WO2014041848A1 - 情報処理装置、情報処理方法、及びプログラム - Google Patents

情報処理装置、情報処理方法、及びプログラム Download PDF

Info

Publication number
WO2014041848A1
WO2014041848A1 PCT/JP2013/063446 JP2013063446W WO2014041848A1 WO 2014041848 A1 WO2014041848 A1 WO 2014041848A1 JP 2013063446 W JP2013063446 W JP 2013063446W WO 2014041848 A1 WO2014041848 A1 WO 2014041848A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
processing
lane
region
captured image
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2013/063446
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
孝宏 前
孝光 渡辺
渡辺　孝弘
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Oki Electric Industry Co Ltd
Original Assignee
Oki Electric Industry Co Ltd
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 Oki Electric Industry Co Ltd filed Critical Oki Electric Industry Co Ltd
Priority to US14/428,352 priority Critical patent/US9946950B2/en
Publication of WO2014041848A1 publication Critical patent/WO2014041848A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/30236—Traffic on road, railway or crossing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/30242—Counting objects in image

Definitions

  • the present invention relates to an information processing apparatus, an information processing method, and a program.
  • the processing area is set manually by the user when a system such as a surveillance camera is installed. Therefore, the characteristics (position, size, etc.) of the processing area vary depending on the user skill (for example, the understanding level of the system characteristics). On the other hand, the characteristics of the processing area greatly affect the measurement accuracy. Therefore, the conventional technique has a problem that the characteristics of the processing region vary depending on the skill of the user, and as a result, the measurement accuracy varies. For this reason, the technique which can stabilize the measurement precision of traffic volume was calculated
  • the present invention has been made in view of the above problems, and an object of the present invention is to provide a new and improved information processing apparatus and information processing capable of stabilizing the traffic measurement accuracy. It is to provide a method and a program.
  • imaging is performed based on an image acquisition unit that acquires a captured image on which a road on which a vehicle passes, a captured image, and road information about the road.
  • a calibration unit that calculates road parameters for converting coordinates in the image into coordinates in real space, a lane region detection unit that detects a lane region from the captured image based on the captured image and the road parameter, and a lane region
  • a processing area setting unit that sets a processing area in which a vehicle passage is detected on the lane area.
  • the processing area setting unit may set the processing area at the end on the near side of the lane area.
  • the processing area setting unit may arrange the entire end on the near side of the processing area inside the captured image.
  • a processing area adjustment unit that adjusts the processing area may be provided based on a shield that blocks a part of the lane area.
  • processing area adjustment unit may set the processing area at a position avoiding the shielding object.
  • processing area adjustment unit may arrange the processing area at the end on the near side of the area behind the shielding object.
  • the processing area adjustment unit may mask a part of the processing area that is shielded by the shielding object.
  • the processing area adjustment unit determines the size of the mask portion and the position of the processing area based on the amount of decrease in detection accuracy due to the size of the mask portion that masks the processing area and the amount of decrease in detection accuracy due to the position of the processing area. May be determined.
  • the processing area adjustment unit may set the processing area in the lane area not covered by the shielding object based on the processing area of the lane area shielded by the shielding object. Good.
  • the processing area setting unit may set a boundary portion between the lane area and the roadside band area as a processing area for detecting a two-wheeled vehicle.
  • the processing area setting unit may set a processing area for a vehicle other than the two-wheeled vehicle at a position avoiding the processing area for detecting the two-wheeled vehicle.
  • processing area setting unit may adjust the processing area based on a user operation.
  • the lane area detection unit may detect the lane area from the captured image based on a user operation.
  • coordinates in a captured image are acquired based on an image acquisition function for acquiring a captured image in which a road on which a vehicle passes is drawn, a captured image, and road information about the road.
  • a calibration function for calculating road parameters for converting the coordinates to real space coordinates, a lane detection function for detecting a lane area from the captured image based on the captured image and the road parameter, and a vehicle based on the lane area There is provided a program for realizing a processing region setting function for setting a processing region where passage is detected on a lane region.
  • the information processing apparatus 1-1 includes an image acquisition unit 10, a calibration unit 20, a lane region detection unit 30, a processing region setting (calculation) unit 40, and a processing region display unit 50.
  • the road area 205 includes a plurality of lane areas 221 to 223.
  • a roadside zone region 300 is drawn on the side of the road region 205.
  • the plurality of lane regions 221 to 223 are a first lane, a second lane, and a third lane from the side close to the roadside belt region 300.
  • processing areas 230 to 250 are set in the lane areas 221 to 223, respectively.
  • the xy axis is set, the horizontal axis is the x axis, and the vertical axis is the y axis.
  • Each pixel constituting the captured image has an xy coordinate and a pixel value (luminance or the like).
  • the calibration unit 20 calculates road parameters by calibrating the captured image.
  • the road parameter is an equation for converting two-dimensional coordinates in the captured image into three-dimensional coordinates in the real space.
