WO2017061500A1 - Appareil de détection de conditions de conduite - Google Patents

Appareil de détection de conditions de conduite Download PDF

Info

Publication number
WO2017061500A1
WO2017061500A1 PCT/JP2016/079687 JP2016079687W WO2017061500A1 WO 2017061500 A1 WO2017061500 A1 WO 2017061500A1 JP 2016079687 W JP2016079687 W JP 2016079687W WO 2017061500 A1 WO2017061500 A1 WO 2017061500A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
road
information
linear
state
Prior art date
Application number
PCT/JP2016/079687
Other languages
English (en)
Japanese (ja)
Inventor
三島　康之
Original Assignee
いすゞ自動車株式会社
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 いすゞ自動車株式会社 filed Critical いすゞ自動車株式会社
Publication of WO2017061500A1 publication Critical patent/WO2017061500A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems

Definitions

  • This disclosure relates to a driving state detection device.
  • a driving state of the vehicle such as a driver's dozing state or a wobbling state of driving operation.
  • a driving state of the vehicle such as a driver's dozing state or a wobbling state of driving operation.
  • a travel locus of a vehicle is calculated based on the yaw rate and the vehicle speed of the vehicle detected by the yaw rate sensor and the vehicle speed sensor included in the vehicle, and the travel locus and the travel path of the vehicle acquired from the navigation system are calculated.
  • An apparatus for detecting a driver's dozing state based on road alignment is disclosed.
  • the traveling locus of the vehicle calculated by the sensor is merely an estimate, and there is a problem that an accurate traveling locus cannot always be obtained. For this reason, the apparatus in Patent Document 1 has a problem that it may erroneously detect the driving state of the vehicle.
  • the present disclosure has been made in view of these points, and an object thereof is to provide a driving state detection device that can accurately detect the driving state of a vehicle.
  • the driving state detection device includes a first acquisition unit that acquires a plurality of vehicle position information indicating the position of the vehicle, and a second information that acquires the linear information indicating the alignment of the road on which the vehicle is traveling.
  • the driving state detection device acquires vehicle position information indicating the position of the vehicle without estimating the position of the vehicle using the sensor, and detects the wobbling state based on the vehicle position information.
  • the driving state of the vehicle can be detected with high accuracy.
  • the linear information includes a plurality of road position information indicating a road position
  • the detection unit changes a difference between a vehicle position indicated by each of the plurality of vehicle position information and a road position corresponding to the vehicle position.
  • the wobbling state may be detected based on the above.
  • the driving state detection device can accurately detect the wobbling state by using the change in the difference.
  • the detection means extracts a first feature point indicating at least one of an apex and an inflection point in a traveling locus of the vehicle based on a plurality of the vehicle position information, and an apex in the road linearity based on the linear information And a second feature point indicating at least one of the inflection points is extracted, and the wobbling state is detected based on the relationship between the extracted plurality of first feature points and the plurality of second feature points.
  • running state detection apparatus can detect a wobble state efficiently based only on the feature point which shows the characteristic of the driving
  • the detecting means detects the wobbling state based on a trajectory pattern included in a travel trajectory of the vehicle based on a plurality of the vehicle position information and a linear pattern included in the alignment of the road based on the linear information. May be. By doing in this way, the driving
  • the detection means performs frequency analysis on a traveling locus of the vehicle based on a plurality of the vehicle position information, performs frequency analysis on the linearity of the road based on the linear information, and performs the wobbling state based on a difference in each frequency distribution. May be detected.
  • running state detection apparatus can identify the frequency component corresponding to wandering based on the difference of each frequency distribution, and can detect a wandering state accurately.
  • the driving state detection device includes a processor and a memory in which a command is recorded.
  • the driving state detection device performs the following operation on the driving state detection device. Let it run: A plurality of vehicle position information indicating the position of the vehicle is acquired using a position information acquisition device mounted on the vehicle, With reference to the map information stored in the memory, linear information including road position information corresponding to the vehicle position indicated by the acquired vehicle position information is acquired, Based on the vehicle position information and the linear information, it is detected that the driving state of the vehicle is a wobbling state.
