JP2012198857A5 - - Google Patents

Download PDF

Info

Publication number
JP2012198857A5
JP2012198857A5 JP2011064048A JP2011064048A JP2012198857A5 JP 2012198857 A5 JP2012198857 A5 JP 2012198857A5 JP 2011064048 A JP2011064048 A JP 2011064048A JP 2011064048 A JP2011064048 A JP 2011064048A JP 2012198857 A5 JP2012198857 A5 JP 2012198857A5
Authority
JP
Japan
Prior art keywords
images
movement
movement vector
approaching
feature points
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.)
Granted
Application number
JP2011064048A
Other languages
Japanese (ja)
Other versions
JP2012198857A (en
JP5539250B2 (en
Filing date
Publication date
Application filed filed Critical
Priority to JP2011064048A priority Critical patent/JP5539250B2/en
Priority claimed from JP2011064048A external-priority patent/JP5539250B2/en
Publication of JP2012198857A publication Critical patent/JP2012198857A/en
Publication of JP2012198857A5 publication Critical patent/JP2012198857A5/ja
Application granted granted Critical
Publication of JP5539250B2 publication Critical patent/JP5539250B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Claims (5)

車両(10)に搭載され、当該車両(10)の周囲を撮影した画像を順次取得する撮像部(2)と、
異なる時刻において前記撮像部(2)により取得された二つの画像から、それぞれ少なくとも一つの特徴点を抽出する特徴点抽出部(432)と、
前記二つの画像からそれぞれ抽出された特徴点のうち、同一の物体に関する二つの特徴点を対応付け、当該対応付けられた特徴点間の画像上の位置の差を求めることにより、当該物体の画像上の移動量及び移動方向を表す観測移動ベクトルを求める観測移動ベクトル算出部(435)と、
前記二つの画像のうちの一方から抽出された前記特徴点のそれぞれについて、前記二つの画像のそれぞれの取得時刻の間における前記撮像部(2)の移動に起因する、画像上での前記物体の移動量及び移動方向を表す見かけの移動ベクトルの最小値を算出する最小見かけ移動ベクトル算出部(434)と、
前記二つの画像のうちの一方から抽出された前記特徴点のそれぞれについて、前記観測移動ベクトルから前記見かけの移動ベクトルの最小値を減じることにより、補正移動ベクトルを算出する移動ベクトル補正部(436)と、
前記二つの画像のうちの一方から抽出された前記特徴点のうちの少なくとも一つの特徴点についての前記補正移動ベクトルに、前記車両(10)の進行方向に接近する方向の移動成分が含まれる場合に、前記物体は前記車両に接近する移動物体であると判定する判定部(437)と、
を有することを特徴とする接近物体検知装置。
An imaging unit (2) that is mounted on the vehicle (10) and sequentially acquires images obtained by photographing the periphery of the vehicle (10);
A feature point extraction unit (432) that extracts at least one feature point from each of the two images acquired by the imaging unit (2) at different times;
Among the feature points extracted from the two images, two feature points related to the same object are associated with each other, and a difference in position on the image between the associated feature points is obtained. An observation movement vector calculation unit (435) for obtaining an observation movement vector representing the movement amount and movement direction above;
For each of the feature points extracted from one of the two images, the object on the image is caused by the movement of the imaging unit (2) between the respective acquisition times of the two images. A minimum apparent movement vector calculation unit (434) for calculating a minimum value of an apparent movement vector representing a movement amount and a movement direction;
For each of the feature points extracted from one of the two images, a movement vector correction unit (436) that calculates a correction movement vector by subtracting the minimum value of the apparent movement vector from the observed movement vector. When,
When the corrected movement vector for at least one of the feature points extracted from one of the two images includes a movement component in a direction approaching the traveling direction of the vehicle (10). And a determination unit (437) that determines that the object is a moving object approaching the vehicle;
An approaching object detection device comprising:
