JPH07229726A - Method for detecting angle of object - Google Patents

Method for detecting angle of object

Info

Publication number
JPH07229726A
JPH07229726A JP6018772A JP1877294A JPH07229726A JP H07229726 A JPH07229726 A JP H07229726A JP 6018772 A JP6018772 A JP 6018772A JP 1877294 A JP1877294 A JP 1877294A JP H07229726 A JPH07229726 A JP H07229726A
Authority
JP
Japan
Prior art keywords
binarized image
image
extracted
angle
axis direction
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.)
Pending
Application number
JP6018772A
Other languages
Japanese (ja)
Inventor
Haruyuki Domae
晴之 堂前
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.)
Kubota Corp
Original Assignee
Kubota Corp
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 Kubota Corp filed Critical Kubota Corp
Priority to JP6018772A priority Critical patent/JPH07229726A/en
Publication of JPH07229726A publication Critical patent/JPH07229726A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Processing (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

PURPOSE:To easily detect the angle of an object to be carried on a carrying device. CONSTITUTION:The contour line of an object is extracted as the binarized image V', and a plurality of lines L1, L2 crossing the binarized image V' are prepared in parallel to each other at appropriate space. Overlapped parts R1, R2, R3, R4 where the lines cross the image are extracted with labeling, and the position of the center of gravity and the maximum length D in X-axis or Y-axis direction according to the direction of the lines L1, L2 are obtained in each overlapped part. The point on the outer circumferential side by the distance of D/2 in X-axis or Y-axis direction from the center of gravity is judged as the outermost contour point of the object, and the gradient of either line connecting the adjacent outermost contour points is detected as the gradient of the object. The processing speed is fast because only the range of the overlapped parts is processed.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】本発明は物体の角度検出方法に関
し、特にベルトコンベヤなどの搬送装置上を搬送されて
いる物体の載置角度を検出する物体の角度検出方法に関
する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an object angle detecting method, and more particularly to an object angle detecting method for detecting a mounting angle of an object being conveyed on a conveyor such as a belt conveyor.

【0002】[0002]

【従来の技術】従来、ベルトコンベヤなどの搬送装置上
を搬送されている物体の載置角度を検出する方法として
は、対象物体を撮影して、撮影画像の輪郭線を画像解析
的に追跡し、その追跡方向から物体の角度を検出する方
法が知られている。
2. Description of the Related Art Conventionally, as a method of detecting the mounting angle of an object being conveyed on a conveyor device such as a belt conveyor, the object is photographed and the contour line of the photographed image is traced by image analysis. , A method of detecting the angle of an object from the tracking direction is known.

【0003】[0003]

【発明が解決しようとする課題】しかしながら、上記し
た従来の検出方法は、輪郭線の追跡に処理時間がかか
り、物体が大きければそれだけ長い処理時間がかるとい
う問題がある。
However, the above-described conventional detection method has a problem that it takes a long processing time to trace the contour line, and that the processing time increases as the size of the object increases.

【0004】本発明は上記問題を解決するもので、長い
処理時間を要することなく物体の角度を検出できるよう
にすることを目的とするものである。
The present invention has been made to solve the above problems, and an object of the present invention is to make it possible to detect the angle of an object without requiring a long processing time.

【0005】[0005]

【課題を解決するための手段】上記問題を解決するため
に、本発明の物体の角度検出方法は、対象物体を撮影し
てその撮影データを画像処理することにより対象物体の
輪郭線を2値化画像として抽出し、この2値化画像上
に、2値化画像と交わる直線を適当間隔で平行に複数本
作成して、2値化画像と各直線とが重なる重複部を抽出
し、この重複部をそれぞれラベリングして、ラベリング
された各重複部における重心の位置と前記直線の方向に
応じたX軸方向またはY軸方向の最大長さDとを求め、
前記重心より前記X軸方向またはY軸方向にD/2の距
離だけ外周側の点を物体の最外輪郭点と判別し、隣接す
る最外輪郭点どうしを連結したいずれかの直線の傾きを
物体の角度として検出することを特徴とする。
In order to solve the above-mentioned problems, the method for detecting the angle of an object according to the present invention uses a binary image of the contour line of the target object by photographing the target object and image-processing the captured data. Extracted as a binarized image, a plurality of straight lines intersecting the binarized image are created in parallel on the binarized image at appropriate intervals, and an overlapping portion where the binarized image and each line overlap is extracted. The overlapping portions are each labeled, and the position of the center of gravity in each labeled overlapping portion and the maximum length D in the X-axis direction or the Y-axis direction according to the direction of the straight line are obtained,
A point on the outer peripheral side from the center of gravity in the X-axis direction or the Y-axis direction by a distance of D / 2 is determined as the outermost contour point of the object, and the inclination of any straight line connecting adjacent outermost contour points is determined. The feature is that it is detected as an angle of the object.