  • FIG. 1 is a diagram illustrating a configuration of an operation state detection device.
  • FIG. 2 is a diagram illustrating an example of calculating a difference between a vehicle position and a road position.
  • FIG. 3 is a flowchart illustrating a processing procedure when the driving state detection device detects a wobbling state.
  • FIG. 4 is a diagram illustrating an example in which a wobbling state is detected based on a trajectory pattern and a linear pattern.
  • FIG. 5A is a diagram illustrating an example of a linear frequency distribution of a road corresponding to linear information.
  • FIG. 5B is a diagram illustrating an example of the frequency distribution of the travel locus when the fluctuation is small.
  • FIG. 5C is a diagram illustrating an example of the frequency distribution of the travel locus when the fluctuation is large.
  • FIG. 1 is a diagram illustrating a configuration of the driving state detection device 10.
  • the driving state detection device 10 is, for example, a computer that is mounted on the vehicle 1 and detects that the driving state of the vehicle 1 is a wobbling state.
  • the driving state detection device 10 includes a storage unit 11 that includes a RAM, a ROM, and the like, and a control unit 12 that includes a CPU (Central Processing Unit) and the like.
  • CPU Central Processing Unit
  • the storage unit 11 stores various programs for causing the control unit 12 to function.
  • the storage unit 11 stores digital map information used in the navigation system of the vehicle 1.
  • the digital map information includes a plurality of pieces of linear information indicating the road alignment.
  • Each of the plurality of linear information includes, for example, a plurality of road position information indicating the road position corresponding to the position of the center line of the road and the lane position of the road.
  • “linear” means the shape of a line
  • “road alignment” means the shape of a line connecting the center line or lane position of the road.
  • the control unit 12 includes a first acquisition unit 121, a second acquisition unit 122, a detection unit 123, and a notification unit 124.
  • the first acquisition unit 121 acquires a plurality of vehicle position information indicating the position of the vehicle 1 (hereinafter referred to as a vehicle position).
  • the first acquisition unit 121 uses a global navigation satellite system (GNSS) used in a navigation system (not shown) of the vehicle 1 to perform a predetermined time ( For example, by receiving vehicle position information from an artificial satellite every 100 ms), a plurality of vehicle position information is acquired.
  • GNSS global navigation satellite system
  • the second acquisition unit 122 acquires linear information indicating the alignment of the road on which the vehicle 1 is traveling. Specifically, when the first acquisition unit 121 acquires the vehicle position information, the second acquisition unit 122 refers to the digital map information stored in the storage unit 11 and sets the vehicle position indicated by the acquired vehicle position information. Linear information including corresponding road position information is acquired. For example, the second acquisition unit 122 compares a line formed by connecting a plurality of vehicle positions (hereinafter referred to as “traveling locus”) with a road position indicated by the plurality of road position information, and determines a predetermined amount from the traveling locus. Linear information indicating a road position within the distance is acquired.
  • traveling locus a plurality of vehicle positions
  • the second acquisition unit 122 identifies the traveling direction of the vehicle 1 based on the plurality of vehicle position information acquired by the first acquisition unit 121. Then, linear information corresponding to the specified traveling direction is acquired from the plurality of linear information having different directions.
  • the second acquisition unit 122 may acquire linear information at a time interval longer than the time interval at which the first acquisition unit 121 acquires vehicle position information.
  • the vehicle 1 includes a communication unit that performs wireless communication with an external device or the like, the second acquisition unit 122 may acquire linear information from the external device via the communication unit.
  • the detection part 123 detects that the driving
  • the detection unit 123 is a road corresponding to the vehicle position among the vehicle position indicated by each of the plurality of vehicle position information and the plurality of road positions included in the linear information acquired by the second acquisition unit 122. A difference from the position is calculated, and based on the magnitude of the difference, it is detected that the driving state is a wobbling state.
  • FIG. 2 is a diagram showing an example of calculating the difference between the vehicle position and the road position.
  • a line LV is a travel locus of the vehicle 1
  • a line LR is a linear shape of a road on which the vehicle 1 travels.
  • vehicle positions PV1, PV2, PV3, PV4, and PV5 corresponding to each of the plurality of vehicle position information acquired by the first acquisition unit 121 are shown.