前記最小見かけ移動ベクトル算出部(434)は、前記撮像部(2)から、前記二つの画像のうちの一方の画像から抽出された前記特徴点を通る視線上の地面の位置を求め、前記二つの画像のそれぞれの取得時刻の間における前記撮像部(2)の移動に起因する当該地面の位置についての前記画像上の見かけの移動ベクトルを前記見かけの移動ベクトルの最小値とする、請求項1に記載の接近物体検知装置。   The minimum apparent movement vector calculation unit (434) obtains the position of the ground on the line of sight passing through the feature point extracted from one of the two images from the imaging unit (2), and The apparent movement vector on the image with respect to the position of the ground due to the movement of the imaging unit (2) between the acquisition times of two images is set as the minimum value of the apparent movement vector. The approaching object detection device described in 1. 前記判定部(437)は、前記車両(10)の進行方向に接近する方向の移動成分が含まれる前記補正ベクトルに対応する前記特徴点を接近物体候補点として検出し、前記物体に対応する前記接近物体候補点が複数存在する場合に限り、前記物体は前記車両に接近する移動物体であると判定する、請求項1または2に記載の接近物体検知装置。   The determination unit (437) detects the feature point corresponding to the correction vector including a moving component in a direction approaching the traveling direction of the vehicle (10) as an approaching object candidate point, and corresponds to the object The approaching object detection device according to claim 1, wherein the object is determined to be a moving object approaching the vehicle only when there are a plurality of approaching object candidate points. 前記車両(10)に接近する移動物体であると判定された前記物体の存在を表す画像を表示部(3)に表示させる表示制御部(438)をさらに有する、請求項1〜3の何れか一に記載の接近物体検知装置。 The display control part (438) according to any one of claims 1 to 3, further comprising a display control part (438) for causing the display part (3) to display an image representing the presence of the object determined to be a moving object approaching the vehicle (10). The approaching object detection device according to one item . 車両(10)の周囲を撮影した画像を、当該車両(10)に搭載された撮像部(2)により順次取得するステップと、
異なる時刻において前記撮像部(2)により取得された二つの画像から、それぞれ特徴点を抽出するステップと、
前記二つの画像からそれぞれ抽出された特徴点のうち、同一の物体に関する二つの特徴点を対応付け、当該対応付けられた特徴点間の画像上の位置の差を求めることにより、当該物体の画像上の移動量及び移動方向を表す観測移動ベクトルを求めるステップと、
前記二つの画像のうちの一方から抽出された前記特徴点のそれぞれについて、前記二つの画像のそれぞれの取得時刻の間における前記撮像部(2)の移動に起因する、画像上での前記物体の移動量及び移動方向を表す見かけの移動ベクトルの最小値を算出するステップと、
前記二つの画像のうちの一方から抽出された前記特徴点のそれぞれについて、前記観測移動ベクトルから前記見かけの移動ベクトルの最小値を減じることにより、補正移動ベクトルを算出するステップと、
前記二つの画像のうちの一方から抽出された前記特徴点のうちの少なくとも一つの特徴点についての前記補正移動ベクトルに、前記車両(10)の進行方向に接近する方向の移動成分が含まれる場合に、前記物体は前記車両に接近する移動物体であると判定するステップと、
を含むことを特徴とする接近物体検知方法。
Sequentially acquiring images taken around the vehicle (10) by the imaging unit (2) mounted on the vehicle (10);
Extracting feature points from the two images acquired by the imaging unit (2) at different times;
Among the feature points extracted from the two images, two feature points related to the same object are associated with each other, and a difference in position on the image between the associated feature points is obtained. Obtaining an observed movement vector representing the amount and direction of movement above;
For each of the feature points extracted from one of the two images, the object on the image is caused by the movement of the imaging unit (2) between the respective acquisition times of the two images. Calculating a minimum value of an apparent movement vector representing a movement amount and a movement direction;
For each of the feature points extracted from one of the two images, calculating a corrected movement vector by subtracting the minimum value of the apparent movement vector from the observed movement vector;
When the corrected movement vector for at least one of the feature points extracted from one of the two images includes a movement component in a direction approaching the traveling direction of the vehicle (10). And determining that the object is a moving object approaching the vehicle;
An approaching object detection method comprising:
JP2011064048A 2011-03-23 2011-03-23 Approaching object detection device and approaching object detection method Active JP5539250B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2011064048A JP5539250B2 (en) 2011-03-23 2011-03-23 Approaching object detection device and approaching object detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2011064048A JP5539250B2 (en) 2011-03-23 2011-03-23 Approaching object detection device and approaching object detection method

