JP2017120672A5 - Image processing apparatus, image processing system, and image processing method - Google Patents

Image processing apparatus, image processing system, and image processing method Download PDF

Info

Publication number
JP2017120672A5
JP2017120672A5 JP2017076805A JP2017076805A JP2017120672A5 JP 2017120672 A5 JP2017120672 A5 JP 2017120672A5 JP 2017076805 A JP2017076805 A JP 2017076805A JP 2017076805 A JP2017076805 A JP 2017076805A JP 2017120672 A5 JP2017120672 A5 JP 2017120672A5
Authority
JP
Japan
Prior art keywords
image
image processing
luminance
acquired
processing apparatus
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
JP2017076805A
Other languages
Japanese (ja)
Other versions
JP2017120672A (en
JP6255125B2 (en
Filing date
Publication date
Application filed filed Critical
Priority to JP2017076805A priority Critical patent/JP6255125B2/en
Priority claimed from JP2017076805A external-priority patent/JP6255125B2/en
Publication of JP2017120672A publication Critical patent/JP2017120672A/en
Publication of JP2017120672A5 publication Critical patent/JP2017120672A5/en
Application granted granted Critical
Publication of JP6255125B2 publication Critical patent/JP6255125B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Description

本発明は、入力画像から対象物体の画像を検出する画像認識処理に用いられる辞書生成用の学習画像を生成する画像処理装置、画像処理システム、および画像処理方法に関する。 The present invention relates to an image processing apparatus , an image processing system, and an image processing method for generating a learning image for generating a dictionary used for image recognition processing for detecting an image of a target object from an input image.

本発明は上記問題に鑑み、実環境下で対象物体を撮影した情報に基づき、環境条件を反映して対象物体の表面輝度を近似した学習画像を、容易に生成する画像処理装置、画像処理システム、および画像処理方法を提供することを目的とする。 In view of the above problems, the present invention provides an image processing apparatus and an image processing system that easily generate a learning image that approximates the surface luminance of a target object by reflecting environmental conditions based on information obtained by photographing the target object in a real environment. And an image processing method.

上記目的を達成するための一手段として、本発明の画像処理装置は以下の構成を備える。すなわち、物体の認識において参照される辞書の生成に用いられる学習画像を生成する画像処理装置であって、
姿勢の異なる複数の前記物体を含む輝度画像から複数の領域の各々における前記物体の表面の輝度値を取得し、前記複数の領域の各々における前記物体の表面の向きに係る情報を取得する第１の取得手段と、
前記第１の取得手段により取得した前記複数の領域における前記物体の表面の向きに係る情報と各領域に対応する輝度値との関係を取得する第２の取得手段と、
前記第２の取得手段により取得した関係と前記物体のモデル情報とに基づいて、前記学習画像を生成する生成手段と
を有することを特徴とする。 As a means for achieving the above object, an image processing apparatus of the present invention comprises the following arrangement. That is, an image processing apparatus for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. Acquisition means of
Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
And generating means for generating the learning image based on the relationship acquired by the second acquiring means and the model information of the object .

Claims (23)