  • the line LR shows a plurality of road positions PR1, PR2, PR3, PR4 and PR5 included in the linear information.
  • the detection unit 123 calculates the difference in position from the nearest road position for each of the plurality of vehicle positions PV1, PV2, PV3, PV4, and PV5.
  • the detection unit 123 includes a difference E1 between the vehicle position PV1 and the road position PR1, a difference E2 between the vehicle position PV2 and the road position PR2, a difference E3 between the vehicle position PV3 and the road position PR3, and the vehicle position.
  • a difference E4 between PV4 and road position PR4 and a difference E5 between vehicle position PV5 and road position PR5 are calculated.
  • the detection unit 123 detects a wobbling state based on a change in the difference calculated for each of a plurality of vehicle position information acquired within a predetermined time from the current time. Specifically, the detection unit 123 changes the difference between two differences calculated for the adjacent vehicle positions for each of the vehicle positions corresponding to a plurality of vehicle position information acquired within a predetermined time from the current time. Is calculated. In the example shown in FIG. 2, the detection unit 123 uses, as the change amount, the absolute value of the difference E1 ⁇ the difference E2, the absolute value of the difference E2 ⁇ the difference E3, the absolute value of the difference E3 ⁇ the difference E4, and the absolute value of the difference E4 ⁇ the difference E5. Calculate the value.
  • the detection unit 123 detects the wobbling state when the total of the plurality of calculated change amounts is larger than a predetermined amount. In this case, the detection unit 123 detects the wobbling state on condition that the maximum value of the calculated change amount exceeds the first threshold value and the minimum value of the calculated change amount is equal to or less than the second threshold value. May be. By doing in this way, the driving
  • the notification unit 124 notifies the driver of the vehicle 1 that the wobbling state has been detected in response to the detection unit 123 detecting the wobbling state.
  • the notification unit 124 outputs a warning sound indicating that a wobbling state is detected from a speaker (not shown) provided in the vehicle 1, or a display (not shown) of a navigation system provided in the vehicle 1.
  • a warning sound indicating that a wobbling state is detected from a speaker (not shown) provided in the vehicle 1, or a display (not shown) of a navigation system provided in the vehicle 1.
  • a warning screen indicating that the wobbling state has been detected
  • the driver of the vehicle 1 is informed that the wobbling state has been detected.
  • running state detection apparatus 10 can make the driver of the vehicle 1 recognize that it is a wobble state, and can concentrate on a driving
  • FIG. 3 is a flowchart showing a processing procedure when the driving state detection device 10 detects a wobbling state.
  • the first acquisition unit 121 acquires vehicle position information (S10). Subsequently, the second acquisition unit 122 acquires one piece of linear information from the digital map information stored in the storage unit 11 based on the vehicle position information acquired in S10 (S20).
  • the detection unit 123 specifies a road position corresponding to the vehicle position indicated by the vehicle position information acquired in S10 among the plurality of road positions included in the acquired linear information (S30). Subsequently, the detection unit 123 calculates a difference between the vehicle position and the road position (S40).
  • the detection unit 123 determines whether or not the change amount of the difference calculated for each of the plurality of vehicle position information acquired within a predetermined time from the current time is greater than a predetermined amount ( S50).
  • the detection unit 123 moves the process to S10 when the change amount of the difference is equal to or smaller than the predetermined amount, and moves the process to S60 when the change amount of the difference is larger than the predetermined amount.
  • the notification unit 124 notifies the driver of the vehicle 1 that the wobbling state has been detected in S60, and then moves the process to S10.
  • the detection unit 123 detects the wobbling state based on the change in the difference between the vehicle position indicated by each of the plurality of vehicle position information and the road position corresponding to the vehicle position. Absent.
  • the detection unit 123 extracts a first feature point indicating at least one of a vertex and an inflection point in a curve indicated by a travel locus of the vehicle 1 based on a plurality of vehicle position information, and the road linearity based on the linear information is detected.
  • a second feature point indicating at least one of a vertex and an inflection point is extracted from the curve shown, and a wobbling state is detected based on the relationship between the extracted first feature points and the plurality of second feature points. May be.
