Car make and model recognition under limited lighting conditions at night

摘要: Car make and model recognition (CMMR) has become an important part of intelligent transport systems. Information provided by CMMR can be utilized when license plate numbers cannot identified or fake number plates are used. also used a certain vehicle is required to automatically cameras. The majority existing methods designed only in daytime most the car features easily seen. Few have been developed cope with limited lighting conditions at night where many detected. aim this work was identify using available rear view features. This paper presents one-class classifier ensemble particular interest from other models. combination salient geographical shape taillights extracted process. vote support vector machine, decision tree, k-nearest neighbors applied verify target classification experiments on 421 makes models captured under show accuracy rate about 93 %.