The invention discloses a crop classification method based on time sequence NDVI and LST. The method comprises the following steps: 1) obtaining remote sensing image data containing a red light band,a near infrared band and a thermal infrared band, constructing a remote sensing image time sequence covering a crop growth period, and calculating to obtain an NDVI time sequence and an LST time sequence; (2) in order to enhance the difference between different crops, for each LST in step 1), firstly calculating LST mean vaue of LST, and then using the mean value to adjust (the formula is ALST(i,j)=LST(i,j)-LST mean, with i, j being the row number and column number of each pixel respectively, and finally supermisoing all the adjusted ALSTs in chronological order to form an ALST time series.; 3) obtaining crop sample data through a field survey or historical map, and 4) taking the NDVI time sequence, the ALST time sequence and the sample data as input, and classifying the crops in the research area by adopting a random forest classifier to form a crop classification result map.