I've been trying to refine my camera parameters with `CvLevMarq` but after reading about it, it seems to be causing mixed results - which is exactly what I am experiencing. I read about the alternatives and came upon `EIGEN` - and also found [this library][1] that utilizes it.
However, the library above seems to use a stitching class that doesn't support `OpenCV` and will probably require me to port it to `OpenCV`.
Before going ahead and doing so, which will probably not be an easy task, I figured I'd ask around first and see if anyone else had the same problem?
**I'm currently using:**
**1.** Calculating features with `SURFFeatureFinder`
**2.** Matching features with `BestOf2NearestMatcher`
**3.** `CameraParams` passed from a Quaternion (used in warping the images)
**4.** `estimateFocal` from the features found in (2), threshold = 0.80f
**5.** Bundle Adjustment (currently only `SpanningTree`, but used to use `cvLevMarq`, `calcError` & `calcJacobian`)
**6.** `ExposureCompensator` (GAIN)
**7.** OpenCV `MultiBand Blender`
**What works so far:**
- `SeamFinder` (I know... It's silly.. But, `SeamFinder` actually works to some extent. The only problem with `SeamFinder` is that its blending the colors around it (`DPSeamfinder COST_COLOR`) )
**Results so far:**
Without `SeamFinder`:
[![enter image description here][2]][2]
With `SeamFinder`:
[![enter image description here][3]][3]
[1]: https://github.com/ppwwyyxx/panorama/blob/master/src/stitch/incremental_bundle_adjuster.cc
[2]: http://i.stack.imgur.com/IMi7m.jpg
[3]: http://i.stack.imgur.com/5CNQD.jpg
↧