【0006】[0006]

【作用】上記構成によれば、対象物体の輪郭線を抽出し
て2値化した2値化画像と、この2値化画像上に作成し
た複数本の平行な直線とが重なる重複部を抽出し、この
重複部より物体の最外輪郭点を複数箇所求めて、隣接す
る最外輪郭点どうしがなす直線の傾きを物体の角度とし
て検出するので、重複部の領域を処理するだけでよく、
処理速度が速い。また、処理方法も単純である。
According to the above construction, the overlapping portion in which the binarized image obtained by extracting the contour line of the target object and binarized and the plurality of parallel straight lines created on the binarized image overlap are extracted. However, the outermost contour points of the object are obtained at a plurality of positions from this overlapping portion, and the inclination of the straight line formed by the adjacent outermost contour points is detected as the angle of the object, so it is sufficient to process the area of the overlapping portion.
The processing speed is fast. The processing method is also simple.

【0007】[0007]

【実施例】以下、本発明の一実施例の物体の角度検出方
法を、図1に示したフローチャートの流れに沿って、図
2〜図11に示したモニター画面に基づき説明する。
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An object angle detecting method according to an embodiment of the present invention will be described below with reference to the monitor screens shown in FIGS. 2 to 11 along the flow of the flow chart shown in FIG.

【0008】a) ベルトコンベヤなどの搬送装置上を
一定速度で搬送されている対象物体を撮影し、その撮影
データを画像入力して、図2に示したような対象物体の
画像Vを得る。
A) A target object being conveyed at a constant speed on a conveyor device such as a belt conveyor is photographed, and the photographed data is input as an image to obtain an image V of the target object as shown in FIG.

【0009】b) 画像Vの輪郭線を抽出して2値化処
理し、図3に示したような、物体の輪郭線の2値化画像
V’を得る。 c) 2値化画像V’上に、図4に示したような外接四
角形S(または外接円でもよい)を作成する。
B) The contour line of the image V is extracted and binarized to obtain a binarized image V'of the contour line of the object as shown in FIG. c) Create a circumscribing quadrangle S (or a circumscribing circle) as shown in FIG. 4 on the binarized image V ′.

【0010】d) 外接四角形S内に2値化画像V’と
交わる平行な直線L1 ,L2 を適当間隔をおいて作成す
る。直線L1 ,L2 は、図5に示したように、2値化画
像V’の傾きが容易にわかるような、たとえば各々が2
値化画像V’の辺Va , Vbと交わるものとすればよ
く、複数本であれば本数は限定されない。
D) Parallel lines L 1 and L 2 that intersect the binarized image V ′ are created in the circumscribed quadrangle S at appropriate intervals. As shown in FIG. 5, the straight lines L 1 and L 2 are such that the inclination of the binarized image V ′ can be easily seen, for example, each is 2
It suffices that it intersects the sides V a and V b of the binarized image V ′, and the number is not limited as long as it is plural.

【0011】e) 2値化画像V’と直線L1 ,L2
が重なる部分を抽出して、図6に示したような重複部R
1 ,R2 ,R3 ,R4 の画像を得る。 f) 重複部R1 ,R2 ,R3 ,R4 の画像をラベリン
グ処理して、図7に示したような、ラベリングされた重
複部R1 ,R2 ,R3 ,R4 の画像を得る。
E) A portion where the binarized image V ′ and the straight lines L 1 and L 2 overlap is extracted, and the overlapping portion R as shown in FIG. 6 is extracted.
Images of 1 , R 2 , R 3 and R 4 are obtained. f) with the image of the overlapping portion R 1, R 2, R 3 , R 4 and labeling, as shown in FIG. 7, the overlapping portions are labeled R 1, R 2, R 3 , an image of R 4 obtain.

