From a77a93a8e2bf33294ea2373e25ce136a7e042b68 Mon Sep 17 00:00:00 2001 From: Ilya Lysenkov Date: Wed, 11 Apr 2012 12:44:34 +0000 Subject: [PATCH] Minor doc fix. --- modules/video/doc/motion_analysis_and_object_tracking.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/video/doc/motion_analysis_and_object_tracking.rst b/modules/video/doc/motion_analysis_and_object_tracking.rst index 70ba2b9d6f..652955361d 100644 --- a/modules/video/doc/motion_analysis_and_object_tracking.rst +++ b/modules/video/doc/motion_analysis_and_object_tracking.rst @@ -37,7 +37,7 @@ Calculates an optical flow for a sparse feature set using the iterative Lucas-Ka * **OPTFLOW_USE_INITIAL_FLOW** Use initial estimations stored in ``nextPts`` . If the flag is not set, then ``prevPts`` is copied to ``nextPts`` and is considered as the initial estimate. - * **OPTFLOW_LK_GET_MIN_EIGENVALS** Use minimum eigen values as a error measure (see ``minEigThreshold`` description). If the flag is not set, then L1 norm between patches around the original and a moved point divided by number of pixels in a window is used as a error measure. + * **OPTFLOW_LK_GET_MIN_EIGENVALS** Use minimum eigen values as a error measure (see ``minEigThreshold`` description). If the flag is not set, then L1 distance between patches around the original and a moved point divided by number of pixels in a window is used as a error measure. :param minEigThreshold: The algorithm computes a minimum eigen value of a 2x2 normal matrix of optical flow equations (this matrix is called a spatial gradient matrix in [Bouguet00]_) divided by number of pixels in a window. If this value is less then ``minEigThreshold`` then a corresponding feature is filtered out and its flow is not computed. So it allows to remove bad points earlier and speed up the computation.