0
$\begingroup$

As I'm advancing in my project I realized I need better hardware, particularly for video input and processing.

From an intuitive feeling sounds like stereo cameras offers a more powerful and flexible solution, on the other hand the Kinect looks like a great out-of-the-box solution for depth sensing and it also takes away a lot of computational complexity as it output directly the depth.

So I would like to know what are the upsides and downsides of the 2 solutions and if they have any well known limitation and/or field of application and why.

Thank you

$\endgroup$

closed as primarily opinion-based by Mark Booth Jul 12 '15 at 12:07

Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Welcome to robotics Cesar, but I'm afraid that this kind of question isn't a good fit for a stack exchange site. We prefer practical, answerable questions based on actual problems that you face. Take a look at How to Ask and tour for more information on how stack exchange works, and try to rephrase your question in terms of the ultimate aim of the project, what you have tried so far and the problems you have had with those attempts to solve the problem. $\endgroup$ – Mark Booth Jul 12 '15 at 12:11
  • $\begingroup$ @MarkBooth Hello mark, thank you for welcoming me into the community. I'm asking it's a comparison of capabilities between 2 different technologies for depth sensing, however I understand your concern, can you point me out what part of the question could lead people into giving opinions more than facts ? I would like to edit it, Thank you $\endgroup$ – Cesar Jul 12 '15 at 14:11
  • $\begingroup$ The problem is, product comparisons are closed questions. They presuppose that the best solution to your problem can be found in one of the options proposed. Much better are open questions which invite solutions which are outside of what you have considered so far. $\endgroup$ – Mark Booth Jul 14 '15 at 17:06
  • $\begingroup$ @MarkBooth Mmm, I see what you mean, however I always had the feeling that an open question would lead even more into opinions, I mean something like What is the best solution for obtaining a depth map and video stream for an outdoor environment ? (with a reasonable limited budged) ... how would you phrase it ? $\endgroup$ – Cesar Jul 15 '15 at 10:41
  • $\begingroup$ Yes, asking for lists of possible solutions are also problematic, as are asking for subjective evaluations. Asking "How do I do X, within the constraints of Y budget and Z expertise? I have already tried V and W and had these problems with those approaches" is the best way to go about it. In this case you would hopefully get an number of possibilities which you can evaluate and chose between. The key is providing enough information that can help people address your specific situation, while also resulting in a answer which will also answer other peoples similar situations. $\endgroup$ – Mark Booth Jul 15 '15 at 11:01
2
$\begingroup$

Kinect: Pro:

  • cheap

  • already calibrated

  • active system (works also on textureless surfaces)

  • dense stereo

Con:

  • defined range (low maximal range)

  • does not work good outdoors in direct sunlight

Stereo:

Pro: - adjustable (different camera, different baseline possible for different ranges)

  • higher framerate possible

  • works outdoors

Cons:

  • hard to built right (cameras must not move at all)

  • higher computational load

  • no dense 3d (does rely on texture)

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.