1. Home
  2. General Robotics Forum
  3. 3D from Image/Video

3D from Image/Video

Dear Newsgroup-Members,

I want to extract 3D information from either two or more images or video. It is sufficient to have approximated 3D information thus I do not need a full 3D model, but the depth information is sufficient (e.g. like disparity maps).

I have implemented/tested several algorithms from epipolar geometry for uncalibrated stereo pictures but even with hand-marked points from both images the quality is horrible (at least for non-example images).

So, what is the current state of the art work (papers, demos, etc.) for extraction of depth information from a) multiple images and b) video? Are there any demos/source code out there to try?

I am looking forward to your suggestions, as I do not know how to continue at the moment.

Regards,

Reply to
Werner Müller
Loading thread data ...

This is a topic I keep meaning to experiment with... You might try SIFT or SURF for automated feature extraction and matching. Having more keypoints may improve the model quality. Also check whether SLAM techniques apply to your problem, especially for the video processing; openslam.org may be a good start.

Have you tried the EGT?

formatting link

- Daniel

Reply to
D Herring

Try the current issue of IEEE Trans. on Robotics and Automation, which is a survey of the current state of the art in SLAM.

John Nagle Animats

Reply to
John Nagle

Yes, I already tried EGT. At the moment I am working with SURFs but probably I could improve the SURF-point-matching between images. Btw: Thanks for the SLAM-link.

Reply to
Werner Müller

Demo yes. Try this one. In swedish but still very butiful.

formatting link
You have to check the checkbox which reads "I approve of the conditions".

According to my sources this was created by merging data from several images captured from a low-flying airplane. No laser scanners no nothing. Just cameras and GPS for tracking plane movements. Result, complete elevation data and texture for most things. Note that bridges may look a bit strange as the algorithm does not seem to handle holes under something.

Reply to
nobody

I don't know about Demo's or software but I have used an excellent piece of video survey software -

formatting link
Working between images you can measure any point in 3D space to any other point. Most points (depending on the proximity to camera and accuracy of click) can be measured with an accuracy of +/-5mm to +/-50mm we've only requires the nearest 500mm.

I don't think I've seen anything like it, fabulous tool.

regards, colin

Reply to
Colin Durrans

See the recent SLAM issue of IEEE Trans. on Robotics.

John Nagle

Reply to
John Nagle

PolyTech Forum website is not affiliated with any of the manufacturers or service providers discussed here. All logos and trade names are the property of their respective owners.