An Improved Pedestrian Detection Method for DSS (Driver Supporting System) using an Attitude Measurement Unit

This paper proposes an improved method for pedestrian detection using an Attitude Measurement Unit (AMU) in conjunction with multi-slit data. During the next decade, on-board pedestrian detection systems will play a key role in the challenge of increasing traffic safety. The main goal of these systems, to detect pedestrians in urban scenarios, involves overcoming difficulties like processing outdoor scenes from a mobile platform and searching for aspect-changing objects in cluttered environments. Using our new method, it becomes possible to decrease the margin of error of parameters by revising the image width. It is demonstrated that using an AMU as a means of on-road pedestrian detection for automobiles eliminates the need for finding specific configurations on the scene plane. Previously finding these configurations has been too time-consuming for practical use. Our results indicate that the integration of the proposed techniques will give rise to a more economical, accurate, and versatile system.