Particle Filter Supported with the Neural Network for Aircraft Tracking Based on Kernel and Active Contour

In this paper we presented a new method for tracking
flying targets in color video sequences based on contour and kernel.
The aim of this work is to overcome the problem of losing target in
changing light, large displacement, changing speed, and occlusion.
The proposed method is made in three steps, estimate the target
location by particle filter, segmentation target region using neural
network and find the exact contours by greedy snake algorithm. In
the proposed method we have used both region and contour
information to create target candidate model and this model is
dynamically updated during tracking. To avoid the accumulation of
errors when updating, target region given to a perceptron neural
network to separate the target from background. Then its output used
for exact calculation of size and center of the target. Also it is used as
the initial contour for the greedy snake algorithm to find the exact
target's edge. The proposed algorithm has been tested on a database
which contains a lot of challenges such as high speed and agility of
aircrafts, background clutter, occlusions, camera movement, and so
on. The experimental results show that the use of neural network
increases the accuracy of tracking and segmentation.

Authors:

• Mohammad Izadkhah
• Mojtaba Hoseini
• Alireza Khalili Tehrani

Keywords:

• Video tracking
• particle filter
• greedy snake
• neural network.

References:

[1] A. Yilmaz, O. Javed, and M. Shah, “Object tracking,” ACM Computing
Surveys, vol. 38, no. 4, p. 13–es, Dec. 2006.
[2] Q. Chen, Q. Sun, P. A. Heng, S. Member, and D. Xia, “Two-Stage
Object Tracking Method Based on Kernel and Active Contour,” Circuits
and Systems for Video Technology, vol. 20, no. 4, pp. 605–609, 2010.
[3] D. Comaniciu and V. Ramesh, “Kernel-Based Object Tracking,” Pattern
Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564–577, 2003.
[4] P.Maybeck, “Object tracking using affine structure for point
correspondences,” Computer vision and pattern recognition, 1997, pp.
704–709.
[5] M. Isard and A. Blake, “Condensation — Conditional Density
Propagation for Visual Tracking,” computer vision, vol. 29, no. 1, pp. 5–
28, 1998.
[6] A. S. Mian, “Realtime Visual Tracking of Aircrafts,” Digital Image
Computing: Techniques and Applications, pp. 351–356, 2008.
[7] D. terzopoulo. M.Kass, A.Witkin, “snakes active countour models,”
computer vision, pp. 321–331, 1988.
[8] A. Amini, S. Tehrani, and T. E. Weymouth, “using dynamic
programming for minimizing the energy of active contours in the
presence of hard constraints,” Pattern Analysis and Machine
Intelligence, pp. 855–867, 1988.
[9] M. S. J.Williams, “A fast algorithm for active contour (greedy snake),”
Image understanding, vol. 55, pp. 14–26, 1992.
[10] J. Denzler and H. Niemann, “Evaluating the performance of active
contour models for real time object tracking,” Asian Conference on
Computer Vision, vol. 2, no. Informatik 5, 1995.
[11] C. Xu, S. Member, J. L. Prince, and S. Member, “Snakes , Shapes , and
Gradient Vector Flow,” vol. 7, no. 3, pp. 359–369, 1998.
[12] S. Sabouri, A. Behrad, and H. Ghassemian, “Deformable Contour-Based
Maneuvering Flying Vehicle Tracking in Color Video Sequences,” ISRN
Machine Vision, vol. 2013, pp. 1–15, 2013.
[13] D. Cremers, F. T. Auser, and J. Weickert, “Diffusion Snakes :
Introducing Statistical Shape Knowledge into the Mumford-Shah
Functional,” computer vision, vol. 50, no. 3, pp. 295–313, 2002.
[14] A. Mian. Home page. http://www.csse.uwa.edu.au/ ajmal