Forgot your password?
typodupeerror

Measure Anything with a Camera and Software 208

Posted by CmdrTaco
from the clever-ideas dept.
Kevin C. Tofel writes "Using a simple concept, iPhotoMEASURE software can measure any objects you can take a picture of. Include a printout of a 7.5- or 15-inch square in the photo and the software can measure any distance or object in the pic to within 99.5% accuracy. Although geared towards contractors, there's any number of consumer usage scenarios as well. Enough to justify a $99 price tag? Jury's still out on that."
This discussion has been archived. No new comments can be posted.

Measure Anything with a Camera and Software

Comments Filter:
  • Unfortunately... (Score:5, Insightful)

    by avalys (221114) on Wednesday February 07, 2007 @09:48AM (#17919934)
    I thought this was some kind of cool new perspective-based algorithm or something, but it turns out you have to be able to get close enough to the object to stick a label of known dimensions on it. The software justs compares the size of the label with the size of the object you're measuring. I'm not paying $99 for that.

    There are already a number of laser rangefinders with compasses built-in that can do the same thing using simple trig.

    • Re: (Score:3, Informative)

      by jbreckman (917963)

      It might have to do something trickier. If you look at their example:

      http://jkontherun.blogs.com/.shared/image.html?/ photos/uncategorized/iphotomeasure.jpg

      They measure objects that are two distances from the camera. (The garage, and the windows on the house which are a few feet forward). Since they are closer, they would appear to the camera as slightly larger, making the software inaccurate. So, either the software doesn't work, or it does do some trickery.

      • by Kadin2048 (468275) <slashdot.kadin@NOsPam.xoxy.net> on Wednesday February 07, 2007 @10:21AM (#17920284) Homepage Journal
        That link doesn't work (at least, not for me). I think it looks at the referer and won't let you deeplink to the image. You have to go through the blog to see it:
        http://jkontherun.blogs.com/jkontherun/2007/02/how _to_measure_.html [blogs.com]

        Looking at that photo, I'm not buying that it can measure all those distances from a single photo. I think there is some advertising hyperbole going on here. I get that you could measure all those distances and dimensions, using multiple photos -- one each of every flat surface, moving the target each time so it's the same distance from the camera as the surface being measured -- but I don't think it would work from a single photo.

        The only way you could measure everything from a single photo like that, would be if the camera was stereoscopic, or had some other form of depth perception. Otherwise, as you noticed, there's no way for it to know that the window that's closer to the camera is not really bigger than the garage door that's further away.
        • Re: (Score:2, Informative)

          by hobbes75 (245657)
          I agree. There is no way the software can figure out the measurements, unless their "DigiTarget" sheet is in the same plane as all the points between which distances need to be measured. It could in (science fiction like) theory use assumptions of orthogonal planes (walls to floor) to help but this is not a solved problem in AI and even then would not work in general.
          So the "hard" part in this software remains to automatically (hopefully it is automatic) find the DigiTarget and calculate a "more or less aff
        • Re: (Score:2, Informative)

          by ArtuRocks (956605)
          A comment [blogs.com] posted to that blog addresses that:

          Yes - it must take foreshortening into account. Briefly what it does is calibrate the camera's parameters (field-of-view for one) from the reference DigiTarget image which has known dimensions, and generates a perspective transformation from that. This should be a simple exercise in computer vision. Notice how it only measures horizontal and vertical lengths. This is because these have particularly special invariance properties under a perspective transfor
          • by ceoyoyo (59147)
            You could do that with the example of a rug, or any flat surface that's not perpendicular to your line of sight, by measuring the distortion of the reference square. BUT, you can't take into account things that do not lie on the same plane as that reference.

            If you have a flat wall with that target on it you can correct for perspective on the bottom and top of that wall, but you can't figure out the dimensions of another wall that's closer or farther from the camera.
        • by muellerr1 (868578)
          I believe you could measure distance without stereoscopy. I'm no mathematician (or even in the sciences--I'm humanities person myself), but the way I'd approach the problem is to check the slight curvature of the reference square's sides (put another way, check the angles on the reference square's corners) to infer the focal length and distance of reference square from the lens, and once you have that you'd be able to measure the amount of focus (or lack of focus) in otherwise hard edges to determine dista
          • Re: (Score:3, Insightful)

            by muellerr1 (868578)
            Here I am, replying to my own post after rtfa. Did anyone else click on the 'take a tour' link of the software and notice under the list of people who would find this software useful: Contractors, Interior designers, Law enforcement, Do-it-yourselfers and Single Moms. WTF? Why would single moms need to know distances in photographs any more than married moms?
            • Why would single moms need to know distances in photographs any more than married moms?
               