物体の認識において参照される辞書の生成に用いられる学習画像を生成する画像処理装置であって、
姿勢の異なる複数の前記物体を含む輝度画像から複数の領域の各々における前記物体の表面の輝度値を取得し、前記複数の領域の各々における前記物体の表面の向きに係る情報を取得する第１の取得手段と、
前記第１の取得手段により取得した前記複数の領域における前記物体の表面の向きに係る情報と各領域に対応する輝度値との関係を取得する第２の取得手段と、
前記第２の取得手段により取得した関係と前記物体のモデル情報とに基づいて、前記学習画像を生成する生成手段と
を有することを特徴とする画像処理装置。 An image processing apparatus for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. Acquisition means of
Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
An image processing apparatus comprising: a generation unit configured to generate the learning image based on the relationship acquired by the second acquisition unit and the model information of the object . 前記第１の取得手段は、姿勢の異なる複数の前記物体を含む輝度画像を複数枚取得し、各輝度画像から複数の領域における前記物体の表面の輝度値を取得し、前記各輝度画像に対して、前記複数の領域における前記物体の表面の向きに係る情報を取得し、The first acquisition means acquires a plurality of luminance images including a plurality of the objects having different postures, acquires a luminance value of the surface of the object in a plurality of regions from each luminance image, and for each luminance image Obtaining information related to the orientation of the surface of the object in the plurality of regions,
前記第２の取得手段は、前記各輝度画像に対して、前記第１の取得手段により取得した前記複数の領域における前記物体の表面の向きに係る情報と各領域に対応する輝度値との関係を取得することを特徴とする請求項１に記載の画像処理装置。The second acquisition means, for each of the luminance images, a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area The image processing apparatus according to claim 1, further comprising: 前記第１の取得手段は、前記輝度画像の各画素の距離情報を取得し、該取得した距離情報に基づいて前記複数の領域における前記物体の表面の向きに係る情報を取得することを特徴とする請求項１又は２に記載の画像処理装置。The first acquisition means acquires distance information of each pixel of the luminance image, and acquires information related to the orientation of the surface of the object in the plurality of regions based on the acquired distance information. The image processing apparatus according to claim 1 or 2. 前記姿勢の異なる複数の物体を含む輝度画像は、前記複数の物体がランダムに配された状態で撮影された画像であることを特徴とする請求項１乃至３の何れか１項に記載の画像処理装置。4. The image according to claim 1, wherein the luminance image including the plurality of objects having different postures is an image taken in a state where the plurality of objects are randomly arranged. 5. Processing equipment. 前記姿勢の異なる複数の物体を含む輝度画像は、前記複数の物体が山積みされた状態で撮影された画像であることを特徴とする請求項１乃至４の何れか１項に記載の画像処理装置。5. The image processing apparatus according to claim 1, wherein the luminance image including the plurality of objects having different postures is an image captured in a state where the plurality of objects are piled up. 6. . 前記第２の取得手段により取得した関係に基づいて、前記物体の表面における輝度分布を推定する推定手段を更に有し、
前記生成手段は、前記推定手段により推定した輝度分布と前記物体のモデル情報とに基づいて、前記学習画像を生成することを特徴とする請求項１乃至５の何れか１項に記載の画像処理装置。 Based on the relationship acquired by the second acquisition means, further comprising an estimation means for estimating a luminance distribution on the surface of the object;
The generation unit, based on the model information of the object and luminance distribution estimated by the estimating means, the image processing according to any one of claims 1 to 5, characterized in that to generate the learning image apparatus. 前記生成手段は、前記物体の表面の向きに係る情報に応じた輝度値を前記輝度分布の分散から決定することを特徴とする請求項６に記載の画像処理装置。 The image processing apparatus according to claim 6 , wherein the generation unit determines a luminance value corresponding to information related to a direction of the surface of the object from a distribution of the luminance distribution. 前記推定手段は、前記第２の取得手段により取得した関係と所定の輝度分布モデルとに基づいて、前記輝度分布を推定することを特徴とする請求項６に記載の画像処理装置。 The image processing apparatus according to claim 6 , wherein the estimation unit estimates the luminance distribution based on a relationship acquired by the second acquisition unit and a predetermined luminance distribution model. 前記推定手段は、複数の輝度分布モデルを取得する手段と、該複数の輝度分布モデルに前記第２の取得手段により取得した関係を割り当てる割り当て手段と、前記複数の輝度分布モデルを該輝度分布モデルに割り当てられている関係に基づいて更新する更新手段と、を有することを特徴とする請求項８に記載の画像処理装置。 Said estimating means, means and, said plurality of the means for assigning the acquired relationship by the second acquisition unit to the luminance distribution model, the luminance distribution model said plurality of luminance distribution models for obtaining a plurality of intensity distribution model The image processing apparatus according to claim 8 , further comprising an update unit configured to update based on a relationship assigned to the image processing apparatus. 前記割り当て手段は、前記第２の取得手段により取得した関係が示す前記物体の表面の向きに係る情報を入力して得られる輝度値が該関係により求められる輝度値に最も近い前記輝度分布モデルに対して、該関係を割り当てることを特徴とする請求項９に記載の画像処理装置。 The assigning means is configured to input the information related to the orientation of the surface of the object indicated by the relationship acquired by the second acquiring means to the brightness distribution model closest to the brightness value obtained by the relationship. The image processing apparatus according to claim 9 , wherein the relationship is assigned to the image processing apparatus. 前記更新の前後における前記第２の取得手段により取得した関係の割当先が一致するまで、前記割り当て手段及び前記更新手段に処理を繰り返し行わせる手段を更に有することを特徴とする請求項９に記載の画像処理装置。 10. The apparatus according to claim 9 , further comprising : a unit that causes the allocation unit and the update unit to repeatedly perform processing until the allocation destinations of the relationship acquired by the second acquisition unit before and after the update match. Image processing apparatus. 前記生成手段は、前記物体の複数の姿勢に対応する射影変換を、前記物体のモデル情報に対して行い、該射影変換後の前記モデル情報によって示される前記物体の表面の向きに、該物体の表面の向きに対応する輝度値を与えて、前記姿勢ごとの前記学習画像を生成することを特徴とする請求項１乃至１１の何れか１項に記載の画像処理装置。 