Timely and accurate agriculture information is vital for ensuring global food security. Satellite imagery has already been proved as a reliable tool for remote crop mapping. Planet satellite imagery provides high cadence, global satellite coverage with higher temporal and spatial resolution than the Landsat-8 and Sentinel-2. This study examined the potential of utilizing high-resolution multitemporal imagery along with and normalized difference vegetation index (NDVI) to map the agricultural crops in Prince Edward Island, Canada. Multitemporal Planet imagery at 3 m resolution combined with multitemporal NDVI data were used as inputs to Support Vector Machine (SVM) and Decision Tree (DT) algorithms. No significant difference in the overall accuracy was observed while using the multitemporal imagery alone as an input to SVM and DT. The accuracy of crops mapping by SVM and DT increased with the use of multitemporal NDVI data combined with Planet satellite multitemporal imagery. However, the SVM algorithm achieved a 6.25% higher overall accuracy and 7% higher kappa coefficient than DT when combined multitemporal Planet imagery with multitemporal NDVI data was used. The framework developed based on Planet imagery in this study is applicable for large-scale implementation across Canada and other regions of the world for accurate crop mapping.