 | 1 | initial version |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
| | 2 | Added images |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Update: Added images to provide greater clarity of the problem
Original image
Silhouette http://i.imgur.com/TX8Qwfw.jpg
Contours (from findContours()) http://i.imgur.com/CaR7Ve4.jpg
| | 3 | No.3 Revision |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Update: Added images to provide greater clarity of the problem
Contours (from findContours()) http://i.imgur.com/CaR7Ve4.jpg
Original image
Silhouette http://i.imgur.com/TX8Qwfw.jpg
Contours (from findContours()) http://i.imgur.com/CaR7Ve4.jpg
| | 4 | No.4 Revision |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Current settings; new BackgroundSubtractorMOG2(2, 40, true);// I've tried lower values, such as (1, 16, true) BSMOG2.apply(frameToExamine, fore, 0.5) // also tried 0.1 findContours(fore, contours, hierarchyMat, 1, 3) I also erode and dilate before findContours.
Update: Added images to provide greater clarity of the problem
Contours (from findContours())
http://i.imgur.com/CaR7Ve4.jpg
Original image
image
Silhouette
http://i.imgur.com/TX8Qwfw.jpgSilhouette
| | 5 | formatted text |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Current settings;
new BackgroundSubtractorMOG2(2, 40, true);// I've tried lower values, such as (1, 16, true)
true)
BSMOG2.apply(frameToExamine, fore, 0.5) // also tried 0.1
0.1
findContours(fore, contours, hierarchyMat, 1, 3)
3)
I also erode and dilate before findContours.
Update: Added images to provide greater clarity of the problem
Contours (from findContours())
Original image
Silhouette
| | 6 | retagged |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Current settings; new BackgroundSubtractorMOG2(2, 40, true);// I've tried lower values, such as (1, 16, true)
BSMOG2.apply(frameToExamine, fore, 0.5) // also tried 0.1
findContours(fore, contours, hierarchyMat, 1, 3)
I also erode and dilate before findContours.
Update: Added images to provide greater clarity of the problem
Contours (from findContours())
Original image
Silhouette
| | 7 | retagged |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Current settings; new BackgroundSubtractorMOG2(2, 40, true);// I've tried lower values, such as (1, 16, true)
BSMOG2.apply(frameToExamine, fore, 0.5) // also tried 0.1
findContours(fore, contours, hierarchyMat, 1, 3)
I also erode and dilate before findContours.
Update: Added images to provide greater clarity of the problem
Contours (from findContours())
Original image
Silhouette
| | 8 | No.8 Revision |
Is there a trick to setting fTau or nShadowDetection values in the Java version of BackgroundSubtractionMOG2? The default values are not giving good results (all too often the shadow gives much better contours in findContours() than does the person themselves).
Update: If there is no current means to access fTau or nShadowDetection via the Java binding, is it something I can add manually to the next version via pull request?
Current settings; new BackgroundSubtractorMOG2(2, 40, true);// I've tried lower values, such as (1, 16, true)
BSMOG2.apply(frameToExamine, fore, 0.5) // also tried 0.1
findContours(fore, contours, hierarchyMat, 1, 3)
I also erode and dilate before findContours.
Update: Added images to provide greater clarity of the problem
Contours (from findContours())
Original image
Silhouette
