* CI: use ubuntu arm runners instead of QEMU
* removed focal deps docker image ci
* run tests in docker ci
* revert temporary test
* trigger ci jobs with modified files
* ldconfig
* arm64 ldconfig order
* No response filtering here: cv::goodFeaturesToTrack() already applies GFTT/QualityLevel, relative to the best corner's measure. Re-applying it as an absolute floor on KeyPoint::response double-filtered (~86% of keypoints ropped on OpenCV 4.5), and dropped *every* keypoint on OpenCV < 4.5, whose GFTTDetector leaves response at 0.
* fixing ExtractXYZCorrespondencesRANSAC ci error
* increased windows timeout (probably caused by gftt fix now extracting more features)
* Integrated OpenGV
* Fixed build without opengv
* Cmake: moved OpenGV dependency status under solvers group
* Added multi-stereocamera models support
* Fixed OpenGV 0 sample error when one of the camera doesn't have features. Fixed g2o BA id offset with multi-camera.
* Fixed multicam 3d points generated from stereo correspondences
* db: Fixed multi stereo models not loaded correctly
* gui: fixed stereo rectification option, RegVis: fixed projection error with old databases (image size not set in calibration)
* OdomF2M: Fixed map.at error when bundle adjustment is not used
* depthai: added imu firmware update option for convenience
* Fixed various refactor errors
* Moved "large number stereo correspondences rejected" warning outside computeCorrespondences function for multicam
* Added error log if ba correspondences are computed with empty signatures
* fixed compilation errors with latest opencv
Co-authored-by: mathieu86 <[email protected]>
matlabbe