【0012】g) 図7に示した重複部R1 ,R2 ,R
3 ,R4 の画像をさらに処理して、図8に示したよう
な、重複部R1 における重心G1 の位置を求めるととも
に、重複部R1 における、直線L1 の方向に応じたY軸
方向の最大長さD1 を求める。同様にして、各重複部R
2 ,R3 ,R4 において、重心G2 ,G3 ,G4 の位置
と、Y軸方向の最大長さD2 ,D3 ,D4 を求める。
G) Overlapping parts R 1 , R 2 and R shown in FIG.
The images of 3 and R 4 are further processed to obtain the position of the center of gravity G 1 in the overlapping portion R 1 as shown in FIG. 8, and the Y-axis corresponding to the direction of the straight line L 1 in the overlapping portion R 1 is obtained. Find the maximum length D 1 in the direction. Similarly, each overlapping portion R
In 2, R 3, R 4, determine the position of the center of gravity G 2, G 3, G 4 , the Y maximum length of axis D 2, D 3, D 4 .

【0013】h) 図9に示したように、各重心G1
2 ,G3 ,G4 よりそれぞれD1/2,D2/2,D3
/2,D4/2の距離だけY軸方向に外周側の点P1
2 ,P3 ,P4 を求めて、これらの点を物体の最外輪
郭点として判別する。
H) As shown in FIG. 9, the center of gravity G 1 ,
G 2, G 3, respectively from the G 4 D 1/2, D 2/2, D 3
/ 2, D 4/2 of distance point P 1 on the outer peripheral side in the Y-axis direction,
Seeking P 2, P 3, P 4 , to determine these points as the outermost contour point of an object.

【0014】i) 隣接する最外輪郭点どうし、たとえ
ばP1 とP2 、およびP3 とP4 を連結して図10に示
したような直線L3 ,L4 を得、直線L3 ,L4 のいず
れかを選択する。そして、図11に示したような、選択
した直線L3 の傾きを物体の角度として検出する。
[0014] i) adjacent the outermost contour point to each other, for example, P 1 and P 2, and P 3 and P 4 are connected to give a straight line L 3, L 4, as shown in FIG. 10, the straight line L 3, Select one of L 4 . Then, the inclination of the selected straight line L 3 as shown in FIG. 11 is detected as the angle of the object.

【0015】以上のように、対象物体の輪郭線を2値化
した2値化画像V’と、この2値化画像V’上に作成し
た直線L1 ,L2 とが重なる重複部R1 ,R2 ,R3
4を抽出し、この重複部をラベリングおよび数的処理
して物体の最外輪郭点P1 ,P2 ,P3 ,P4 を求め、
この最外輪郭点より物体の角度を検出する方法であるた
め、重複部という小領域をラベリングするだけでよく、
処理速度が速い。このとき、対象物体の大きさに関係な
く処理できるとともに、複数の画像が存在する場合でも
処理可能である。さらに、単純な処理方法であるため、
オンライン処理にも適用可能である。
As described above, the overlapping portion R 1 in which the binarized image V ′ obtained by binarizing the contour line of the target object and the straight lines L 1 and L 2 created on the binarized image V ′ overlap each other , R 2 , R 3 ,
R 4 is extracted, and the overlapping portion is labeled and numerically processed to obtain outermost contour points P 1 , P 2 , P 3 , P 4 of the object,
Since this is the method of detecting the angle of the object from the outermost contour points, all that is required is to label the small area called the overlapping part,
The processing speed is fast. At this time, the processing can be performed regardless of the size of the target object, and even when there are a plurality of images. Furthermore, since it is a simple processing method,
It is also applicable to online processing.

