Car tracking algorithms have recently found a major role in intelligent automotive applications. They are mainly based on the state estimation techniques to solve the maneuvering car tracking problems. The dynamic 2nd-order SVSF method is a novel robust state estimation method that is based on the variable structure control theory. It benefits from the accuracy, robustness, and chattering suppression properties of second-order sliding mode systems for robust state estimation. The main contribution of this paper is to present and implement a new tracking strategy that is a combination of the dynamic 2nd-order SVSF with the IMM filter. It benefits from the robust performance of the dynamic 2nd-order SVSF and the switching property of the IMM filter. This strategy is simulated and examined under several car driving patterns and experimental position data that are captured by a GPS device. The robustness and efficiency of this strategy is then compared with the Kalman filter-based counterparts.