Context awareness system in the use phase of a smart mobility platform: A vision system for a light-weight approach

Abstract

Due to the development of image processing over the last years, the application of vision systems and image recognition technologies has been increasingly applied in many fields. In this paper, Machine Learning and Principal Component Analysis are utilized for context awareness at a smart mobility platform. The restrictions concern a rather dynamic environment and a relevantly small dataset of images. The aim is to determine the position of the camera itself and the appearance of obstacles within a predefined area. To examine the performance of the proposed approach Hierarchical Cluster Analysis has been applied to group similar observations into clusters.