              For evaluating "Escort service" photos in preparation for that big night on the town, of course. *tee hee*
            • by drinkypoo (153816)

              WTF? Why would single moms need to know distances in photographs any more than married moms?

              You put the square on your street, then you take a picture when your ex is violating their restraining order.

            • by hackstraw (262471) *
              Why would single moms need to know distances in photographs any more than married moms?

              Married moms tell their husband to do the feat.

              I can't believe I replied to this, or that this was moderated up. These marketing lists of people that might find a product useful are rarely surveyed, quantified, or measured, but rather just a product of a brainstorming session.

              I guess this software won't make a great gift because the marketing people didn't tell me it would?!?!

        • by Mike1024 (184871)
          I get that you could measure all those distances and dimensions, using multiple photos -- one each of every flat surface, moving the target each time so it's the same distance from the camera as the surface being measured -- but I don't think it would work from a single photo.

          There is something known as 'depth from defocus [rma.ac.be]'. If you know the focal distance and depth of field, you can detect range by how out of focus things become. It sounds inaccurate, but some people report 1/200 [cmu.edu] accuracy. However, I gather
          • by ceoyoyo (59147)
            You also need certain circumstances like a small depth of field to give you enough defocus effect to measure. Small digicams, especially camera phones have tiny little sensors and use fairly small apertures so they produce images with very little focus variation with distance.
    • by iamhassi (659463)
      "The software justs compares the size of the label with the size of the object you're measuring. I'm not paying $99 for that."

      I thought $99 was a little steep to start with, but after seeing your post and reading the website and determining you're right, you have to run up to the object, stick the label on, then run back to where you were to snap the picture. That makes the software darn near worthless, for $99 they could probably make an entire camera with built-in rangefinder to figure out distance fr
    • by krayzkrok (889340)
      I would be very surprised if there wasn't a far more accurate and expensive way of doing this. I think what you're looking at here is simply a cheap solution for those who can't afford the high end software and hardware.

      For my PhD about 15 years ago (that long?!) I had a custom-built system to measure distances and dimensions (even speeds from one frame to the next) that employed the perspective differences between two cameras a set distance apart. Back in those days I had to develop each print separat
  • Good news (Score:3, Funny)

    by spellraiser (764337) on Wednesday February 07, 2007 @09:50AM (#17919956) Journal

    ... for all of us guys. The subject of how to measure with a with a tape measure has long been a controversial one, and thus the size debate has been marred by a lack of common consensus. This gadget will settle things once and for all!

  • Now where am I supposed to come up with a 7.5" square? I threw away my tape measure.
    • You hold your camera against a surface, draw two lines to indicate its length. Take the picture with those two lines in view, look up the dimensions of that particular camera to use a reference measurement.
    • by gstoddart (321705)

      Now where am I supposed to come up with a 7.5" square? I threw away my tape measure.

      Presumably you're a geek, and the summary indicates you can also use a 15" square.

      CDs are known to be 5.25", so 3 of them span 15 3/4". Find your own clever approximation for 3/4" (probably just smaller than a quarter). I bet with 10 minutes, some string, and a pencil most people around here could give you a good approximation of a 15" square from that.

      From there, some nice simple bisection of two angles to get you a 7.5"

  • This is rather cool. Is there anything like this in the OSS world? I would not be surprised if there is soon!
  • by popo (107611) on Wednesday February 07, 2007 @09:54AM (#17919992) Homepage
    Would be to project a laser 'shape' from the camera to compute distance, and keep the entire measurement operation localized within the camera.

    Just a thought.

    • by fbjon (692006)
      Cameras like that already exist.
    • This is what is done with the laser illuminators commonly seen in video from submarines and ROVs. The beams are parallel and a known distance apart so the size of objects they project onto can be estimated with ease.
  • just need to snap it again with the reference object in it. http://btc.montana.edu/ceres/html/Universe/images/ cobe.gif [montana.edu]
  • by physicsboy500 (645835) on Wednesday February 07, 2007 @09:59AM (#17920038)

    Honestly, I could see almost every contractor getting into this...

    I think people need to realize that this will be it's major market as surveying costs run in the $20~30/hour range for a single trained surveyor... this is skilled work. If companies can instead send out untrained (or barely trained) individuals at $10-$15/hr with much less time spent in calculation and only a $100 sunk cost into the software there is no reason they wouldn't choose this method. Very good news for contractors, bad for surveyors.

    The price is almost low enough for consumers with a need to calculate distances relatively regularly to purchase this software.

