Abstract-Pedestrians are the most vulnerable participants in urban traffic. The first step toward protecting pedestrians is to reliably detect them. We present a new approach for standing-and walking-pedestrian detection, in urban traffic conditions, using grayscale stereo cameras mounted on board a vehicle. Our system uses pattern matching and motion for pedestrian detection.

No abstract

Abstract-This paper deals with a pedestrian pre-crash sensor based on dense stereovision and motion analysis. We aim to provide means to deploy safety measures before a crash occurs. Depending on the concrete selected actuator, it could be interesting to know the type of object (e. g. vehicle, pedestrian, bicyclist, etc.) involved in the collision. Some actuators need the information about the collision partner type, because they have to be triggered only in specific situations, or in a situation dependent manner. We present a pedestrian detection system based on dense stereo and motion, acting as pre-crash sensor. In order to detect pedestrians, we use simple features such as object size, speed, and also more complex, motion based features. All these features are combined into a flexible, Bayesian framework.

No abstract

A preliminary step for many computer vision algorithms is the estimation of camera motion. In this paper we describe and compare the results of three algorithms for camera motion estimation, which require various degrees of knowledge about the camera(s) used and the scenario. The first algorithm uses a single uncalibrated camera and it is useful for applications such as content based image retrieval. This method provides only qualitative results. The second algorithm uses a single calibrated camera in order to obtain quantitative results. The third approach uses a calibrated stereo camera pair, together with a hardware stereo reconstruction system.