Real-Time Tracking of Moving Objects through Efficient Scale Space Adaptation and Normalized Correlation Filtering

Abstract

The field of real-time mobile object tracking is a crucial aspect of computer vision. Despite numerous algorithms proposed for efficient tracking, the high computational complexity presents challenges in achieving real-time performance. This paper presents a novel approach by introducing an adaptive search region proposal block that works in tandem with Mean Shift and Unscented Kalman Filter. The block efficiently searches the region of the estimated object location. The dynamic changes in the appearance and size of a moving target make tracking difficult, but the proposed Multi-scale Template Matching technique addresses this challenge by utilizing the Normalized Cross-Correlation method in the adaptive search region. This optimization results in a reduced computational complexity and an increased frame rate of 53.4 FPS. Additionally, the approach leads to a 50.3% decrease in error rate and improved precision and success rates of 76% and 79% respectively. Comparisons with various state-of-the-art trackers show that the proposed algorithm achieves the best results in terms of precision, success rate, and object tracking error.