and free space notification method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006160147A (en) * 2004-12-09 2006-06-22 Nissan Motor Co Ltd Parking support device
JP2007118655A (en) * 2005-10-25 2007-05-17 Nissan Motor Co Ltd Parking supporting device and parking supporting method
JP2007176244A (en) * 2005-12-27 2007-07-12 Aisin Seiki Co Ltd Parking support system
JP2007527007A (en) * 2004-03-05 2007-09-20 キネテイツク・リミテツド Mobility control system
JP2007322357A (en) * 2006-06-05 2007-12-13 Fujitsu Ltd Program, apparatus and method for measuring distance
JP2008055958A (en) * 2006-08-29 2008-03-13 Aisin Aw Co Ltd Parking assist method and parking assist device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007527007A (en) * 2004-03-05 2007-09-20 キネテイツク・リミテツド Mobility control system
JP2006160147A (en) * 2004-12-09 2006-06-22 Nissan Motor Co Ltd Parking support device
JP2007118655A (en) * 2005-10-25 2007-05-17 Nissan Motor Co Ltd Parking supporting device and parking supporting method
JP2007176244A (en) * 2005-12-27 2007-07-12 Aisin Seiki Co Ltd Parking support system
JP2007322357A (en) * 2006-06-05 2007-12-13 Fujitsu Ltd Program, apparatus and method for measuring distance
JP2008055958A (en) * 2006-08-29 2008-03-13 Aisin Aw Co Ltd Parking assist method and parking assist device

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014174676A1 (en) * 2013-04-26 2014-10-30 トヨタ自動車 株式会社 Parking assist device
CN105121231A (en) * 2013-04-26 2015-12-02 丰田自动车株式会社 Parking assist device
JP5975172B2 (en) * 2013-04-26 2016-08-23 トヨタ自動車株式会社 Parking assistance device
CN110709910A (en) * 2017-06-07 2020-01-17 三菱电机株式会社 Free space notification device, free space notification system, and free space notification method
JP2019125131A (en) * 2018-01-16 2019-07-25 株式会社豊田自動織機 Unmanned carrier and control method thereof
JP7000870B2 (en) 2018-01-16 2022-01-19 株式会社豊田自動織機 Automated guided vehicle and its control method

Similar Documents

Publication Publication Date Title
CN110316182B (en) Automatic parking system and method
US10019017B2 (en) Autonomous driving system
JP6304086B2 (en) Automatic driving device
JP6642334B2 (en) Vehicle control device
JP6583061B2 (en) Automatic operation control device
US9540000B2 (en) Acceleration suppression device for vehicle, and acceleration suppression method for vehicle
CN101808852B (en) Control device for a display device of a parking device, and representation method
JP6235528B2 (en) Vehicle control device
CN102470865B (en) For equipment and the method for supported ground parked vehicle
JP4089674B2 (en) Contact derailment avoidance navigation system
CN105416284B (en) Parking assistance device and parking assistance method
US8886364B2 (en) Method and apparatus for determining traveling condition of vehicle
KR102464484B1 (en) Assistant system and assistant method for backward driving of vehicle
JP4661639B2 (en) Driving assistance device
US20130261950A1 (en) Railroad crossing barrier estimating apparatus and vehicle
JP6926976B2 (en) Parking assistance device and computer program
WO2007132860A1 (en) Object recognition device
KR20080109871A (en) Parking assistance device and parking assistance method
CN102596691A (en) Method for support when driving out of a parking space
GB2479998A (en) A parking system for a vehicle
US20140160287A1 (en) Guide method of a reverse guideline system
JP2007309670A (en) Vehicle position detector
JP2009211624A (en) Driving support device, driving support method, and computer program
GB2473551A (en) Parking assist which compensates for distance covered in an undetected direction
JP4052011B2 (en) Parking assistance device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 09770008

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 09770008

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP