Adding OpenCV's GPU GFTT/ OpticalFlow and CudaSift support (#1330)

* Adding GFTT and SIFT Cuda support

* Working CudaSift

* Disable cudasift option when not available

* Added check to avoid re-allocating gpu memory everytime parseParameters is called. Added workaround of to detect/ignore invalid descriptors

* Added SIFT/PreciseUpscale and SIFT/Upscale parameters. Adjusted max octave to behave more like opencv

* Refactored how maximum features are thresholded, to be more similar to OpenCV version

* Updated loop closure benchmark scripts

* Cuda optical flow tmp commit

* Added Stereo/Gpu Vis/CorFlowGpu parameters (optical flow gpu integration for F2F odom and stereo correspondences)

* Fixed build without opencv cuda

* Fixed build with Opencv 4.10

* ZED: updated parameters to match zed sdk 4

* MRPT requires C++17

* updated max octave limit CudaSift
This commit is contained in:
matlabbe
2024-09-13 14:22:54 -07:00
committed by GitHub
parent f3ccfcb452
commit 69ac21f811
37 changed files with 2253 additions and 1375 deletions

View File

@@ -58,6 +58,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@FASTCV@#define RTABMAP_FASTCV
@OPENGV@#define RTABMAP_OPENGV
@PDAL@#define RTABMAP_PDAL
@CUDASIFT@#define RTABMAP_CUDASIFT
@LOAM@#define RTABMAP_LOAM
@FLOAM@#define RTABMAP_FLOAM
@DC1394@#define RTABMAP_DC1394