Subway tunnel foreign matter intrusion detection device and method based on machine vision

The invention discloses a subway tunnel foreign matter intrusion detection device and method based on machine vision, and the method comprises the steps: employing a high-definition camera installed on a subway tunnel inspection robot to carry out the shooting in a subway tunnel in a reciprocating manner, comparing a shot picture with a standard picture without a foreign matter, employing a digital image processing technology for detecting foreign matters, employing a classification algorithm based on an Adaboost algorithm for judging and classifying the foreign matters, and sending warning information to a train according to whether the foreign matters needing to be alarmed exist or not. According to the method, the foreign matters in the subway environment can be accurately extracted, the extracted suspicious areas can be accurately classified, the foreign matters needing to be alarmed can be screened out, and finally rapid and accurate alarm of foreign matter intrusion detection can be realized. 本发明公开了一种基于