This paper is based on naturalistic driving data that collected by Intelligent Vehicle Test and Evaluation Center of China Automotive Engineering Research Institute. In order to extract the typical scenario from naturalistic driving data, driver behavior characteristics need to be researched. For massive naturalistic driving data, a method of extraction of driving behaviors is needed. This paper focuses on automatic extraction lane changing behavior from naturalistic driving data. Analyzed the original methods and the data in our project, an algorithm which automatically extract lane change data is proposed based on distance between vehicle and lane markings. The results show that, our algorithm can well obtain lane change behaviors from straight roads in highway and urban road, and support research on typical traffic scenario in China.