Aerial images are widely used in various remote sensing tasks and research to improve remote sensing in unmanned aerial vehicles (uav). Building and shadow detection is an important task for urban planning, disaster response, and environmental monitoring. Aerial imagery is a valuable source of data for building and shadow detection due to its high spatial resolution and ability to capture large areas. In recent years, machine learning-based methods have shown promising results in detecting buildings. In this review, we provide an overview of the state-of-the-art techniques for building and shadow detection using aerial imagery, with a focus on machine learning-based methods. We discussed the datasets for aerial imagery used for building shadow detection for different machine learning based methods and its applications. We also highlight the challenges and future directions in this field.