This systematic literature review aims to investigate the current state-of-the-art in machine learning (ML) based road traffic analysis, hindrance estimation, and predicting vehicle safety measures for the Internet of Vehicles (IoV). Specifically, we focus on the verification of the scope and need of federated learning in this field. Federated learning is a decentralized ML technique that allows multiple edge devices to collaboratively train a shared model while keeping the data locally. We searched various academic databases and selected peer-reviewed publications related to the topic. The review highlights the existing challenges and limitations of the traditional centralized ML approaches and presents the advantages and potential benefits of federated learning in road traffic analysis and vehicle safety. Furthermore, we analyzed the current state-of-the-art research in federated learning for road traffic analysis and identified the research gaps and future research directions. The findings of this review demonstrate the scope and need of federated learning in the field of road traffic analysis and vehicle safety, as well as the potential of federated learning to overcome the limitations of the centralized ML approaches.