JP2017016356A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2017016356A5 JP2017016356A5 JP2015131841A JP2015131841A JP2017016356A5 JP 2017016356 A5 JP2017016356 A5 JP 2017016356A5 JP 2015131841 A JP2015131841 A JP 2015131841A JP 2015131841 A JP2015131841 A JP 2015131841A JP 2017016356 A5 JP2017016356 A5 JP 2017016356A5
- Authority
- JP
- Japan
- Prior art keywords
- dimensional position
- candidate
- time
- image processing
- interest
- 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
Links
- 230000000875 corresponding Effects 0.000 claims description 24
- 238000003384 imaging method Methods 0.000 claims description 7
- 230000001186 cumulative Effects 0.000 claims 4
- 102000003743 Relaxin Human genes 0.000 claims 3
- 108090000103 Relaxin Proteins 0.000 claims 3
- 238000000034 method Methods 0.000 claims 3
- 238000003672 processing method Methods 0.000 claims 2
- 230000002401 inhibitory effect Effects 0.000 claims 1
Description
本発明の目的を達成するために、例えば、本発明の画像処理装置は以下の構成を備える。すなわち、
連続して撮影されたフレーム画像群を、視野が重複している複数の撮像部のそれぞれから取得する取得手段と、
前記フレーム画像群上の物体を追尾する追尾手段と、
前記物体のフレーム画像上の位置と前記複数の撮像部間の位置関係とに基づいて着目時刻における前記物体の三次元位置の候補を生成する生成手段と、
前記着目時刻における三次元位置の候補と、前記着目時刻より前の過去時刻における前記物体の三次元位置の候補とを対応付ける対応付け手段と、
前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す局所対応確度と、前記過去時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度と、に基づいて、前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度を求める算出手段と、
前記積算対応確度に基づいて前記着目時刻における前記物体の三次元位置を判定する判定手段と、
を備える。
In order to achieve the object of the present invention, for example, an image processing apparatus of the present invention comprises the following arrangement. That is,
Acquisition means for acquiring a group of continuously captured frame images from each of a plurality of imaging units having overlapping fields of view;
Tracking means for tracking an object on the frame image group;
Generating means for generating a candidate for the three-dimensional position of the object at the time of interest based on the position of the object on the frame image and the positional relationship between the plurality of imaging units;
Association means for associating a candidate for a three-dimensional position at the time of interest with a candidate for a three-dimensional position of the object at a past time prior to the time of interest;
And local corresponding probability indicating the likelihood of the candidate of the three-dimensional position before Symbol focused time corresponding to the object, the integrated response probability indicating the likelihood of a candidate of the three-dimensional position in the past time corresponding to the object, on the basis Calculating means for obtaining an integrated correspondence accuracy indicating a probability that a candidate for a three-dimensional position at the time of interest corresponds to the object;
A determining means for determine a constant three-dimensional position of the object in the time of interest based on the integrated response accuracy,
Is provided.
