Object tracking is one of the fundamental problems in computer
vision and has received considerable attention in the past two
decades. The success of a tracking algorithm relies on two key
components: 1) an effective representation so that the object being
tracking can be distinguished from background and other objects, and
2) an update scheme of the object representation to accommodate
object appearance and structure changes. Despite the progress made
in the past, reliable and efficient tracking of objects with
changing appearance remains a challenging problem. In this paper, a
novel sparse, local feature based object representation - attributed
relational feature graph (ARFG) is proposed to solve this problem.
Each object is modelled using invariant features such as the scale
invariant feature transform (SIFT) and the geometric relations among
features are encoded in the form of a graph. A dynamic model is
developed to evolve the feature graph according to the appearance
and structure changes by adding new stable features as well as
deleting inactive features. Extensive experiment show that our
method can achieve reliable tracking even under significant
appearance changes, view point changes and occlusion.
Tracking videos
Tracking of rolling coffee pot. (Download)
Pedestrian tracking with appearance changes and heavy occlusion. (Download)
Vehicle tracking under heavy occlusion (Download)
Vehicle tracking with pose changes and appearance changes (Download)
Tracking of two mice. (Download)
.jpg)
Tracking of the PETS dataset. (Download)
.jpg)
Pedestrian tracking in the thermal images from OSU dataset. (Download)
