Abstract:

Since 3D registration is easily affected by the environment and target tracking and detection algorithms are timeconsuming with low precision, we propose a tracking and registration method based on an improved kernerlized correlation filter (IKCF). The method includes four steps: (1) utilizing the regularized least squares classifier for sample training to obtain kernel correlation filter and position information; (2) searching scale kernel correlation filter and the maximum of position output to achieve the detection of the scale and position; (3) updating the model by referring to the MOSSE tracker; (4) adopting the oriented FAST and rotated BRIEF (ORB) to do feature extraction and matching, and then calculate the registration matrix. We utilize 6 sets of data in the Visual Tracker Benchmark datasets and video sequence to simulate. The results show that the IKCF generally outperforms the KCF, trackinglearningdetection (TLD), structured output tracking with kernel (Struck) and compressive tracking (CT) in precision, success rate and efficiency when rotation, scale variation, partial occlusion, illumination or motion blur occurs. Besides, the target position is highly aligned with OpenGL cube registration, and the augmented reality (AR) system based on IKCF is more realtime, stable and robust.

Key words: kernerlized correlation filter(KCF) tracking, IKCF algorithm, ORB algorithm, 3D registration, augmented reality