Tracking-Learning-Detection Adopted Unsupervised Learning Algorithm

In this paper, we research the real-time object tracking technology. The object tracking algorithm discussed in this paper is developed based on the Tracking-Learning-Detection(TLD) and the Centroid Neural Network(CNN). The object is unknown ahead of tracking, the model of the object is composed of objects transformed geometrically immediately after tracking. The TLD framework is useful for long-term object tracking in a video stream because the TLD framework applies a novel learning algorithm called P-N learning. We propose a method that applies the CNN algorithm to the TLD framework. The CNN algorithm is an unsupervised learning algorithm that provides a stable result, regardless of initial values of learning coefficients and neurons. The object tracking algorithm discussed in this paper has a higher accuracy than that of TLD in terms of detection. Additionally, it exhibits better processing performance than that of TLD.