    • by davidsyes (765062)
      Hmmm. I think this will be HOT item in Canada... when they come to map the US homes, they will be fully equipped...
  • I doubt it (Score:4, Insightful)

    by oliverthered (187439) <oliverthered.hotmail@com> on Wednesday February 07, 2007 @09:59AM (#17920046) Journal
    If I take a picture of an arch with something in the background of the arch there's no way it's going to be able to measure both the foreground and background distances without any knowledge of the distance the objects are away from the camera etc...
    You'd have to stick known distance marks on everything in your picture.
  • Impossible (Score:2, Insightful)

    by Anonymous Coward
    You can not measure arbitrary dimensions in a single photograph using a single calibration target. If you stick the target onto a surface you can measure dimensions on that surface, i.e. parallel to the target, but you would have no information about locations not on the plane of the target. If you are not convinced just think of it this way - any point in an image can be at an arbitrary depth.

    This means two things, either you provide the software with more information or you need a calibration target for e
    • You are correct ... with one picture you don't have any depth information on any point other than where the known target is. It is not impossible if they take more than one picture from different perspectives though.

      However, nothing on the website indicates how many pictures you need to take for their software to work. I suspect it is not just as simple as taking one picture and being done with it. Digital photogrammetry generally takes a fair amount of post-processing.
  • by fermion (181285) on Wednesday February 07, 2007 @10:01AM (#17920060) Homepage Journal
    When asked why math helps, this is the the sort of situation I point to. What this software does is nothing more than apply similarity. Researchers have been doing this for years by placing a rule in every photo so that, no matter how the photo is resized, the dimensions are always knows. Measure the line, measure the feature, divide the two, and multiply by the length of the line. In any case, more sophisticated software is available for free, like tracker at sourceforge.

    But what really gets me is the claim in the advert, claims that hyperbolic if not outright lies. I can easily construct a photo in which a house appears to be the same dimensions of the squares. One more effective way to do what the software is proposing is to know the dimensions of a feature that is part of the object you wish to measure, and use similarity to approximate the dimensions of the smaller or larger object.

    • by fbjon (692006)

      I can easily construct a photo in which a house appears to be the same dimensions of the squares.
      No you can't. There's a sticker that you slap on a surface, which gives an absolute measure of size. On a small, but identical model house, the sticker would be huge.
  • by Anonymous Coward
    From now on any girl I meet online will be required to send me a picture with one of the squares in frame. No more "just a few extra pounds" for me.
    • Re: (Score:2, Funny)

      by antoinjapan (450229)
      She better hope she didn't photocopy the sticker up 200% first.
    • by Dare nMc (468959)
      most digital photos do have all the needed info their, the f-stop, the camera make/model/... so if you have the lense dimensions, and she is in focus, it should be possible to calculate all dimensions sans square.

      Now, calculating how stretched the elastic is holding everything back is going to be much more difficult.
  • Hang on, how can this thing possibly work?
    By putting the reference printout in the image you can determine the distance and orientation of the reference, but how does that tell you about the distance to other points in the image?
    It can only work for points in the same plane as the reference printout, such as the features on a flat wall.
    It cannot tell you anything about the dimensions of a complex object like a car.

    There are systems I've seen that can do similar jobs using video or multiple images to triangu
    • Not that I disagree entirely with your post (and I didn't RTFA), but what's stopping the software from using multiple target squares for different depths from the camera? The 'trickery' then would be to look for division lines. Then again, there isn't any accounting for stuff at an angle either. *shrug*. Useful for really quick rough estimates, I guess.
  • Seems like a piece of software that would only be useful in a few applications, but VERY useful in those applications.

    It's not going to be useful to someone who needs precise measurements, like a contractor. Those people will use a measuring tape, which is more than 99.5% accurate when used properly.

    But for estimators and appraisers this sounds like a killer app. Usually one would charge a lot more than $99 for such a niche application. Because of its niche status, there will not be as much competition f
  • Waste of money! (Score:5, Informative)

    by robkeeney (1061032) on Wednesday February 07, 2007 @10:10AM (#17920158)
    All it does is count pixels. Take the picture with the known size block in it, then count how many pixels the block takes up: that's your dots per inch -- for objects the same distance away as the known size image. I read somewhere that the Japanese (I think) used to do this at musical instrument trade shows, by wearing a 1 cm square tie tack and taking photos of each other holding instruments. They could get the dimensions of the instrument from the photos that way, and make great cheap knock-offs.
    • If what they're advertising is true, then it's more complicated than that. Pixel counting alone would only allow them to accurately calculate the length of line segments that are both the same distance from the camera and orthogonal to the camera's view axis. Even then, it would be hard to achieve 99.5% accuracy in many cases because the edges of the calibration block probably don't line up very well with pixel boundaries. So to provide a reasonable guarantee of accuracy on that plane alone requires the
    • I read somewhere that the Japanese (I think) used to do this at musical instrument trade shows, by wearing a 1 cm square tie tack and taking photos of each other holding instruments. They could get the dimensions of the instrument from the photos that way, and make great cheap knock-offs.