The generating means performs projective transformation corresponding to a plurality of postures of the object on the model information of the object, and in the orientation of the surface of the object indicated by the model information after the projective transformation , giving a brightness value corresponding to the orientation of the surface, the image processing apparatus according to any one of claims 1 to 11, characterized in that to generate the learning images for each of the posture. 前記モデル情報はＣＡＤデータであり、前記学習画像はＣＧ画像であることを特徴とする請求項１乃至１２の何れか１項に記載の画像処理装置。 The model information is CAD data, the learning image is an image processing apparatus according to any one of claims 1 to 12, characterized in that a CG image. 前記第１の取得手段により取得した物体の表面の向きに係る情報は、該物体の表面の法線の情報であることを特徴とする請求項１乃至１３の何れか１項に記載の画像処理装置。The image processing according to any one of claims 1 to 13, wherein the information related to the orientation of the surface of the object acquired by the first acquisition means is information on a normal of the surface of the object. apparatus. 前記輝度画像と前記物体のモデル情報から距離画像を生成する距離画像生成手段を更に有することを特徴とする請求項１乃至１４の何れか１項に記載の画像処理装置。 The image processing apparatus according to any one of claims 1 to 14, further comprising a distance image generating means for generating a distance image from the model information of the said luminance image object. 前記距離画像は、前記物体の表面の位置を表すことを特徴とする請求項１５に記載の画像処理装置。 The image processing apparatus according to claim 15 , wherein the distance image represents a position of a surface of the object. 前記生成手段により生成された学習画像に基づいて、前記物体を認識するための識別器を生成する手段を更に有することを特徴とする請求項１乃至１６の何れか１項に記載の画像処理装置。 Based on the generated training image by the generation unit, an image processing apparatus according to any one of claims 1 to 16, further comprising means for generating a classifier for recognizing said object . 前記物体を含む画像を取得する手段と、
前記識別器に基づいて、前記物体を含む画像から前記物体を認識する認識手段と
を更に有することを特徴とする請求項１７に記載の画像処理装置。 It means for obtaining an image including the object,
Recognition means for recognizing the object from an image including the object based on the classifier ;
The image processing apparatus according to claim 17 , further comprising: 前記姿勢の異なる複数の物体を含む輝度画像は、前記物体の認識と同じ照明条件で撮影された画像であることを特徴とする請求項１乃至１８の何れか１項に記載の画像処理装置。The image processing apparatus according to claim 1, wherein the luminance image including a plurality of objects having different postures is an image photographed under the same illumination condition as the recognition of the object. 物体の認識において参照される辞書の生成に用いられる学習画像を生成する画像処理方法であって、
姿勢の異なる複数の前記物体を含む輝度画像から複数の領域の各々における前記物体の表面の輝度値を取得し、前記複数の領域の各々における前記物体の表面の向きに係る情報を取得する第１の取得ステップと、
前記第１の取得ステップで取得した前記複数の領域における前記物体の表面の向きに係る情報と各領域に対応する輝度値との関係を取得する第２の取得ステップと、
前記第２の取得ステップで取得した関係と前記物体のモデル情報とに基づいて、前記学習画像を生成する生成ステップと
を有することを特徴とする画像処理方法。 An image processing method for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. The acquisition step of
A second acquisition step of acquiring a relationship between the luminance value corresponding to the information and each region according to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition step,
An image processing method comprising: a generation step of generating the learning image based on the relationship acquired in the second acquisition step and the model information of the object . 前記輝度画像を入力するステップを更に有し、Further comprising the step of inputting the luminance image;
前記第１の取得ステップでは、前記入力された輝度画像の複数の領域の各々における前記物体の表面の輝度値を取得し、前記複数の領域の各々における前記物体の表面の向きに係る情報を取得することを特徴とする請求項２０に記載の画像処理方法。In the first acquisition step, the luminance value of the surface of the object in each of the plurality of regions of the input luminance image is acquired, and information relating to the orientation of the surface of the object in each of the plurality of regions is acquired. The image processing method according to claim 20, wherein: 物体の認識において参照される辞書の生成に用いられる学習画像を生成する画像処理システムであって、An image processing system for generating a learning image used for generating a dictionary referred to in object recognition,
姿勢の異なる複数の前記物体を含む輝度画像を撮影する撮影手段と、Photographing means for photographing a luminance image including a plurality of the objects having different postures;
前記撮影された輝度画像から複数の領域の各々における前記物体の表面の輝度値を取得し、前記複数の領域の各々における前記物体の表面の向きに係る情報を取得する第１の取得手段と、First acquisition means for acquiring a luminance value of the surface of the object in each of a plurality of areas from the captured luminance image, and acquiring information relating to the orientation of the surface of the object in each of the plurality of areas;
前記第１の取得手段により取得した前記複数の領域における前記物体の表面の向きに係る情報と各領域に対応する輝度値との関係を取得する第２の取得手段と、Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
前記第２の取得手段により取得した関係と前記物体のモデル情報とに基づいて、前記学習画像を生成する生成手段とGenerating means for generating the learning image based on the relationship acquired by the second acquiring means and the model information of the object;
を有することを特徴とする画像処理システム。An image processing system comprising: コンピュータ装置で実行されることにより、該コンピュータ装置を請求項１乃至１９の何れか１項に記載の画像処理装置の各手段として機能させるためのプログラム。 A program for causing a computer device to function as each unit of the image processing device according to any one of claims 1 to 19 when executed by the computer device.
JP2017076805A 2017-04-07 2017-04-07 Image processing apparatus, image processing system, and image processing method Active JP6255125B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2017076805A JP6255125B2 (en) 2017-04-07 2017-04-07 Image processing apparatus, image processing system, and image processing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2017076805A JP6255125B2 (en) 2017-04-07 2017-04-07 Image processing apparatus, image processing system, and image processing method

