Title :
Modelling pedestrian shapes for outlier detection: a neural net based approach
Author :
Nanda, Harsh ; Benabdelkedar, Chiraz ; Davis, Larry
Author_Institution :
Dept. of Comput. Sci., Maryland Univ., College Park, MD, USA
Abstract :
In this paper we present an example-based approach to learn a given class of complex shapes, and recognize instances of that shape with outliers. The system consists of a two-layer custom-designed neural network. We apply this approach to the recognition of pedestrians carrying objects from a single camera. The system is able to capture and model an ample range of pedestrian shapes at varying poses and camera orientations, and achieves a 90% correct recognition rate.
Keywords :
computer vision; learning (artificial intelligence); neural nets; object recognition; traffic engineering computing; complex shapes; computer vision; learning method; neural net; outlier detection; pedestrian shape modelling; pedestrians recognition; recognition rate; two layer custom design; Biological system modeling; Cameras; Face detection; Humans; Legged locomotion; Neural networks; Shape; Support vector machine classification; Support vector machines; Videoconference;
Conference_Titel :
Intelligent Vehicles Symposium, 2003. Proceedings. IEEE
Print_ISBN :
0-7803-7848-2
DOI :
10.1109/IVS.2003.1212949