Claims (19)
前記フレーム画像群上の物体を追尾する追尾手段と、
前記物体のフレーム画像上の位置と前記複数の撮像部間の位置関係とに基づいて着目時刻における前記物体の三次元位置の候補を生成する生成手段と、
前記着目時刻における三次元位置の候補と、前記着目時刻より前の過去時刻における前記物体の三次元位置の候補とを対応付ける対応付け手段と、
前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す局所対応確度と、前記過去時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度と、に基づいて、前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度を求める算出手段と、
前記積算対応確度に基づいて前記着目時刻における前記物体の三次元位置を判定する判定手段と、
を備えることを特徴とする画像処理装置。 Acquisition means for acquiring a group of continuously captured frame images from each of a plurality of imaging units having overlapping fields of view;
Tracking means for tracking an object on the frame image group;
Generating means for generating a candidate for the three-dimensional position of the object at the time of interest based on the position of the object on the frame image and the positional relationship between the plurality of imaging units;
Association means for associating a candidate for a three-dimensional position at the time of interest with a candidate for a three-dimensional position of the object at a past time prior to the time of interest;
And local corresponding probability indicating the likelihood of the candidate of the three-dimensional position before Symbol focused time corresponding to the object, the integrated response probability indicating the likelihood of a candidate of the three-dimensional position in the past time corresponding to the object, on the basis Calculating means for obtaining an integrated correspondence accuracy indicating a probability that a candidate for a three-dimensional position at the time of interest corresponds to the object;
A determining means for determine a constant three-dimensional position of the object in the time of interest based on the integrated response accuracy,
An image processing apparatus comprising:
前記着目時刻における三次元位置の候補のそれぞれについて、1つのフレーム画像群上で追尾されている物体に対応して記録されている前記積算対応確度を取得し、
複数のフレーム画像群のそれぞれについて前記取得された積算対応確度に応じて前記三次元位置の候補の信頼度を求め、
前記信頼度に基づいて前記着目時刻における前記物体の三次元位置を判定する
ことを特徴とする、請求項1に記載の画像処理装置。 It said determination means,
Wherein for each candidate of the three-dimensional position in the time of interest, acquires the accumulated corresponding likelihood of being recorded in correspondence with the object being tracked on a frame image group,
Seeking Shin Yoriyukido candidate of the three-dimensional position in accordance with the accumulated corresponding likelihood of being the acquired for each of the plurality of frame images group,
Wherein the determining the three-dimensional position of the object in the time of interest on the basis of the reliability, the image processing apparatus according to claim 1.
前記信頼度が最も高い三次元位置の候補であって、当該三次元位置の候補に対応する物体が所定数以上存在する三次元位置の候補を選択して、前記着目時刻における前記物体の三次元位置に対応すると判定する選択処理と、
前記選択された三次元位置の候補と、当該三次元位置の候補に対応する物体と、を前記選択処理における対象から外す除外処理と、
を繰り返すことを特徴とする、請求項2乃至10の何れか1項に記載の画像処理装置。 The determination means includes
A candidate for the highest three-dimensional position before relaxin Yoriyukido, objects corresponding to the candidate of the three-dimensional position selects a candidate of the three-dimensional position occurs more than a predetermined number, of the object in the time of interest A selection process for determining that it corresponds to a three-dimensional position;
The candidate of the selected three-dimensional position, a removal process removing the object corresponding to the candidate of the three-dimensional position, from put that Target in the selection process,
The image processing apparatus according to claim 2, wherein the image processing apparatus is repeated.
連続して撮影されたフレーム画像群を、視野が重複している複数の撮像部のそれぞれから取得する取得工程と、
前記フレーム画像群上の物体を追尾する追尾工程と、
前記物体のフレーム画像上の位置と前記複数の撮像部間の位置関係とに基づいて着目時刻における前記物体の三次元位置の候補を生成する生成工程と、
前記着目時刻における三次元位置の候補と、前記着目時刻より前の過去時刻における前記物体の三次元位置の候補とを対応付ける対応付け工程と、
前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す局所対応確度と、前記過去時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度と、に基づいて、前記着目時刻における三次元位置の候補が前記物体に対応する確度を示す積算対応確度を求める算出工程と、
前記積算対応確度に基づいて前記着目時刻における前記物体の三次元位置を判定する判定工程と、
を備えることを特徴とする画像処理方法。 An image processing method performed by an image processing apparatus,
An acquisition step of acquiring a group of continuously captured frame images from each of a plurality of imaging units having overlapping fields of view;
A tracking step of tracking an object on the frame image group;
Generating a candidate for the three-dimensional position of the object at the time of interest based on the position of the object on the frame image and the positional relationship between the plurality of imaging units;
