Abstract: Leaf area index (LAI) is one of the most important indictors for the crop growth and yield estimation. The LAI dynamics can also greatly contribute to the crops monitoring. The inversion of radiative transfer model has been commonly used for the LAI inversion from remote sensing images. However, the inversed value cannot be unique after inversion. Additionally, previous studies of LAI inversion have concentrated mainly on the individual crop species. The LAI values cannot be concurrently inverted from the multiple types of crops. Hence, it is necessary to estimate the LAIs of different crop species in the mixed agricultural landscapes. This study aims to inverse the LAIs of the maize and rice in fields. The PROSAIL (PROSPECT and Scattering by Arbitrary Inclined Leaves) model was utilized to construct the simulated dataset. The spectral signatures and biophysical characteristics of maize and rice were then collected under varying environmental conditions at different growing stages. The tasselled cap-vegetation isoline pattern was obtained for the different type of crops. A look-up table (LUT) was developed to invert the LAI of maize and rice. The vegetation cover fraction (FVC) was taken as the prior knowledge. Another LUT without FVC was also developed to invert the LAI from the same GF-1 WFV images. Then, the LUT was applied into the multiple temporal images of maize and rice in fields. These images were captured by the Wide Field View (WFV) sensor onboard the Gaofen-1 (GF-1) satellite. The entire growing season of the maize and rice was selected to provide the continuous monitoring of LAI dynamics. The inversed LAIs were validated using ground-based measurements. The results showed that there was the significant correlation between the inversed LAI by the LUT-FVC and the ground measurements, with a coefficient of determination (R²) of 0.60 and a root mean square error (RMSE) of 0.75. The consistent trend was also found with the great variations in the measured LAIs during the whole growing season. By contrast, a R² of 0.47 and an RMSE of 0.85 for the inversed LAIs by the LUT without FVC, compared with the ground measurements. Specifically, the R² increased by 0.13, whereas, the RMSE decreased by 0.1. The high accuracy of the inversed LAIs was achieved in the LUT with the FVC. As such, the tasselled cap-vegetation isoline with the prior knowledge can be expected to effectively obtain the LAI information of multiple types of crops in fields. A challenge is also remained on the influence of different objects with the same spectrum on the inversion of LAIs. Especially, the various types of crops can lead to the spectral confusion and uncertainties during LAI estimation. Additional more prior knowledge can also be incorporated to fuse the multiple spectral indices with the spatial features of images during inversion. The applicability and accuracy of LAI estimation can also be achieved in the agricultural landscape with the various types of crops.