【0016】[0016]

【発明の効果】以上のように本発明によれば、対象物体
の輪郭線を2値化画像として抽出し、この2値化画像
と、2値化画像上に作成した複数本の直線とが重なる重
複部を抽出して、この重複部という小領域を処理するこ
とにより物体の角度を検出する構成であるため、処理速
度が速いだけでなく、対象物体の大きさに関係なく処理
でき、複数の画像が存在する場合でも処理可能である。
また、単純な処理方法であるため、オンライン処理にも
適用可能である。
As described above, according to the present invention, the contour line of the target object is extracted as a binarized image, and the binarized image and a plurality of straight lines created on the binarized image are extracted. Since the overlapping portion is extracted and the angle of the object is detected by processing the small area called the overlapping portion, not only the processing speed is high, but also processing can be performed regardless of the size of the target object. Can be processed even when the image of.
Further, since it is a simple processing method, it can be applied to online processing.

【図面の簡単な説明】[Brief description of drawings]

【図1】本発明の一実施例の物体の角度検出方法を説明
するフローチャートである。
FIG. 1 is a flowchart illustrating an object angle detection method according to an embodiment of the present invention.

【図2】同実施例を図1のフローチャートの流れに沿っ
て示した第1の説明図である。
FIG. 2 is a first explanatory diagram showing the same embodiment along the flow of the flowchart of FIG.

【図3】同実施例を図1のフローチャートの流れに沿っ
て示した第2の説明図である。
FIG. 3 is a second explanatory diagram showing the same embodiment along the flow of the flowchart of FIG.

【図4】同実施例を図1のフローチャートの流れに沿っ
て示した第3の説明図である。
FIG. 4 is a third explanatory diagram showing the same embodiment along the flow of the flowchart of FIG.

【図5】同実施例を図1のフローチャートの流れに沿っ
て示した第4の説明図である。
5 is a fourth explanatory view showing the embodiment according to the flow of the flowchart of FIG. 1. FIG.

【図6】同実施例を図1のフローチャートの流れに沿っ
て示した第5の説明図である。
FIG. 6 is a fifth explanatory diagram showing the same embodiment along the flow of the flowchart in FIG. 1.

【図7】同実施例を図1のフローチャートの流れに沿っ
て示した第6の説明図である。
FIG. 7 is a sixth explanatory diagram showing the same embodiment as the flow of the flowchart in FIG. 1.

【図8】同実施例を図1のフローチャートの流れに沿っ
て示した第7の説明図である。
FIG. 8 is a seventh explanatory view showing the embodiment along the flow of the flowchart of FIG. 1.

【図9】同実施例を図1のフローチャートの流れに沿っ
て示した第8の説明図である。
9 is an eighth explanatory diagram showing the same embodiment as the flow of the flowchart in FIG. 1. FIG.

【図10】同実施例を図1のフローチャートの流れに沿
って示した第9の説明図である。
FIG. 10 is a ninth explanatory diagram showing the same embodiment as the flowchart of FIG. 1.

【図11】同実施例を図1のフローチャートの流れに沿
って示した第10の説明図である。
FIG. 11 is a tenth explanatory view showing the embodiment along the flow of the flowchart of FIG. 1.

【符号の説明】[Explanation of symbols]

V 対象物体の画像 V’ 対象物体の2値化画像 L1,L2,L3,L4 直線 R1,R2,R3,R4 重複部 G1,G2,G3,G4 重複部の重心 P1,P2,P3,P4 物体の最外輪郭点Binarized image L 1 of the image V 'target object V object, L 2, L 3, L 4 straight R 1, R 2, R 3 , R 4 overlapping portions G 1, G 2, G 3 , G 4 Center of gravity of overlapping part P 1 , P 2 , P 3 , P 4 Outermost contour point of object

