KR950005469A

KR950005469A - Location Recognition Method

Info

Publication number: KR950005469A
Application number: KR1019940021298A
Authority: KR
Inventors: 킨지 오리카미; 요시히로 이츠자키; 마사야 나카오; 미스즈 티가노; 카즈마사 오쿠무라
Original assignee: 모리시타 요이찌; 마쯔시다덴기산교 가부시기가이샤
Priority date: 1993-08-31
Filing date: 1994-08-27
Publication date: 1995-03-20
Also published as: KR0167585B1; JPH0765175A

Abstract

본 발명은, 공장의 조립공정 등의 자동화에 사용하는 위치인식방법에 관한 것으로서, 범용성이 높고, 대상물이 회전어긋남이되어있어도, 간단, 신속, 정확한 위치·방향의 인식을 할 수 있는 위치인식방법을 제공하는 것을 목적으로 하고, 그 구성에 있어서, 윤곽에 복수의 원호형상(4) (5) (6)을 가진 대상물을 촬상수단에 의해서 촬상하고, 촬상된 영상정보를 농담화상데이터로 변경해서 기억수단에 기억하고, 상기 농담화상(2)을 농담화상(2)위의 상기 원호형상(4) (5) (6)과 동일 직경의 주사원형윤곽(15)과 이 주사원형윤곽(15)에 직교하고 이 주사원형윤곽(15)의 내외의 화상농도를 측정하는 복수개의 농도상관라인(16)으로 이루어진 원형윤곽주사윈도우A에 의해서 주사하고, 상기 복수의 원호형상(4) (5) (6)의 위치를 검출하고, 이들 복수의 원호형상(4) (5) (6)의 위치의 상대위치관계로부터 대상물을 동정하여, 위치·방향을 인식하는 것을 특징으로 하는 것이다.BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a position recognition method for use in automation of an assembly process of a factory, etc., and has a high versatility and a position recognition method that can recognize a simple, quick and accurate position and orientation even when an object is rotated. For the purpose of providing the present invention, in the configuration, an image having a plurality of arc-shaped shapes (4) (5) and (6) in the outline is picked up by the image pickup means, and the picked-up image information is changed to the shaded image data. The shaded image 2 is stored in the storage means, and the scan circular contour 15 and the scan circular contour 15 having the same diameter as the arc shapes 4, 5 and 6 on the shaded image 2 are provided. Scanned by circular contour window A consisting of a plurality of concentration-correlation lines 16 orthogonal to and measuring the image density of the scanning circular contour 15, wherein the plurality of circular arc shapes (4) (5) ( 6) the position of the plurality of arcs (4) (5) (6) The object is identified from the relative positional relationship of the position, and the position and the direction are recognized.

Description

Location Recognition Method

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제1도는 본 발명의 위치인식방법의 대상물과 그 화상을 표시한 도면,1 is a view showing an object of the position recognition method of the present invention and an image thereof;

제2도는 본 발명의 위치인식방법을 사용하는 위치인식장치의 블록도,2 is a block diagram of a position recognition device using the position recognition method of the present invention;

제3도는 본 발명의 위치인식방법의 제1실시예의 동작을 표시한 순서도,3 is a flowchart showing the operation of the first embodiment of the position recognition method of the present invention;

제4도는 본 발명의 위치인식방법의 제1실시예의 동작을 표시한 도면.4 is a view showing the operation of the first embodiment of the position recognition method of the present invention.

Claims

Image capturing an object having an arc shape in at least a part of the outline by the image pickup means, converting the captured image information into the shaded image data and storing in the storage means, scanning the shaded image by the circular contour scanning window to scan the circular shape. And detecting the position of the object and recognizing the position of the object from the detected position of the arc shape.

The image pickup means captures an object having a plurality of arc shapes in the outline, converts the captured image information into shaded image data, stores it in the storage means, scans the shaded image with a circular contour scanning window, and scans the plurality of circular arcs. A position recognition method characterized by detecting the position of the shape, identifying the object from the relative positional relationship of the positions of the plurality of circular arcs, and recognizing the position and the direction.

A screw fastening hole or an open hole is used as an object, and the object is picked up by the image pickup means. The picked-up image information is converted into a shaded image data, stored in a storage means, and the shaded image is stored in a circular contour scanning window. And detecting the position of the arc shape of the long hole or the open hole by scanning, and recognizing the position of the object from the detected position of the arc shape.

With the long hole for screw tightening as an object, the object is picked up by the image pickup means, the picked-up image information is converted into the shaded image data, stored in the storage means, and the shaded image is scanned by the circular contour scanning aid window. The position recognition method of Claim 2 characterized by detecting the position of two circular arcs of a long hole, and recognizing the position and the direction of the said object from the detected center position of the said arc.

