As a basic parameter in the formation, transformation, and consumption of surface water resources, soil moisture has a very important influence on vegetation growth, agricultural production, and the healthy function of regional ecosystems. Monitoring of soil moisture by remote sensing plays a significant role in the dynamic characterization and management of surface heat balance, water evapotranspiration, and soil moisture in agricultural production. In order to verify the applicability of GF-1 data to the rapid acquisition of agricultural parameters in arid and semi-arid regions, this study simulated, compared, and validated the effectiveness of soil moisture inversion. All data were sampled from the vegetated area of the Aksu River basin in July 2016. GF-1 WFV images, Landsat8 OLI images, as well as measured soil moisture data were used to retrieve the perpendicular drought index (PDI), modified perpendicular drought index (MPDI), and vegetation adjusted perpendicular drought index (VAPDI). The results showed that, first, the determinant coefficients of correlation analyses of PDI, MPDI, VAPDI, and measured soil moisture in the 0-10, 10-20, and 20-30 cm depth layers based on GF-1 WFV images and Landsat8 OLI images, were good. In the 0-10 cm depth layer, the average determination coefficient was 0.68, all models met the accuracy requirements of soil moisture inversion. Inversion indices based on NIR-Red spectral space derived from optical remote sensing images were more sensitive to soil moisture information near the surface layer, but the accuracy of soil moisture retrieval for deeper layers was slightly lower in the study area. Second, in the area of moderate vegetation coverage, MPDI and VAPDI had higher inversion accuracy than PDI; to a certain extent, they overcame the influence of mixed pixels in soil moisture spectral information. In the area of high vegetation coverage, VAPDI modified by PVI was not susceptible to vegetation saturation, and thus had higher inversion accuracy. Third, the spatial heterogeneity of soil moisture retrieved by the remote sensing types was similar. However, GF-1 WFV images were more sensitive to changes in soil moisture, which reflected the actual soil moisture level covered by different vegetation. These results provide a practical reference for dynamic monitoring of surface soil moisture and large-scale water-saving irrigation projects in the arid and semi-arid regions, under the Belt & Road initiative.