0
$\begingroup$

I'm a Mechatronics Student Engineer, and still new with the computer vision field and am now working on a project that needs to Tracks a small ball and need to determine it's (x,y,z). 1st) Kinect was bad for detecting small objects. 2nd) Stereo with 2 cameras not hardware synchronized isn't accurate. 3rd) Single Stereo Camera is very expensive and I don't have any information of how dealing with it.

So how Can I track a ball to return its coordinates(x,y,z) ?

$\endgroup$

closed as off-topic by Chuck Jul 25 '17 at 13:12

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "Questions must demonstrate an understanding of the problem to be solved, so they should include details of what you want to achieve, what you tried, what you saw, what you expected to see and what you don't understand. See How to Ask, tour, help center and the Robotics question checklist for advice on how to write a good question." – Chuck
If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Welcome to Robotics ZainKhaled, but I'm afraid that Unbounded Design Questions are off-topic because there are many ways to solve any given design problem. We prefer practical, answerable questions based on actual problems that you face, so questions which ask for a list of approaches or a subjective recommendation on a method (for how to build something, how to accomplish something, what something is capable of, etc.) are off-topic. Please take a look at How to Ask & tour for more information on how stack exchange works. $\endgroup$ – Chuck Jul 25 '17 at 13:05
  • $\begingroup$ Any method that gives you (x,y,z), that is also capable of resolving your object, should work, unless you have some other specifications - frame rate, measurement accuracy, etc. You could use RGB-D cameras, stereo vision, structured light (like the Kinect), etc. Regarding simple examples that [you] could modify to [your] case - Simple is a relative term; computer vision is a pretty advanced topic. However, please consider the OpenCV sample files; browse to cpp (C++) or Python and try to "stereo_match" example. $\endgroup$ – Chuck Jul 25 '17 at 13:12
  • $\begingroup$ Thanks guys I got it, sorry for any miss understanding, it was my 1st question on this site so I didn't know how to ask well. I'm now trying the kinect so if i get any good results i will inform others similar questions with what I get. $\endgroup$ – Zain Khaled Jul 25 '17 at 18:45
  • $\begingroup$ Sorry @ZainKhaled but this is still not a practical, answerable questions based on actual problems that you face, so I can't re-open it. It looks like you do have a couple of good questions you could ask instead however: "How to improve the accuracy of detecting small objects with Kinect" and "How to improve accuracy of stereo vision when cameras aren't synchronised". In each case you will need to include details of what you want to achieve, what you tried, what you saw & what you expected to see. $\endgroup$ – Mark Booth Jul 27 '17 at 8:38
0
$\begingroup$

I did this for my project usingb 2 webcams,to get x,y,z it is a very hard topic you need to be well informed in computer vision,even you get a stero vision camera you need to threads,so you wont be dealing with low fps ,since you are using computer vision in 2 camera frame,getting depth from stero vision is hard,also the accuracy in stereo vision is less than a kinect,and takes a big amount of time,i recommend you use kinenct or a 3d camera,and it is not the camera that is important the more important thing is your code and your method to track the ball,there are alot of method to track it ,in kinect or any other3d vision system getting x,y,z is easy since you know the depth,otherwise if you want to use normal or fast camera,if you are not well informed in computer vision ,i recommend you change the project

$\endgroup$
  • $\begingroup$ I liked the recommendation part :'D, but I really challenge my self with my team in this project. I was told that kinect is bad for detecting small objects, even I'm trying now to check, but if not do you have any information about how to deal with a stereo camera.? also could you share your idea or any files of your project with me ?! "Not the code and privet stuff" just any files you learned form :') thanks in advance. $\endgroup$ – Zain Khaled Jul 24 '17 at 19:00

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