Using the long hole or the open hole and the lower hole of the upper screw fastening as an object, the object is picked up by the image pickup means, and the captured image information is changed to light image data and stored in the storage means. The circular contour scanning window is used to detect the position of the long hole or the open hole and the lower hole of the upper hole and the position of the upper hole and the position of the lower hole from the detected arc-shaped position. The position recognition method, characterized in that the determination of whether or not to tighten the screw from these.

The circular-shaped position detection by scanning a circular contour scanning window is a scanning circular shape of the same diameter as the said circular arc shape of a shaded image. Scan by a circular contour scanning window composed of a plurality of concentration-correlation lines orthogonal to the contour and the scanning circular contour, and measuring the image density in the scanning circular contour, and a predetermined number of each concentration-correlation line at each position during scanning. Calculates the absolute value of the difference between the sum of the measured inner concentrations of the inner concentration corre- lation lines consisting of the inner image concentration measurement points and the sum of the outer blue concentrations of the outer concentration correlated lines consisting of a predetermined number of outer image concentration measurement points, and the absolute value of the difference. The number of concentration-correlation lines larger than a predetermined concentration threshold is obtained, and the position of the circular contour scanning window in which the number becomes maximum with respect to the periphery is formed in the arc shape. Position recognition method characterized in that a detection device.

6. The position detection according to claim 1, 2, 3, 4 or 5, wherein the position detection of the arc shape by the scanning of the circular contour scanning window is carried out on the scanning circle contour having the same diameter as the arc shape on the shaded image and the scanning circle contour. Scanning by a circular contour scanning window composed of a total number of inner measurement concentrations of an inner concentration correlation line and a predetermined number of outer image concentration measurement points that are orthogonal and consist of a plurality of concentration correlation lines for measuring image concentrations inside and outside the scanning circular contour. Calculate the absolute value of the difference with the total outside concentration concentration value of the outside concentration correlation line consisting of a predetermined number of inside image concentration measurement points for each concentration correlation line at each position during scanning, and sum the absolute value of the absolute value of the difference of the entire concentration correlation line. Position recognition, characterized in that the position of the circular contour scanning window that is maximized with respect to the surroundings is detected as the arc-shaped position. Law.

The image pickup means captures an object having a circular shape in at least a part of the outline, converts the captured image information into the shaded image data, stores it in the storage means, and scans the outline of the same diameter as the circular shape on the shaded image. Scan by a circular contour scanning window composed of a plurality of concentration-correlation lines orthogonal to the scanning circular contour and measuring the image density inside and outside the scanning circular contour, and a predetermined number of inner sides of each concentration-correlated line at each position during scanning. The absolute value of the difference between the total value of the inner measurement concentration of the inner concentration correlation line composed of the image concentration measurement points and the total of the outer measurement concentration of the outer conduction correlation line composed of the predetermined number of the outer image concentration measurement points is calculated. Calculating the number of concentration-correlation lines greater than a predetermined concentration threshold, the number of which is maximum with respect to The position of the contour scanning window is detected as the arc-shaped position, and the two end points of the scanning circular contour at which the continuous arrangement of the concentration correlation line in which the absolute value of the difference is greater than the predetermined concentration threshold are stopped are detected. Recognizing the opening direction of the arc-shaped from the position of the end point, the position recognition method characterized by recognizing the direction that the object is directed by the opening direction.

The method according to claim 8, wherein after recognizing the direction in which the object faces, the search range of the next position control point of the object is defined based on the direction in which the object faces, and the position of the next position control point is determined from the limited search range. And detecting the position and direction of the object from the position of the arc shape and the position of the next position control point.

The screwing long hole or the open hole is an object, and the object is imaged by the image pickup means, and the captured image information is changed into the shaded image data and stored in the storage means, which is the same as the arc shape above the shaded image. The shaded image is scanned by a circular contour scanning window composed of a scanning circular contour having a diameter and a plurality of concentration-correlation lines orthogonal to the scanning circular contour and measuring the image density inside and outside the scanning circular contour. The difference between the total inner measured concentration value of the inner concentration correlation line, which consists of a predetermined number of inner image concentration measurement points, and the outer measured concentration total value of the outer concentration correlation line, which consists of a predetermined number of outer image concentration measurement points, The absolute value is calculated, and the number of concentration-correlation lines whose absolute value of the difference is greater than the predetermined concentration threshold is calculated. The position of the circular contour scanning window that is maximized with respect to the periphery is detected as the arc-shaped position, and the direction of the long hole or the opening direction of the open hole is recognized from the distribution position of the concentration correlation line at this position. Position Recognition Method.

※ Note: The disclosure is based on the initial application.