opticalflow
所属分类:Windows编程
开发工具:Visual C++
文件大小:14KB
下载次数:32
上传日期:2006-04-27 09:17:11
上 传 者:
笑看落花
说明: this program, opticalflow.c, is an implementation of Uras et al. 1988 s motion
(this program, opticalflow.c. is an implementation of Uras et al. 1,988 s motion)
文件列表:
opticalflow (0, 2006-04-27)
opticalflow\makeuras.txt (79, 2005-05-23)
opticalflow\uras.c (68510, 2005-05-23)
This README written by Steven Beauchemin
This program, uras.c, is an implementation of Uras et al. 1***8's motion
detection algorithm.
To compile:
make -f makeuras
Everything is in a single file so a make is really not necessary but...
This program uses a sequence of input images and smooths them according
to the sigma values provided by the user prior to the estimation of the optical
flow using a 2nd-order derivative technique. Derivatives are computed using
4-point central difference masks.
Examples of run files are also present. (You'll have to change the directory
names where the input and output are directed.) Here's a description of a
typical command line (that is exactly what one gets if one invokes the
program with no parameters):
Usage: uras input-path output-path seq-name. [-SG n.n] [-TG n.n] [-M n] [-R 1 | -R 2 n.n] [-B rows cols] [-F n.n] [-C corr-vel-file -T1 nbins1 increment1 -T2 nbins2 increment2]
[-SG n.n] : sigma value for spatial gaussian
default value is 3.0
[-TG n.n] : sigma value for temporal gaussian
default value is 1.5
[-M n] : middle frame of image sequence
default value is 0
[-R 1 | -R 2 n.n] : n = 1 : applies TR1 regularization
n = 2 : applies TR2 regularization
with sigma = n.n
[-B rows cols] : for binary input files without header
[-F n.n] : filters out unreliable estimates
using the Gaussian curv. (det(H))
[-C corr-vel-file -T1 nbins1 increment1 -T2 nbins2 increment2]
: error histogram
corr-vel-file : file of correct velocities
nbins1, nbins2 : number of bins for histogram
increnent1, increment2 : value of gap between bins
Here is a typical run:
uras /data/images1/BURKITT/testdata /data/images1/BURKITT/outdata treet. -SG 3.0 -TG 1.5 -M 9 -R 1 -F 0.5 -C correct_treet -T1 20 0.5 -T2 20 0.5
This command means: run uras using the input files from
/data/images1/BURKITT/testdata and put output files in
/data/images1/BURKITT/outdata
treet. is the stem name of a typical set of input images (for example,
the complete filename for frame 9 is "treet.9"). In the above example,
the program expects to find the input images in /data/images1/BURKITT/testdata.
-SG 3.0 indicates that the sigma value of the spatial smoothing of the image
sequence is 3.0
-TG 1.5 indicates that the sigma value of the temporal smoothing of the image
sequence is 1.5 (the program computes the required number of frames by itself,
see option -M)
-M 9 indicates that the flow field will be estimated for frame 9, the
program will automatically read in the required number of frames on both
sides of frame 9, according to the sigma value of temporal smoothing given
by -TG and the size of the derivative masks
-R 1 indicates that regularization procedure TR1 is used (see Uras et al.'s
paper). -R 2 n.n indicates that procedure TR2 is used (we did not use
it in our study). n.n is the sigma value of the spatial smoothing of the
computed flow field when using TR2
-C indicates the correct answer is available and that you want error analysis
conducted and that data is in /data/images1/BURKITT/testdata/correct_treet
(change this as well as appropriate). The data is analysed by producing 2
histograms.
-T1 and -T2 are mandatory when using -C. They specify the number of bins
the histogram will contain and the increment between them. The histograms are
constructed by considering the error of the estimates versus the confidence
measure det(H) and the condition number of the matrix H.
-F n.n allows the user to preserve the estimates that show det(H) >= n.n
only.
The program automatically generates the output filenames for the flow field
and the histogram (if an histogram is requested). For the above example,
the filename of the flow field would be:
uras.treet.F-sg3.0-tg1.5-m9-r1-f0.5
and the filename of the histogram:
uras.treet.H-sg3.0-tg1.5-m9-r1-f0.5
Note that the letters and numbers of the extension are the parameters
used when invoking the program.
The program takes between 0:30 and 4:00 minutes to run on an IBM 6000,
depending on the size of the images being processed. See the README for
information about the output format for flows and use software in ../SOFTWARE
to print out the flow fields in postscript.
近期下载者:
相关文件:
收藏者: