部分重疊工件辨識:幾何形態比對

Locating Partially Occluded Parts from the Poses of Shape Primitives

廖嘉楷(Chia-Kai Liao)

指導教授 ： 蔡篤銘

元智大學/工程學院/工業工程與管理學系/碩士(1993年)

摘要

本研究利用機器視覺技術分辨部分重疊工件中各工件的類別和位置.本研
究中辨識的對象是二度平面工件,且工件的外形為直線和圓弧構成.本研究
的架構分為兩部分:形狀描述及形態比對.在形狀描述方面,先偵測工件邊
緣的頂角,再以最小平方法決定相鄰兩頂角間的幾何圖形是直線或圓弧.在
形態比對方面,利用霍氏轉換法的技術,以標準工件幾何圖形之單一特質和
二元關係為基礎建立參照表,將待測工件與參照表比對,求出欲辨識工件相
對於標準工件的位移和旋轉角度,並經由假設檢定提高辨識之精確度.找出
欲辨識工件在部分重疊工件中的位置後,利用灰度平均值,交熵和點數比值
三種指標判定重疊工件的上下關係,因此本研究的結果可應用於機器人自
動裝配作業.

關鍵字

機器視覺 ； 部分重疊 ； 形狀描述 ； 幾何形態比對 ； 霍氏轉換法

並列摘要

The problem of recognizing and locating partially occluded
parts is of considerable interest and challenge in the field of
industrial automation. While it is possible to employ carriers
or pallets to separate or prearrange the parts for easy
recognition, a vision system which can recognize the parts even
though they may be partially overlapped and in random positions
is much flexible. In this research, we consider the problem of
identifying and locating partially occluded industrial parts
lying on a flat surface, and the contours of the two-
dimensional parts are represented by linear and circular
segments. Phase I of this research has been concentrated on the
development of shape representation algorithms that extract
line and circular primitives of objects. Phase II of this
research concentrates on the shape matching algorithm using the
generalized Hough transform technique. Not only the proposed
algorithm evaluates the locations of parts but also determines
the top-down relation of two overlapped parts based on the
shade along the obstacled boundaries.

並列關鍵字

computer vision ； occluded parts ； shape matching