Angle spectrum for estimation of trajectory deviation using combined tracking and neural network labeling

Doulamis, N; Vescoukis, V; Georgopoulos, A

dc.contributor.author	Doulamis, N	en
dc.contributor.author	Vescoukis, V	en
dc.contributor.author	Georgopoulos, A	en
dc.date.accessioned	2014-03-01T02:45:07Z
dc.date.available	2014-03-01T02:45:07Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32160
dc.subject	Automatic neural-based labeling	en
dc.subject	Curve spectrum	en
dc.subject	Motion-based tracking	en
dc.subject.other	Classification scheme	en
dc.subject.other	Curve representations	en
dc.subject.other	Curve spectrum	en
dc.subject.other	Foreground objects	en
dc.subject.other	Foreground/background	en
dc.subject.other	Frame differencing	en
dc.subject.other	Fusion algorithms	en
dc.subject.other	Matching scheme	en
dc.subject.other	Morphological opening	en
dc.subject.other	Motion-based tracking	en
dc.subject.other	Moving objects	en
dc.subject.other	Moving regions	en
dc.subject.other	Neural network classifier	en
dc.subject.other	Neural network model	en
dc.subject.other	Non-linear	en
dc.subject.other	Nonlinear identifications	en
dc.subject.other	Polar coordinate	en
dc.subject.other	Rigid motions	en
dc.subject.other	Texture properties	en
dc.subject.other	Trajectory deviation	en
dc.subject.other	Vehicle trajectories	en
dc.subject.other	Image coding	en
dc.subject.other	Labeling	en
dc.subject.other	Management	en
dc.subject.other	Spectrum analysis	en
dc.subject.other	Technical presentations	en
dc.subject.other	Trajectories	en
dc.subject.other	Vehicles	en
dc.subject.other	Video streaming	en
dc.subject.other	Neural networks	en
dc.title	Angle spectrum for estimation of trajectory deviation using combined tracking and neural network labeling	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1463542.1463547	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1463542.1463547	en
heal.publicationDate	2008	en
heal.abstract	In this paper, we combine rigid motion-based tracking algorithms and non-linear identification methods for automatic detecting and tracking vehicles' trajectory in roadways. In addition, we introduce the concept of the angle spectrum for determining the deviation of a vehicle trajectory from the ideal trace, provided by surveyor engineers. Motion-based tracking is implemented through frame differencing and advanced non-linear convolution filters such as the morphological opening by reconstruction. However, motion based tracking suffers from noise, occlusions and the fact that the detected moving region may contains more than one foreground objects (e.g., a vehicle approach another vehicle). For this reason, a neural network-based classification scheme is adopted in this paper for identifying foreground/background objects. The neural network models the colour and texture properties of the detected moving objects. Fusion algorithm are then exploited which it combine the output of the neural network classifier and the output of the motion-based tracking for efficiently detecting the vehicles trajectory. In the following, we introduce the concept of the angle spectrum which estimates the deviation between two curves, i.e., the vehicle trajectory and the ideal trace. The angle spectrum is computed through quantization of the polar coordinate space, adopted for the curve representation along with novel matching schemes. Experimental results are presented, which indicate the performance of the proposed method in real file environments. Copyright 2008 ACM.	en
heal.journalName	MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops	en
dc.identifier.doi	10.1145/1463542.1463547	en
dc.identifier.spage	25	en
dc.identifier.epage	32	en