Publications (3)

Publication Number Publication Date
JP2012198857A JP2012198857A (en) 2012-10-18
JP2012198857A5 true JP2012198857A5 (en) 2013-06-20
JP5539250B2 JP5539250B2 (en) 2014-07-02

Family

ID=47180982

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2011064048A Active JP5539250B2 (en) 2011-03-23 2011-03-23 Approaching object detection device and approaching object detection method

Country Status (1)

Country Link
JP (1) JP5539250B2 (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6221283B2 (en) * 2013-03-19 2017-11-01 富士通株式会社 Image processing apparatus, image processing method, and image processing program
EP2990290B1 (en) * 2014-09-01 2019-11-06 Honda Research Institute Europe GmbH Method and system for post-collision manoeuvre planning and vehicle equipped with such system
JP6454554B2 (en) * 2015-01-20 2019-01-16 クラリオン株式会社 External environment recognition device for vehicle and vehicle behavior control device using the same
JP6699902B2 (en) 2016-12-27 2020-05-27 株式会社東芝 Image processing apparatus and image processing method
JP7102800B2 (en) 2018-03-13 2022-07-20 富士通株式会社 Evaluation program, evaluation method and evaluation device
JP7148390B2 (en) * 2018-12-27 2022-10-05 株式会社デンソーテン APPROACHING OBJECT DETECTION DEVICE AND APPROACHING OBJECT DETECTION METHOD
KR102312932B1 (en) * 2020-07-31 2021-10-14 한화시스템 주식회사 Situation monitoring apparatus and situation monitoring method for 360-degree panoramic image acquisition using target handover

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3364771B2 (en) * 1994-03-09 2003-01-08 本田技研工業株式会社 Moving object detection device
JP3485135B2 (en) * 1995-09-27 2004-01-13 矢崎総業株式会社 Rear side monitoring device for vehicles
JP2000168442A (en) * 1998-12-11 2000-06-20 Mitsubishi Motors Corp Backward monitoring device for vehicle
JP3776094B2 (en) * 2002-05-09 2006-05-17 松下電器産業株式会社 Monitoring device, monitoring method and monitoring program

Similar Documents

Publication Publication Date Title
JP2012198857A5 (en)
JP2011175477A5 (en) Three-dimensional measuring apparatus, processing method, program, and storage medium
EP2348280A3 (en) Systems and methods for monocular airborne object detection
JP2015519957A5 (en)
JP2011229834A5 (en) Ophthalmic device and ophthalmic method
EP2958054A3 (en) Hazard detection in a scene with moving shadows
WO2014132090A3 (en) Optical navigation & positioning system
GB2547391A (en) Using depth-camera images to speed registration of three-dimensional scans
MX2017001248A (en) Position self-calculation device and position self-calculation method.
EP2527787A3 (en) Aerial photograph image pickup method and aerial photograph image pickup apparatus
BR112012026769A2 (en) calibration apparatus, distance measuring system, calibration method and calibration program
JP2010134649A5 (en)
JP2015090298A5 (en)
JP2013196341A5 (en)
MY179728A (en) Three-dimensional object detection device
WO2013149916A3 (en) Method and device for optically determining a position and/or orientation of an object in space
JP2015106290A5 (en)
CN106470877A (en) Display apparatus and vehicle display packing
MX2017006717A (en) Method of controlling a traffic surveillance system.
JP2016045903A5 (en)
JP2013186853A5 (en)
JP2011179909A5 (en) Position / orientation measuring apparatus, position / orientation measuring method, program, and storage medium
EP2639741A3 (en) Monitoring device, reliability calculation program, and reliability calculation method
EP2927710A3 (en) Ranging system, information processing apparatus, information processing method and program thereof
EP2654289A3 (en) Ranging apparatus, ranging method and imaging system