ahmetozlu / augmented_reality Goto Github PK

Hi,

I've just found this repo and wanted to give some tips to improve your algorithm.

1. Don't do feature detection and matching on every frame. This is really slow, once you've found the target image you can just track the keypoints using sparse optical flow (calcOpticalFlowPyrLK) and compute camera pose (solvePnp) but only do feature detection again when you loose tracking on most of your keypoints.
2. If you use this approach you could separate detection and tracking in 2 threads, making the tracking able to recover fast if it starts loosing keypoints.

Here it is a sample repo I made for MarkerlessAR for iOS, it doesn't include separate threads but you can figure out how tracking works:

https://github.com/pawlusmall/MarkerlessAR

Your documentation and code is very clean and understandable for those wanting to learn how AR works, congratulations.

the register object's position is changing randomly even the camera and object keep static.Do you ever encountered this condition?

Hello

I have problem when I want to use that
. after run command cmake .
cmake created sln file and when I build project I have 6 unresolved externals

Hi! This can be portable for WebAR? i.e OpenCV.js or some way to transpile for web?

Thanks,
Pablo.

may i ask you What version of opencv do you use?when i run you code in oppencv3.4.0 i meet some problem such as :1、cv::Ptrcv::FeatureDetector detector = new cv::ORB(1000),2、cv::Ptrcv::DescriptorExtractor extractor = new cv::FREAK(false, false), it reminded me that Objects of abstract class type are not allowed