  • a specific method of calibration is not particularly limited. For example, calibration may be performed by the method disclosed in Patent Document 1.
  • the calibration unit 20 outputs calibration information including road parameters and road information to the lane area detection unit 30.
  • the lane area detection unit 30 can also detect the lane area based on the point and the road parameters.
  • the lane area detection unit 30 recognizes the number of lanes and the position of the lane area based on the detected lane area. For example, the lane area detection unit 30 detects the lane areas 221 to 223 from the captured image 200 shown in FIG. 6, and recognizes that the number of lanes is 3.
  • the lane area detection unit 30 outputs the lane area to the processing area setting unit 40.
  • the processing area setting unit 40 sets the processing area on the lane area based on the captured image and the lane area.
  • the processing area is an area where vehicle passage is detected. That is, vehicle passage is detected when the vehicle passes through the processing area.
  • the vehicle passing may be performed by an apparatus different from the information processing apparatus 1-1, but may be performed within the information processing apparatus 1-1.
  • the processing area setting unit 40 sets the processing area at the end on the near side of the lane area.
  • the “end on the near side” is an end having a large y-coordinate (disposed on the lower side in FIG. 6) among both ends in the length direction of the lane region.
  • the “front end” is closer to the imaging device than the “back end” in real space.
  • the length of the processing region 230 is preferably equal to or longer than the average length of the vehicle (the value obtained by arithmetically averaging the lengths of buses, private cars, trucks, etc.). Further, from the viewpoint of preventing a vehicle on the back side of the processing area from going out to the back side of the processing area (that is, outside the captured image) during one frame, it is necessary to make the length of the processing area 230 as long as possible. . However, if it is too long, there is a possibility that noise will be applied to the processing area. Therefore, the processing area setting unit 40 determines a length considering these circumstances. For example, the length of the processing region 230 may be about 10 m in real space.
  • the processing area setting unit 40 sets the processing area at the end on the near side of the lane area. This is due to the following reason. That is, when the vehicle in the captured image reaches the foremost side of the lane region, the overlap with the following vehicle is easily eliminated. That is, erroneous detection is unlikely to occur. Therefore, the processing area setting unit 40 sets the processing area at the end on the near side of the lane area.
  • the processing region setting unit 40 outputs processing region information related to the processing region to the processing region display unit 50 and a device that detects vehicle passing. As will be described later, the processing area setting unit 40 corrects the position and size of the processing area based on the information when the user inputs information on the position or the like of the processing area.
  • the processing area is a plane, but the processing area may be a three-dimensional shape as shown in FIG. In the example shown in FIG. 7, three-dimensional processing areas 230 ′ to 250 ′ are set.
  • the processing area setting unit 40 may make the processing area flat or solid. However, for example, when the device that detects vehicle passing also detects the size of the vehicle, the processing region setting unit 40 makes the processing region three-dimensional. On the other hand, the processing region setting unit 40 may set the processing region to a plane when the device that detects vehicle passage detects only the passage of the vehicle.
  • step S10 the image acquisition unit 10 acquires a captured image from an imaging device (not shown), and outputs the acquired image to the calibration unit 20, the lane region detection unit 30, the processing region setting unit 40, and the processing region display unit 50.
  • the processing area is set at a position avoiding the shielding. Specifically, the processing area is set at the end on the near side of the area on the back side of the shield.
  • Detecting accuracy is calculated (simulated) as follows. That is, a rectangular parallelepiped corresponding to a vehicle is arranged in a real space corresponding to the processing area. Further, a similar rectangular parallelepiped is arranged in the real space 7 to 8 m behind it. Here, 7-8 m is a value assumed as an inter-vehicle distance. Therefore, this value may be another value. Then, how much these rectangular parallelepipeds are imaged by the imaging device is calculated. Then, the amount of decrease in accuracy is calculated based on the degree of overlap and the performance of the device that detects vehicle passage. As shown in FIG. 12, the greater the distance from the initial position, the greater the decrease in accuracy. This is because the greater the distance from the initial position, the greater the degree of vehicle overlap. In addition, a decrease in accuracy is suppressed as the distance between the lane and the roadside belt increases. In this case, since the distance between the imaging device and the lane is increased, overlapping of vehicles in the captured image can be suppressed.
  • Specific processing includes the following two. (1) Align the front end of all processing areas at the same position. (2) Under the condition that only one vehicle area passes through the processing area, the processing area is arranged as close to the lane area as possible.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Closed-Circuit Television Systems (AREA)
PCT/JP2013/063446 2012-09-14 2013-05-14 情報処理装置、情報処理方法、及びプログラム Ceased WO2014041848A1 (ja)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/428,352 US9946950B2 (en) 2012-09-14 2013-05-14 Data processing apparatus, data processing method, and program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2012-202273 2012-09-14
JP2012202273A JP5811975B2 (ja) 2012-09-14 2012-09-14 情報処理装置、情報処理方法、及びプログラム

