File: visp_tracker/MovingEdgeSettings.msg
Raw Message Definition
# This message contains tracking parameters.
#
# These parameters determine how precise, how fast and how
# reliable will be the tracking.
#
# It should be tuned carefully and can be changed dynamically.
#
# For more details, see the ViSP documentation:
# http://www.irisa.fr/lagadic/visp/publication.html
# Moving edge parameters.
int64 mask_size # Mask size (in pixel) used to compute the image gradient
# and determine the object contour.
# A larger mask size is better for larger images.
# 3 pixels is enough for 640x480 images.
# Increasing this value makes the tracking slower.
#
# Caution: this value cannot be changed dynamically
# without resetting the tracking.
int64 n_mask # Number of masks applied to determine the object contour.
# Increasing this value makes the tracking slower.
int64 range # Maximum seek distance on both sides of the reference pixel.
# It should match the maximum distance in pixel between
# the current position of the feature projection and
# its next position.
# I.e. if the object moves fast and your tracking
# frequency is low, this value should be increased.
# Increasing this value makes the tracking slower.
float64 threshold # Value used to determine if a moving edge is valid
# or not.
float64 mu1 # Minimum image contrast allowed to detect a contour.
float64 mu2 # Maximum image contrast allowed to detect a contour.
int64 sample_step # Minimum distance in pixel between two
# discretization points.
# It avoids having too many discretization points when
# the tracked object is far away (and its projection
# in the image is small).
# Increasing this value makes the tracking *faster*.
int64 ntotal_sample # How many discretization points are used to track the
# feature.
# Higher is better but slow down the tracking.
# The best value depends on your model and its distance
# with respect to the camera.
# Increasing this value makes the tracking slower.
int64 strip # How many pixels are ignored around the borders.
float64 min_samplestep # Minimum allowed samplestep. Useful to specify
# a lower bound when the samplestep is changed
# dynamically.
# This is not done by visp_tracker currently.
float64 aberration # Ignored.
float64 init_aberration # Ignored.
# Tracker parameters.
float64 lambda # Gain used to compute the control law.
float64 first_threshold # What proportion of points should be valid to
# acccept an initial pose.
# Value should be between 0 et 1.
Compact Message Definition
int64 mask_size
int64 n_mask
int64 range
float64 threshold
float64 mu1
float64 mu2
int64 sample_step
int64 ntotal_sample
int64 strip
float64 min_samplestep
float64 aberration
float64 init_aberration
float64 lambda
float64 first_threshold