Computer vision based object detection and recognition for vehicle driving

Abstract

Applying computer techndou to vehicle driving has been studied ,for many years. Most of the studies focused on autonomous vehicle driving in a simplified environment like freeways, or life independent systems like GPS. A general case where kind of unexpectedly fatal conditions may occur which we are driving in an urban area, however, has not been considered. In this papev, we proposed a system to satisjj the basic criteria for such a general in front of the vehicle we art! driving, and then classifi them into three predefined categories: pedestrians, vehicles, and others.In the proposed system, we exploit a simplified stereovision system to detect t,he obstacles instantly. Ajler that, to search and track pedestrians and vehicles, different methods are useL! .for adapting to their heterogeneity. For the sake of implementation, we also propose a method to decide the maximal speed of driving to keep such kind of systems working. driving assistance. We detect ihe obstacles on the ground

Human Localization via Multi-Cameras and Floor Sensors in Smart Home

“…In order to detect human in the environment, we apply robust background model [13] and human template matching techniques [14] on the image captured by each camera. The outputs of the cameras' video localization are the possible locations of the residents and our system directly use these outputs as the observations for later evaluation.…”