An association step of associating a candidate for a three-dimensional position at the time of interest with a candidate for a three-dimensional position of the object at a past time prior to the time of interest;
And local corresponding probability indicating the likelihood of the candidate of the three-dimensional position before Symbol focused time corresponding to the object, the integrated response probability indicating the likelihood of a candidate of the three-dimensional position in the past time corresponding to the object, on the basis Calculating a cumulative correspondence accuracy indicating a probability that a candidate for a three-dimensional position at the time of interest corresponds to the object;
A determination step of determining a three-dimensional position of the object at the time of interest based on the cumulative correspondence accuracy;
An image processing method comprising:
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015131841A JP6659095B2 (en) | 2015-06-30 | 2015-06-30 | Image processing apparatus, image processing method, and program |
US15/084,381 US9877012B2 (en) | 2015-04-01 | 2016-03-29 | Image processing apparatus for estimating three-dimensional position of object and method therefor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015131841A JP6659095B2 (en) | 2015-06-30 | 2015-06-30 | Image processing apparatus, image processing method, and program |
Publications (3)
Publication Number | Publication Date |
---|---|
JP2017016356A JP2017016356A (en) | 2017-01-19 |
JP2017016356A5 true JP2017016356A5 (en) | 2018-08-09 |
JP6659095B2 JP6659095B2 (en) | 2020-03-04 |
Family
ID=57829253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2015131841A Active JP6659095B2 (en) | 2015-04-01 | 2015-06-30 | Image processing apparatus, image processing method, and program |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP6659095B2 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111670456B (en) * | 2018-02-08 | 2023-09-15 | 三菱电机株式会社 | Information processing apparatus, tracking method, and recording medium |
CN110675426B (en) | 2018-07-02 | 2022-11-22 | 百度在线网络技术(北京)有限公司 | Human body tracking method, device, equipment and storage medium |
JP6800509B1 (en) * | 2020-09-30 | 2020-12-16 | アースアイズ株式会社 | Shooting system and shooting method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007281792A (en) * | 2006-04-05 | 2007-10-25 | Mitsubishi Electric Corp | Dynamic management apparatus |
JP2009143722A (en) * | 2007-12-18 | 2009-07-02 | Mitsubishi Electric Corp | Person tracking apparatus, person tracking method and person tracking program |
JP2010063001A (en) * | 2008-09-05 | 2010-03-18 | Mitsubishi Electric Corp | Person-tracking device and person-tracking program |
JP6186834B2 (en) * | 2013-04-22 | 2017-08-30 | 富士通株式会社 | Target tracking device and target tracking program |
-
2015
- 2015-06-30 JP JP2015131841A patent/JP6659095B2/en active Active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11004210B2 (en) | Methods circuits devices systems and associated computer executable code for extraction of visible features present within a video feed from a scene | |
WO2016147644A1 (en) | Image processing apparatus, image processing system, method for image processing, and computer program | |
JP7134012B2 (en) | Parallax estimation device and method | |
KR101283262B1 (en) | Method of image processing and device thereof | |
JP2018049591A5 (en) | Image processing apparatus, image processing method, and program | |
JP2018198056A5 (en) | ||
JP6454984B2 (en) | Hand position determination method and device based on depth image | |
JP2010134649A5 (en) | ||
KR20130066438A (en) | Image processing apparatus and image processing method | |
CN104969261B (en) | For detecting the method and system of mobile object | |
US8660302B2 (en) | Apparatus and method for tracking target | |
JP2015090298A5 (en) | ||
JP2014009975A (en) | Stereo camera | |
JP2015079433A5 (en) | ||
JP2016220198A5 (en) | ||
JP2018036898A5 (en) | Image processing apparatus, image processing method, and program | |
JP2021060868A5 (en) | ||
JP2016218758A5 (en) | ||
JP2017016356A5 (en) | ||
JP2018081402A5 (en) | ||
JP2016217944A5 (en) | ||
JP6527183B2 (en) | Leftover object detection device | |
JP6558831B2 (en) | Object tracking apparatus, method and program | |
JP6659095B2 (en) | Image processing apparatus, image processing method, and program | |
JP2017196948A (en) | Three-dimensional measurement device and three-dimensional measurement method for train facility |