Path: news.mathworks.com!newsfeed-00.mathworks.com!fu-berlin.de!feeder.erje.net!eu.feeder.erje.net!newsfeed.datemas.de!rt.uk.eu.org!aioe.org!.POSTED!not-for-mail
From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Re: Finding an item's position
Date: Tue, 11 Jun 2013 00:38:36 -0500
Organization: Aioe.org NNTP Server
Lines: 17
Message-ID: <kp6d4q$c8c$1@speranza.aioe.org>
References: <kp58cd$pm8$1@newscl01ah.mathworks.com>
NNTP-Posting-Host: B7RZOrfcknleFdbC4aYD+Q.user.speranza.aioe.org
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
X-Complaints-To: abuse@aioe.org
User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.2.28) Gecko/20120306 Thunderbird/3.1.20
X-Notice: Filtered by postfilter v. 0.8.2
Xref: news.mathworks.com comp.soft-sys.matlab:797017

On 6/10/2013 2:11 PM, Eric wrote:
> I need to find the position of an item within +- .005 inches. The item
> is a 2D, hollow square, about 7 inches on each side, about .5 inches
> thick with chamffered and filleted corners, and is black with white-ish
> background. I need to find both the position and rotation.
>
> So far, my thoughts are this: I can use two cameras, one on each of
> adjacent corners, to do edge detection. I'd be nice if I could get a set
> up that will allow me to have 1 pixel = .001 inches, but I'm not sure
> how to do this yet. For now, I'm just assuming it can be done and
> worrying about the software first.
>
...

Be easier if could put the camera above...

--