Real-time object recognition using data science and machine learning is a subject that is becoming more and more crucial in a variety of sectors, including security, robotics, and autonomous driving. Real-time object identification algorithms can be made more accurate and efficient by using statistics and probability. In this scoping paper, we give an overview of real-time object identification, machine learning for object recognition, and statistics and probability in data science. The effect of statistics and probability on data science and machine learning-based real-time object recognition is then covered. We give instances of statistical methods and probability models used in real-time object recognition and discuss how these methods and models affect object recognition's precision and efficacy across a range of sectors and use cases. Finally, we talk about the difficulties and potential directions for future study and development in this area. In order to fully grasp the significance of statistics and probability in real-time object recognition using data science and machine learning, as well as the implications for further study and development in this area, the scope of this paper aims to provide a thorough understanding.

Robotics, Statistics, Probability, Object Recognition;