| | |
Summary: Machine Vision and Applications (2000) 11: 267276 Machine Vision and
Applications
c Springer-Verlag 2000
MODEEP: a motion-based object detection
and pose estimation method for airborne FLIR sequences
Alexander Strehl, J.K. Aggarwal
Computer and Vision Research Center, The University of Texas at Austin, Department of Electrical and Computer Engineering, Austin, TX 78712-1084,
USA; e-mail: {strehl,aggarwaljk}@mail.utexas.edu
Abstract. In this paper, we present a method called MOD-
EEP (Motion-based Object DEtection and Estimation of
Pose) to detect independently moving objects (IMOs) in
forward-looking infrared (FLIR) image sequences taken from
an airborne, moving platform. Ego-motion effects are re-
moved through a robust multi-scale affine image registra-
tion process. Thereafter, areas with residual motion indicate
potential object activity. These areas are detected, refined
and selected using a Bayesian classifier. The resulting re-
gions are clustered into pairs such that each pair represents
one object's front and rear end. Using motion and scene
knowledge, we estimate object pose and establish a region
|
