The present invention belongs to the remote sensing classification technical field and relates to a vegetation index idea-based ground object information remote sensing extraction method. The method includes the following steps that: S1, a ground object target is selected, corresponding NEW-NDVI or NEW-RVI values are calculated; S2, parts in the NEW-NDVI or NEW-RVI values obtained in the step 1, which are larger than T, are extracted through applying a threshold segmentation technique, namely, a part of non-ground object information can be eliminated; and S3, set intersection operation in the mathematics is adopted to perform intersection on the obtained NEW-NDVI or NEW-RVI values, so that final target ground object information can be obtained. According to the vegetation index idea-based ground object information remote sensing extraction method of the invention, a target ground object feature information curve is made to be equivalent to a chlorophyll spectrum characteristic curve, so that target information can be extracted, and therefore, the method is stable in extraction precision, high in universality, high in automation degree, is suitable for various environments and can assist in avoiding the interference of man-made factors in an extraction process. Information extracted by using the method is accurate. The extraction method has simplicity and is of great significance for mastering ground object target spatial distribution information and promoting the application and development of remote sensing classification technologies.