  • the detection unit 123 detects a wobbling state when the number of the extracted first feature points is different from the number of the extracted second feature points, or the position indicated by the plurality of first feature points. And the wobbling state is detected based on the difference between the positions of the plurality of second feature points.
  • running state detection apparatus 10 can detect a wobbling state efficiently only based on the feature point which shows the driving
  • the detection unit 123 may detect a wobbling state based on a trajectory pattern included in the travel trajectory of the vehicle 1 based on a plurality of vehicle position information and a linear pattern included in the road alignment based on linear information.
  • the detection unit 123 specifies the trajectory pattern of the vehicle 1 corresponding to the travel section of the vehicle 1 and the linear pattern of the road corresponding to the travel section at predetermined time intervals (for example, every 10 seconds).
  • the detection part 123 defines the area
  • the detection unit 123 defines two border lines LR1 and a border line LR2 that are separated from each other by a predetermined position with respect to the line LR indicating the specified linear pattern, and these border lines
  • An area between LR1 and border line LR2 is defined as an area for detecting a wobbling state.
  • the detection part 123 detects a wandering state, when at least one part of the specified locus
  • the detection unit 123 since a part of the line LV indicating the trajectory pattern of the vehicle 1 is out of the region, the detection unit 123 detects the wobbling state.
  • the detection part 123 can detect a wobble state easily by comparing patterns.
  • the detection unit 123 may calculate the degree of coincidence between the identified trajectory pattern and the linear pattern, and may determine that the wobbling state is obtained when the calculated degree of coincidence is equal to or less than a predetermined threshold.
  • the detection unit 123 performs frequency analysis on the travel locus of the vehicle 1 based on a plurality of vehicle position information, performs frequency analysis on the road linearity based on the linear information, and detects a wobbling state based on the difference in frequency distribution between them. May be. Specifically, the detection unit 123 applies a bandpass filter (for example, a moving average filter) to each of the trajectory information indicating the traveling trajectory of the vehicle 1 and the linear information indicating the road alignment, and obtains a noise component (for example, acquisition). Small errors included in the positional information and linear information).
  • a bandpass filter for example, a moving average filter
  • the detection unit 123 performs FFT (Fast Fourier Transform) on the trajectory information and the linear information after applying the bandpass filter, and calculates a frequency distribution (frequency spectrum) corresponding to the trajectory information and the linear information. And the detection part 123 detects a wobble state based on the difference in each frequency distribution.
  • FFT Fast Fourier Transform
  • FIG. 5A to 5C are diagrams showing examples of frequency distribution.
  • FIG. 5A shows the linear frequency distribution of the road corresponding to the linear information.
  • FIG. 5B shows the frequency distribution of the travel locus when the fluctuation is small.
  • FIG. 5C shows the frequency distribution of the travel locus when the fluctuation is large.
  • the detection unit 123 detects the wobbling state when the frequency distribution of the trajectory information includes a distribution of a predetermined frequency or higher that is not included in the frequency distribution of the linear information. By doing in this way, the driving
  • the driving state detection device 10 acquires the first acquisition unit 121 that acquires a plurality of vehicle position information indicating the vehicle position, and the second information that acquires the linear information indicating the alignment of the road on which the vehicle 1 is traveling.
  • running state of the vehicle 1 is a wobble state based on vehicle position information and linear information are provided.
  • running state detection apparatus 10 acquires the vehicle position information which shows a vehicle position, without estimating a vehicle position using a sensor, and detects a wandering state based on the said vehicle position information, The driving state of the vehicle 1 can be detected with high accuracy.
  • the detection unit 123 of the driving state detection device 10 detects the wobbling state based on the change in the difference between the vehicle position indicated by each of the plurality of vehicle position information and the road position corresponding to the vehicle position.
  • the vehicle 1 does not travel at a certain distance from the center line or white line of the road, and the difference between the road position and the vehicle position changes greatly. Therefore, the driving
  • the present invention has an effect that the driving state of the vehicle can be detected with high accuracy, and is useful for a driving state detection device and the like.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