Publications (1)

Publication Number Publication Date
WO2014041848A1 true WO2014041848A1 (ja) 2014-03-20

Family

ID=50277984

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2013/063446 Ceased WO2014041848A1 (ja) 2012-09-14 2013-05-14 情報処理装置、情報処理方法、及びプログラム

Country Status (3)

Country Link
US (1) US9946950B2 (https=)
JP (1) JP5811975B2 (https=)
WO (1) WO2014041848A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504913A (zh) * 2014-12-25 2015-04-08 珠海高凌环境科技有限公司 视频车流检测方法及装置

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5783304B1 (ja) * 2014-07-09 2015-09-24 沖電気工業株式会社 情報処理装置、情報処理方法およびプログラム
WO2016152196A1 (ja) 2015-03-23 2016-09-29 日本電気株式会社 監視装置、監視システム、監視方法、及びコンピュータ読み取り可能な記録媒体
JP6634842B2 (ja) * 2016-01-19 2020-01-22 沖電気工業株式会社 情報処理装置、情報処理方法およびプログラム
JP2017151706A (ja) * 2016-02-24 2017-08-31 沖電気工業株式会社 検出領域変更装置、検出領域変更方法およびプログラム
KR20180078361A (ko) * 2016-12-29 2018-07-10 (주)캠시스 차량 주변 물체 알림 방법 및 장치
US12518546B2 (en) * 2020-10-02 2026-01-06 Nec Corporation Information processing apparatus, image transmission system, and information processing method
CN112833940B (zh) * 2020-12-17 2022-08-12 山东省交通规划设计院集团有限公司 一种真实路用环境下道路多功能测试系统及方法
JP7739190B2 (ja) * 2022-01-27 2025-09-16 京セラ株式会社 状態推定装置、状態推定方法及び状態推定プログラム
CN115272182B (zh) * 2022-06-23 2023-05-26 禾多科技（北京）有限公司 车道线检测方法、装置、电子设备和计算机可读介质
US11715305B1 (en) * 2022-11-30 2023-08-01 Amitha Nandini Mandava Traffic detection system using machine vision
CN116934786A (zh) * 2023-07-20 2023-10-24 上海同陆云交通科技有限公司 一种基于道路线激光的车辙沉陷拥包的定量检测方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09212791A (ja) * 1996-02-07 1997-08-15 Babcock Hitachi Kk 路面監視方法と装置
JP2001043483A (ja) * 1999-07-29 2001-02-16 Oki Electric Ind Co Ltd 交通流計測システム
JP2011198030A (ja) * 2010-03-19 2011-10-06 Mitsubishi Electric Corp 交通流計測装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0710387B1 (en) * 1993-07-22 1997-12-03 Minnesota Mining And Manufacturing Company Method and apparatus for calibrating three-dimensional space for machine vision applications
JP3384526B2 (ja) * 1996-12-19 2003-03-10 松下電器産業株式会社 物流計測装置
JP2003288695A (ja) * 2002-03-27 2003-10-10 Natl Inst For Land & Infrastructure Management Mlit 出会い頭衝突防止支援システム
AU2003225228A1 (en) * 2002-05-03 2003-11-17 Donnelly Corporation Object detection system for vehicle
JP4223320B2 (ja) * 2003-04-17 2009-02-12 富士重工業株式会社 車両用運転支援装置
JP4311107B2 (ja) * 2003-08-08 2009-08-12 オムロン株式会社 三次元物体認識装置およびその設定方法
JP3925488B2 (ja) * 2003-11-11 2007-06-06 日産自動車株式会社 車両用画像処理装置
CN101042802A (zh) * 2006-03-23 2007-09-26 安捷伦科技有限公司 交通信息传感器、交通信息检测方法和系统
JP2008168811A (ja) * 2007-01-12 2008-07-24 Honda Motor Co Ltd 車線認識装置、車両、車線認識方法、及び車線認識プログラム
JP4947138B2 (ja) * 2007-03-28 2012-06-06 富士通株式会社 ナビゲーション装置
US8379926B2 (en) * 2007-12-13 2013-02-19 Clemson University Vision based real time traffic monitoring
US8174406B2 (en) * 2008-07-02 2012-05-08 International Business Machines Corporation Detecting and sharing road traffic condition information
TWI452540B (zh) * 2010-12-09 2014-09-11 Ind Tech Res Inst 影像式之交通參數偵測系統與方法及電腦程式產品
KR20120127830A (ko) * 2011-05-16 2012-11-26 삼성전자주식회사 차량용 단말을 위한 사용자 인터페이스 방법 및 장치

