Effective multi-object tracking is crucial for autonomous vehicles to navigate safely and efficiently in dynamic environments. Three challenges in implementation of multi object tracking in autonomous vehicles are: 1) In these vehicles, sensors like cameras are not static, which can cause motion blur in the frames and make tracking inefficient. 2) Traditional methods for motion compensation, such as those used in Kalman Filter-based Multi-Object Tracking, require extensive parameter tuning to match features between consecutive frames accurately. 3) Simple intersection over union (IoU) metric is insufficient for reliable identification in such environments. This paper explores new methodology for 2D multi-object tracking using cameras, introducing three primary modules in a Tracking-by-Detection (TBD) approach: 1) Real-time deblurring module mitigates motion blur, ensuring clearer frames for more accurate detection; 2) Deep learning based motion compensation dynamically adjusts to varying motion patterns, enhancing robustness; 3) Adaptive cost function for association using bounding boxes, incorporating factors such as object appearance and temporal consistency, improves upon traditional IoU metrics. While keeping it Simple Online and Realtime (SORT), we enhance detection by fine-tuning YOLOv8 on the KITTI dataset, tailored for autonomous driving scenarios. Our evaluations show that this methodology significantly outperforms previous state-of-the-art methods while maintaining the same inference rate as the baseline. These improvements increase the accuracy and reliability of multi-object tracking and reduce the computational overhead associated with parameter tuning and motion compensation, advancing robust, tracking systems for autonomous vehicles.