BIT: Bio-inspired tracker

Abstract— Visual tracking is a challenging problem due to various factors such as deformation, rotation and illumination. As is well known, given the superior tracking performance of human vision, bio-inspired model is expected to improve the computer visual tracking. However, the design of bio-inspired tracking framework is challenging, due to the incomplete comprehension and hyper-scale of senior neurons, which will influence the effectiveness and real-time performance of the tracker. According to the ventral stream in visual cortex, a novel bio-inspired tracker (BIT) is proposed, which simulates shallow neurons (S1 and C1) to extract low-level bio-inspired feature for target appearance and imitates senior learning mechanism (S2 and C2) to combine generative and discriminative model for position estimation. In addition, Fast Fourier Transform (FFT) is adopted for real-time learning and detection in this framework. On the recent benchmark, extensive experimental results show BIT performs favorably against state-of-the-art methods in terms of accuracy and robustness. Visual object tracking is one of the fundamental problems of computer vision, with wide-ranging applications including video surveillance, human-machine interfaces and robot perception. Although visual tracking has been investigated intensively in the past decade, it is still an enormous challenge in real application because of various factors such as pose, occlusion, scale and illumination. < final year projects >