Object tracking is crucial for a wide range of computer vision applications, including autonomous navigation and surveillance systems. This paper introduces StrongSort, a novel object tracking algorithm designed to tackle the difficulties of achieving real-time accuracy in challenging environments. StrongSort leverages the capabilities of YOLOv8, a leading object detection model, to achieve this goal. The foundation of StrongSort lies in its integration with YOLOv8, which provides excellent object detection accuracy and speed. Leveraging YOLOv8's detection outputs, StrongSort utilizes a combination of object embeddings, motion prediction and a deep association mechanism to create a robust tracking framework. This enables StrongSort to handle occlusions, scale variations and abrupt object movements effectively. One of the key contributions of StrongSort is its ability to handle multiple object tracking making it suitable for multi-object tracking scenarios, such as autonomous vehicles navigating through urban environments or surveillance systems monitoring crowded areas. The algorithm employs a hierarchical approach that accurately associates detected objects across frames while maintaining low computational overhead. Experimental results show that StrongSort surpasses existing object tracking algorithms in key areas: accuracy, robustness, and speed. Furthermore, its efficiency enables real-time performance on standard hardware, making it a practical choice for a variety of applications.