Modelling pedestrian shapes for outlier detection: a neural net based approach
| Title | Modelling pedestrian shapes for outlier detection: a neural net based approach |
| Publication Type | Conference Papers |
| Year of Publication | 2003 |
| Authors | Nanda H, Benabdelkedar C, Davis LS |
| Conference Name | Intelligent Vehicles Symposium, 2003. Proceedings. IEEE |
| Date Published | 2003/06// |
| Keywords | (artificial, complex, Computer, computing;, custom, design;, detection;, engineering, intelligence);, layer, learning, method;, modelling;, net;, nets;, neural, object, outlier, pedestrian, pedestrians, rate;, recognition, recognition;, SHAPE, shapes;, traffic, two, vision; |
| 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. |
| DOI | 10.1109/IVS.2003.1212949 |