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
JP2013074860A Division JP6126437B2 (en) 2013-03-29 2013-03-29 Image processing apparatus and image processing method

Publications (3)

Publication Number Publication Date
JP2017120672A JP2017120672A (en) 2017-07-06
JP2017120672A5 true JP2017120672A5 (en) 2017-08-17
JP6255125B2 JP6255125B2 (en) 2017-12-27

Family

ID=59272288

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2017076805A Active JP6255125B2 (en) 2017-04-07 2017-04-07 Image processing apparatus, image processing system, and image processing method

Country Status (1)

Country Link
JP (1) JP6255125B2 (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019061484A (en) 2017-09-26 2019-04-18 キヤノン株式会社 Image processing device and control method thereof and program
EP3474185B1 (en) * 2017-10-18 2023-06-28 Dassault Systèmes Classification of 2d images according to types of 3d arrangement
WO2019167277A1 (en) * 2018-03-02 2019-09-06 日本電気株式会社 Image collection device, image collection system, image collection method, image generation device, image generation system, image generation method, and program
WO2019192744A1 (en) 2018-04-06 2019-10-10 Siemens Aktiengesellschaft Object recognition from images using cad models as prior
JP7017462B2 (en) * 2018-04-26 2022-02-08 株式会社神戸製鋼所 Learning image generation device and learning image generation method, as well as image recognition device and image recognition method
JP7186521B2 (en) * 2018-06-12 2022-12-09 シチズンファインデバイス株式会社 Teacher image generator for visual inspection equipment
JP7446615B2 (en) * 2020-11-09 2024-03-11 東京ロボティクス株式会社 Data set generation device, generation method, program, system, machine learning device, object recognition device, and picking system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5290865B2 (en) * 2009-05-18 2013-09-18 キヤノン株式会社 Position and orientation estimation method and apparatus

Similar Documents

Publication Publication Date Title
JP2017120672A5 (en) Image processing apparatus, image processing system, and image processing method
JP2014199584A5 (en)
US10803351B2 (en) Image processing apparatus and image processing method
CN108292362B (en) Gesture recognition for cursor control
JP5837508B2 (en) Posture state estimation apparatus and posture state estimation method
US9665803B2 (en) Image processing apparatus and image processing method
JP6844692B2 (en) Learning data generator, learning data generation method, and program
JP6793151B2 (en) Object tracking device, object tracking method and object tracking program
JP2018116599A5 (en)
JP2010512581A (en) Fast human pose estimation using appearance and motion via multidimensional boost regression
KR20130101942A (en) Method and apparatus for motion recognition
JP2014137756A5 (en)
JP2019040229A5 (en)
JP2015219868A (en) Information processor, information processing method and program
JP5704909B2 (en) Attention area detection method, attention area detection apparatus, and program
JP2018042237A5 (en)
US20210042576A1 (en) Image processing system
JP2015203680A (en) Information processing device, method, and program
JP2017033556A (en) Image processing method and electronic apparatus
JP2021108022A5 (en)
JP2015187769A (en) Object detection device, object detection method, and program
JP7433849B2 (en) Information processing device, information processing method and program
JP2023008030A (en) Image processing system, image processing method, and image processing program
JP2014178967A (en) Three-dimensional object recognition device and three-dimensional object recognition method
US20220005223A1 (en) Coordinate calculation apparatus, coordinate calculation method, and computer-readable recording medium