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】 対象物体を撮影してその撮影データを画
像処理することにより対象物体の輪郭線を2値化画像と
して抽出し、この2値化画像上に、2値化画像と交わる
直線を適当間隔で平行に複数本作成して、2値化画像と
各直線とが重なる重複部を抽出し、この重複部をそれぞ
れラベリングして、ラベリングされた各重複部における
重心の位置と前記直線の方向に応じたX軸方向またはY
軸方向の最大長さDとを求め、前記重心より前記X軸方
向またはY軸方向にD/2の距離だけ外周側の点を物体
の最外輪郭点と判別し、隣接する最外輪郭点どうしを連
結したいずれかの直線の傾きを物体の角度として検出す
ることを特徴とする物体の角度検出方法。
1. A contour line of a target object is extracted as a binarized image by photographing the target object and subjecting the photographed data to image processing, and a straight line intersecting with the binarized image is extracted on the binarized image. A plurality of parallel images are created at appropriate intervals to extract overlapping portions where the binarized image and each straight line are overlapped, and the overlapping portions are labeled respectively, and the position of the center of gravity at each labeled overlapping portion and the straight line X-axis direction or Y depending on direction
The maximum length D in the axial direction is obtained, and a point on the outer peripheral side from the center of gravity by a distance of D / 2 in the X-axis direction or the Y-axis direction is determined as the outermost contour point of the object, and the adjacent outermost contour points are determined. A method for detecting an angle of an object, which comprises detecting an inclination of any one of straight lines connecting the two as an angle of the object.
JP6018772A 1994-02-16 1994-02-16 Method for detecting angle of object Pending JPH07229726A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP6018772A JPH07229726A (en) 1994-02-16 1994-02-16 Method for detecting angle of object

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP6018772A JPH07229726A (en) 1994-02-16 1994-02-16 Method for detecting angle of object

Publications (1)

Publication Number Publication Date
JPH07229726A true JPH07229726A (en) 1995-08-29

Family

ID=11980933

Family Applications (1)

Application Number Title Priority Date Filing Date
JP6018772A Pending JPH07229726A (en) 1994-02-16 1994-02-16 Method for detecting angle of object

Country Status (1)

Country Link
JP (1) JPH07229726A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010186407A (en) * 2009-02-13 2010-08-26 Dainippon Screen Mfg Co Ltd Arrangement direction detection device, arrangement direction detection method, and arrangement direction detection program
JP2015147680A (en) * 2015-02-26 2015-08-20 日本電気株式会社 outline detection system
WO2019107141A1 (en) * 2017-11-30 2019-06-06 日本電産サンキョー株式会社 Image processing device and image processing method
JP2020003239A (en) * 2018-06-25 2020-01-09 株式会社富士通アドバンストエンジニアリング Baggage posture determination method, baggage posture determination program, and baggage posture determination device

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010186407A (en) * 2009-02-13 2010-08-26 Dainippon Screen Mfg Co Ltd Arrangement direction detection device, arrangement direction detection method, and arrangement direction detection program
JP2015147680A (en) * 2015-02-26 2015-08-20 日本電気株式会社 outline detection system
WO2019107141A1 (en) * 2017-11-30 2019-06-06 日本電産サンキョー株式会社 Image processing device and image processing method
JP2020003239A (en) * 2018-06-25 2020-01-09 株式会社富士通アドバンストエンジニアリング Baggage posture determination method, baggage posture determination program, and baggage posture determination device

Similar Documents

Publication Publication Date Title
JPH03294976A (en) Reference mark pattern detecting device
JPH07229726A (en) Method for detecting angle of object
CN105911065A (en) Pattern inspection apparatus and pattern inspection method
JPH04346187A (en) Quality decision method for subject to be detected
JP3460356B2 (en) Method and apparatus for detecting circle or ellipse
JPH1186199A (en) Method and device for detecting traffic lane
JP2000180138A (en) Calibration plate and calibration system for visual sensor utilizing it
JP3333224B2 (en) Traveling path detection device for mobile vehicles
JPH06201715A (en) Moving object detecting device
JPH01177682A (en) Graphic recognizing device
JPS6055474A (en) Detector for difference between images
JP3235392B2 (en) Rotation angle detection method for target pattern
JPS625480A (en) Edge detection system
Haga et al. The detection of lane boundary markings using the modified spoke filter
JP3048718B2 (en) Vertex detector
JPH02206882A (en) Picture processor
JP3562871B2 (en) Image processing device
JP2522511B2 (en) Image contour tracking unit
JPS59108907A (en) Position detecting device for three dimensional body
JPH0718810B2 (en) Pattern inspection method
JPH02179401A (en) Measuring method of object
JPH11232463A (en) Picture recognizing device and method therefor
JPS6186879A (en) Label attachment device to hole
JPH08287232A (en) Method for removing unmonitored object for image processing
JPH0855295A (en) Vehicle detecting device