Stereo matching algorithm plays an important role in binocular vision. Census stereo matching algorithm based on nonparametric transformation has been widely used in recent years, but there are some shortcomings in the process of disparity calculation. In view of the shortcomings of census stereo matching algorithm, there have been many improvements of census stereo matching algorithm. Firstly, the basic principle of disparity calculation based on census stereo matching algorithm is introduced, and the limitation of disparity calculation based on census stereo matching algorithm is analyzed. Then，the improved census stereo matching algorithm is summarized in the form of classification, and the improved census stereo matching algorithms are divided into six categories. Finally, the advantages, disadvantages and core ideas of each kind of improved census stereo matching algorithms are summarized, and six kinds of improved census stereo matching algorithms are compared and analyzed, and the application and development trend of census stereo matching algorithms are summarized.