La présente invention concerne un appareil 10 de détection de conditions de conduite comportant une première unité 121 d'acquisition qui acquiert une pluralité d'informations de position de véhicule indiquant une position d'un véhicule 1, une deuxième unité 122 d'acquisition qui acquiert une information linéaire indiquant une forme linéaire de la route sur laquelle circule le véhicule 1, et une unité 123 de détection qui détecte que les conditions de conduite du véhicule 1 se trouvent dans un état instable d'après les informations de position de véhicule et l'information linéaire. L'information linéaire comporte une pluralité de informations de position de la route indiquant des positions de la route, et l'unité 123 de détection détecte un état instable d'après des variations dans l'écart entre la position du véhicule 1 indiquée par le pluralité respective d'informations de position de véhicule et la position de la route correspondant à la position du véhicule 1.
PCT/JP2016/079687 2015-10-07 2016-10-05 Appareil de détection de conditions de conduite WO2017061500A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2015-199076 2015-10-07
JP2015199076A JP6582844B2 (ja) 2015-10-07 2015-10-07 運転状態検知装置

Publications (1)

Publication Number Publication Date
WO2017061500A1 true WO2017061500A1 (fr) 2017-04-13

Family

ID=58487805

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/079687 WO2017061500A1 (fr) 2015-10-07 2016-10-05 Appareil de détection de conditions de conduite

Country Status (2)

Country Link
JP (1) JP6582844B2 (fr)
WO (1) WO2017061500A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7020348B2 (ja) * 2018-08-30 2022-02-16 トヨタ自動車株式会社 自車位置推定装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002154345A (ja) * 2000-11-24 2002-05-28 Fuji Heavy Ind Ltd 車両用の覚醒度推定装置および覚醒度推定方法
JP2010102538A (ja) * 2008-10-24 2010-05-06 Toyota Motor Corp 居眠り判定装置
WO2010143291A1 (fr) * 2009-06-11 2010-12-16 トヨタ自動車株式会社 Procédé et dispositif de détermination de position de déplacement de véhicule
JP2015001773A (ja) * 2013-06-13 2015-01-05 ボッシュ株式会社 車線推定装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002154345A (ja) * 2000-11-24 2002-05-28 Fuji Heavy Ind Ltd 車両用の覚醒度推定装置および覚醒度推定方法
JP2010102538A (ja) * 2008-10-24 2010-05-06 Toyota Motor Corp 居眠り判定装置
WO2010143291A1 (fr) * 2009-06-11 2010-12-16 トヨタ自動車株式会社 Procédé et dispositif de détermination de position de déplacement de véhicule
JP2015001773A (ja) * 2013-06-13 2015-01-05 ボッシュ株式会社 車線推定装置

Also Published As

Publication number Publication date
JP6582844B2 (ja) 2019-10-02
JP2017072962A (ja) 2017-04-13

Similar Documents

Publication Publication Date Title
JP5939357B2 (ja) 移動軌跡予測装置及び移動軌跡予測方法
KR101405583B1 (ko) 차량 속도 추정 장치 및 방법
CN116129376A (zh) 一种道路边缘检测方法和装置
US11430227B2 (en) Method, computer program product, and driver assistance system for determining one or more lanes of a road in an environment of a vehicle
EP3640684B1 (fr) Procédé de détection de marqueur et système pour véhicule
CN103164851A (zh) 道路分割物检测方法和装置
EP3188154A1 (fr) Système de détection d'état et d'avertissement pourvéhicule
US10928524B2 (en) Lane detection
JP2019108116A (ja) 車両の縦方向速度を制御する装置及び方法
US9159176B2 (en) Vehicle identification apparatus and method
US10810749B2 (en) Image processing apparatus, moving body device control system, computer-readable medium, and image processing method
JP2007240422A (ja) 俯角算出装置、俯角算出方法、俯角算出プログラムおよび画像処理装置
JP2021096265A (ja) 測定装置、測定方法、及び、プログラム
US11889047B2 (en) Image processing device and image processing method
WO2017061500A1 (fr) Appareil de détection de conditions de conduite
JP2017154516A (ja) 衝突判定装置、衝突判定方法、およびプログラム
JP2014197351A (ja) 運転状態判定システム、運転状態判定方法、及び運転状態判定プログラム
KR102044192B1 (ko) 차선폭 보정 장치 및 방법과 이를 이용한 차량 스마트 크루즈 컨트롤 시스템
JP5821687B2 (ja) 車両検出装置及び車両検出方法
JP6763198B2 (ja) 画像処理装置、撮像装置、移動体機器制御システム、画像処理方法、及びプログラム
JP2018112461A (ja) 確率算出装置及び確率算出方法
JP2018084987A (ja) 物体認識装置
JP2016224797A (ja) 落下物検出装置
JP6833259B2 (ja) 物体検知支援装置
JP2015011645A (ja) 光軸補正装置

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: 16853654

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16853654

Country of ref document: EP

Kind code of ref document: A1