      I would have to consider at least some parts of this story to be apocryphal -- there's a lot more factors involved in making a good knock-off of a musical instrument than building at an exactly 1:1 scale.

      And honestly, if th
  • by TerranFury (726743) on Wednesday February 07, 2007 @10:20AM (#17920268)

    I was taking a mechanical design class, and I wanted to know the coordinates of a bunch of screwholes in a mounting plate. I looked at it for a second, grinned, and darted to the nearest computer with a scanner -- as my teammates shook their heads (and micrometers) at me, saying "damnit, you're being impractical; it'll never work." (They thought I was too interested in theory and not enough in turning the cranks on lathes and mills; though we generally got along, we did have -- philosophical differences.) Scanning took a few seconds, after which I took a minute to note the pixel coordinates of the hole centers in a spreadsheet. Then I measured one edge of the part with the micrometer to get a pixel-to-inch scale, popped that number into the spreadsheet, and out came the x,y coordinates of all the holes in the part. When we CNCed the new plate with those hole locations, they all lined up with the part-to-be-mounted perfectly -- at which point they were pretty much forced to admit that maybe the kid knew what the hell he was doing!

    I've thought since then that some software designed for the task (with edge-recognition algorithms, measurement features, etc) could turn consumer-grade scanners into decent reverse-engineering tools (for planar parts).

  • by asadodetira (664509) on Wednesday February 07, 2007 @11:12AM (#17920888) Homepage
    There are some subtleties in measuring things from an image. Lenses distort images in a non-linear way, so just counting the pixels wouldn't be extremely accurate. One of the ways this can be improved is by calibration, basically taking a picture of a bunch of dots in a square array that covers the whole field of view, and do some math. Hey iPhotomeasure people, if you need a consultant for version 2, "with improved calibration" give me a call!!
  • ARToolkit (Score:2, Interesting)

    by diodegod (70255)
    It may be possible to get ARToolkit [sourceforge.net] to do this. It's dual-licensed under the GPL so it's OSS. If you want to play with it just get a v4l video capture device and print out the squares.

    ARToolkit's been used by the University of South Australia to create ARQuake [unisa.edu.au] which is a lot of fun to use with the actual wearable computer :) Thanks Wayne Piekarski from UniSA for letting me play ARQuake on that thing at linux.conf.au in 2003.

    I'm not sure if they used ARToolkit or something more in-house to make Tinmith [tinmith.net],
  • Matrox Imaging has been offering a software product known as the Matrox Imaging Library (MIL) [matrox.com] for years which provides standard measurement functions and now even a metrology module that measures arcs, tolerances and more.

    Best of all, it supports Windows AND Linux!

  • I used to work for one of the biggest wallpaper producers, and they were going to buy a similar program where the user prints out a sheet with some kind of arrow on it, and put it on the wall. After that, the user would take a picture of his room, and load the jpg in the application. From there, the application would calculate the angle of the wall etc, and the user could load any texture (in our case, wallpaper) and it would apply it the the user's picture of his own room. It was pretty cool, but unfortuna
  • the ubiquitous "grey card" from Kodak was long used in the chemical-photo world as a standard measurement of both distances and color density. you KNEW you had an 8x10 element in the photo.
  • Needs stereo (Score:3, Informative)

    by mattr (78516) <mattr @ t e l e b o d y . com> on Wednesday February 07, 2007 @02:17PM (#17923556) Homepage Journal
    Unless more more than one photo is used with computer vision algorithms to actually build a perspective (two or more eye view) this thing is only going to produce approximate measurements.. not good enough for anything worth using it for.

    99.5% is also no good unless you don't really want to measure things accurately.

    The example shown in the link shows a garage that is farther from you than the windows, and the windows are not directly in line of sight but actually off to the side a little.

    I think it would really only be useful if you have a very high resolution digital camera and stand quite far from the building. But for closeup work you might as well have a ruler.

    It would be useful for things you can't reach though, if you can get directly in line with it.
  • Unless more more than one photo is used with computer vision algorithms to actually build a perspective (two or more eye view) this thing is only going to produce approximate measurements.. not good enough for anything worth using it for.

    99.5% is also no good unless you don't really want to measure things accurately.

    The example shown in the link shows a garage that is farther from you than the windows, and the windows are not directly in line of sight but actually off to the side a little.

    I think it would r

If a camel is a horse designed by a committee, then a consensus forecast is a camel's behind. -- Edgar R. Fiedler

Working...