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09212791A (ja) * 1996-02-07 1997-08-15 Babcock Hitachi Kk 路面監視方法と装置
JP2001043483A (ja) * 1999-07-29 2001-02-16 Oki Electric Ind Co Ltd 交通流計測システム
JP2011198030A (ja) * 2010-03-19 2011-10-06 Mitsubishi Electric Corp 交通流計測装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504913A (zh) * 2014-12-25 2015-04-08 珠海高凌环境科技有限公司 视频车流检测方法及装置

Also Published As

Publication number Publication date
US20150363659A1 (en) 2015-12-17
JP5811975B2 (ja) 2015-11-11
JP2014056536A (ja) 2014-03-27
US9946950B2 (en) 2018-04-17

Similar Documents

Publication Publication Date Title
JP5811975B2 (ja) 情報処理装置、情報処理方法、及びプログラム
US10636130B2 (en) Image processing device
US8964189B2 (en) Three-dimensional measurement apparatus, method for three-dimensional measurement, and computer program
CN103080976B (zh) 三维物体检测装置和三维物体检测方法
US9288381B2 (en) In-vehicle image recognizer
CN107507558B (zh) 一种led显示屏的校正方法
US9740943B2 (en) Three-dimensional object detection device
CN104509100B (zh) 三维物体检测装置以及三维物体检测方法
KR102022402B1 (ko) 캘리브레이션 방법 및 장치
US10339396B2 (en) Vehicle accessibility determination device
WO2012120856A1 (ja) 物体検出装置及び物体検出方法
CN104106105A (zh) 立体物检测装置
WO2011114947A1 (ja) 横断歩道検出装置、横断歩道検出方法及びプログラム
US10338211B2 (en) Apparatus for measuring distance
CN104115203B (zh) 立体物检测装置
CN104115204B (zh) 立体物检测装置
US20160207473A1 (en) Method of calibrating an image detecting device for an automated vehicle
JP2013186663A (ja) 横断歩道認識装置および横断歩道認識方法
JP2006268199A (ja) 車両用画像処理システム、車両用画像処理方法、車両用画像処理プログラム、及び車両
JP2016200557A (ja) 校正装置、距離計測装置及び校正方法
US10339394B2 (en) Step detection device and step detection method
JP6316154B2 (ja) 車両検出装置、調整支援装置、車両検出方法及び調整方法
JP5959245B2 (ja) レーンマーク検出装置およびレーンマークの信頼度算出方法
JP7064400B2 (ja) 物体検知装置
EP3637368A1 (en) Image processing device and light distribution control system

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: 13836314

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)
WWE Wipo information: entry into national phase

Ref document number: 14428352

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13836314

Country of ref document: EP

Kind code of ref document: A1