作者: Houssam Salmane , Yassine Ruichek , Louahdi Khoudour
DOI: 10.1007/978-3-642-37807-2_12
关键词:
摘要: In this paper we present a video surveillance system for evaluating and detecting dangerous situations in level crossing environments. The is composed of the following main parts: robust algorithm able to detect separate moving objects perceived environment, Gaussian propagation model based dense optical flow tracking, Hidden Markov Model recognize trajectories detected objects, an uncertainty using theory evidence calculate danger allowing crossings. This method tested on real image sequences, results are discussed. work developed within framework PANsafer project, supported by ANR VTT program.