Title :
Learning motion trajectories via self-organization
Author :
Heikkonen, J. ; Koikkalainen, P. ; Schnörr, C.
Author_Institution :
Dept. of Inf. Technol., Lappeenranta Univ. of Technol., Finland
Abstract :
This paper proposes a general framework for learning motion representations from low-level spatiotemporal features. The concept is based on a self-organizing map (SOM). The authors show how the SOM can be used for predicting object movements, and how additional information of the environment can be related to the inherent model of the movement to obtain generalized motion representations for objects. Traffic scenes are used to test the performance of the system
Keywords :
self-organising feature maps; low-level spatiotemporal features; motion representations; object movements prediction; self-organizing map; traffic scenes; Buffer storage; Counting circuits; Extraterrestrial phenomena; Feature extraction; Image sequences; Information technology; Layout; Predictive models; Spatiotemporal phenomena; System testing;
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
DOI :
10.1109/ICPR.1994.577034
