To achieve safe and effective management of transportation networks a knowledge of the level of pedestrian activity is essential. This is however lacking or rudimentary at most existing signalised junctions. This paper describes results from a research program, funded by the EPSRC, to develop algorithms for the automatic visual sensing of pedestrian demand at pedestrian crossings. The measurement of pedestrian demand is achieved using small low-cost image sensors together with the automatic computer analysis of the sensed images. Such a pedestrian monitoring system will also find applications in a variety of related transportation areas including volumetric estimation of demand at bus stops and in metro systems. This paper begins with an introduction to the problem of pedestrian detection at PUFFIN (pedestrian user friendly intelligent) pedestrian crossings. It then goes on to describe the development of a new algorithm for pedestrian sensing which incorporates a model of observed pedestrian characteristics to improve detection performance. Finally results from the analysis of video recordings from initial site trials covering a range of flow and environmental conditions are presented.
Detection of pedestrians at Puffin crossings using computer vision
1996-01-01
6 pages
Aufsatz (Zeitschrift)
Englisch
pedestrian monitoring system , computer vision , transportation networks , image sensors , video recordings , pedestrian crossings , detection performance , PUFFIN crossings , automatic computer analysis , CCD image sensors , pedestrian activity , pedestrian demand , automatic visual sensing , pedestrian characteristics
The puffin pedestrian crossing
Tema Archiv | 1995
|Pedestrians behaviour at traffic-actuated crossings
Online Contents | 2002
|Toucan crossings for cyclists and pedestrians
TIBKAT | 1993
|Pedestrians' and cyclists' attitudes to Toucan crossings
TIBKAT | 1997
|Sight Distance for Disabled Pedestrians at Crossings
Transportation Research Record | 2013
|