apoorva/greenhouse
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added "NearestNeighbor/7ConvertBinToFloat" parameter: This will convert binary descriptors to float so that vocabulary approaches with KD-Tree or K-means can be used with binary descriptors like Brief/ORB/FREAK (use MANHATTAN_L1 too)

Browse Source
This commit is contained in:
matlabbe
2016-02-01 12:53:16 -05:00
parent 138d004169
commit 91bce9ac69
5 changed files with 187 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/find_object/Settings.h
+2
View File
@@ -234,6 +234,8 @@ class FINDOBJECT_EXP Settings
PARAMETER(NearestNeighbor, 4nndrRatio, float, 0.8f, "Nearest neighbor distance ratio.");
PARAMETER(NearestNeighbor, 5minDistanceUsed, bool, false, "Minimum distance with the nearest descriptor to accept a match.");
PARAMETER(NearestNeighbor, 6minDistance, float, 1.6f, "Minimum distance. You can look at top of this panel where minimum and maximum distances are shown to properly set this parameter depending of the descriptor used.");
PARAMETER(NearestNeighbor, 7ConvertBinToFloat, bool, false, "Convert binary descriptor to float before quantization, so you can use FLANN strategies with them.");
PARAMETER(NearestNeighbor, BruteForce_gpu, bool, false, "Brute force GPU");