Title: Motivation
1Motivation
Technion-Israel Institute of Technology
Hybrid Classification of Moving Targets
Michael Rudzsky Joint work with Ehud Rivlin, Uri
Bogomolov, Stas Lapchev and Gideon Dror
2Tracking
3Tracking
4Classification -people
walk
run
run45
5Shape is not enough for reliable
classification !
Solution- hybrid of appearance-based and
motion-based methods !
6Main Goals
- Detection of moving objects
- Tracking of detected targets
- Classification to one of predefined classes
- human,
- human group,
- animal,
- vehicle
-
E.Rivlin, M.Rudzsky, R.Goldenberg, U.Bogolmolov
and S.Lapchev.,ICPR'02 Y.Bogomolov, G.Dror,
S.Lapchev, E.Rivlin, M.Rudzsky. BMVC03
7 Classification
Flow chart
8Main Goals
- Detection of moving objects
- Tracking of detected targets
- Classification to one of predefined classes
- human,
- human group,
- animal,
- vehicle
-
E.Rivlin, M.Rudzsky, R.Goldenberg, U.Bogolmolov
and S.Lepchev.,ICPR'02 Y.Bogomolov, G.Dror,
S.Lapchev, E.Rivlin, M.Rudzsky. BMVC03
9 The classes handled by the system
10Motion Based Feature Extraction
Fitted ellipse
Star skeleton
11Combined classifier for all classes
12Targets Tracking Classification
13 Segmentation Tracking in Difficult
Conditions