International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
e Calculate D,, »(k) pseudo-spectrums for various n, for ex-
ample, n = 2,4, 8,16 in each pixel of the image on frame
number k.
eo If signal exits in some pixels, then |D, 2(k)| in them will
be greater than zero. It can be or a signal from the object, or
some noise on the image sequence. To make an algorithm
more robust, we should filter the noise with some threshold.
This threshold can be found adaptively on each frame using
methods described above.
e Divide the whole accumulator image on many square parts
using grid. Assume each small square as moving if its value
is greater than threshold and not moving (background) oth-
erwise. Let us call these small image squares moving image
elements wi ...wm.
Moving object is created from moving image elements w1 .. . Wm.
Various moving elements exist for all values of n (or don't exist
if there's no moving objects on video sequence on current frame).
It's obvious that pseudospectrums with longer memory are more
robust to noise, but it takes longer to react for them, when a sig-
nal in some pixels starts being received. Pseudospectrums with
shorter memory react to a pixel signal much faster, but they react
to noise as well as to a real signal. So if an element is a moving
one, its signal should exist on most of faster pseudospectrums.
And if it is a new or disappeared object, its signal should ex-
ist on most of slower pseudospectrums. Let us suppose that we
have a set of moving objects A; ... As1 and set of new or dis-
appeared objects A1 ... A,» on a previous frame, set of moving
image elements wı ...wm1 and elements that concern to new or
disappeared objects w1 ...wm2 ON current frame. So we must
somehow associate all objects with their new regions. Let us see
hypotheses forming for moving objects:
e No object associates with the moving element. So this mov-
ing element belongs to a new object.
e No moving element associates with the object. This object
is treated as lost on this frame. Maybe it will be found in
future.
e Several moving elements are associated with the object. This
object is treated as found on this frame. New position is cal-
culated for it.
e Several objects are associated with one moving element.
This case is called a “collision”. It’s the most difficult case,
it should be treated very carefully. We have to use additional
algorithms to parse this conflict.
As a result, on each frame we have a number of moving objects
with their unique IDs and a number of new or disappeared objects
with their unique IDs too.
5 EXPERIMENTAL RESULTS
Described algorithms were tested using the private video bases
and public domain video bases like PETS (PETS video database,
n.d.), ETISEO (ETISEO video database, n.d.). Typical screen-
shot of object tracking visualization is presented on Figure 4.
We created an algorithm analyzing and testing block that is based
on comparison of automatic object detection and tracking results
with results of manual object marking. Performance is measured
562
in FPS (frames per second processed). Detection probability is
estimated in terms of “precision” and “recall”.
The “Precision” is a percentage ratio of real (human-marked) ob-
jects traced by the algorithm to all number of objects traced by
algorithm. Simply put, 100% minus precision is a percentage of
outliers provided by algorithm. The “Recall” equals is a percent-
age ratio of human-marked objects found by the algorithm to all
number of human-marked objects in a sequence, i.e. 100% minus
recall means percentage of real objects that were not found by the
algorithm somehow.
The table 1 contains some video sequences from PETS and ETISEO
databases and corresponding processing results. FPS was espe-
cially estimated for budget PC configuration: Intel Atom N270
1600 MHz processor and 1 Gb of RAM memory.
6 CONCLUSION
The problem of automatic video analysis for object detection and
tracking is the most significant algorithmic topic in the digital
video surveillance. The new motion analysis and object tracking
technique is presented. Motion analysis algorithms are based on
forming and processing of multiple-regression pseudospectrums.
The object detection and tracking scheme contains: detection of
moving pixel groups based on pseudospectrum analysis; forming
of object hypotheses and interframe object tracking; spatiotem- Ee
poral filtration of object motion parameters. Results of testing on
public domain PETS and ETISEO video test beds are outlined.
REFERENCES
Anandan, P., 1989. A computational framework and an algorithm
for the measurement of visual motion. Int. J. Comp. Vision 2,
pp. 283-310.
Barron, J., Fleet, D. and Beauchemin, S., 1994. Performance of
optical flow techniques. Internat. Jour. of Computer Vision 12(1),
pp. 43-77.
Box, G., Jenkins, G. M. and Reinsel, G., 1994. Time series anal-
ysis: Forecasting and control (3rd edition).
ETISEO video database, n.d. http://www-
sop.inria.fr/orion/ETISEO/.
Gabor, D., 1946. Theory of communication. Journal of the Insti-
tute of Electrical Engineers 93, pp. 429-457.
Heeger, D. J., 1988. Optical flow using spatiotemporal filters. Int.
J. Comp. Vision 1, pp. 279-302.
Horn, B. K. P. and Schunck, B. G., 1981. Determining optical
flow. Artificial Intelligence 17, pp. 185-203.
Nagel, H., 1983. Displacement vectors derived from second-
order intensity variations in image sequences. CGIP 9, pp. 85-
117.
PETS video database, n.d. http://www.cvg.rdg.ac.uk/slides/pets.html.
Singh, A., 1992. Optic flow computation. a unified perspective. Figure 4
IEEE Computer Society Press pp. 168-177. and park
