Fast and sub-pixel precision target tracking algorithm for intelligent dual-resolution camera

Abstract

Listen

Translate article

The intelligent dual-resolution camera can provide large imaging field and high-resolution for the parts in which we are interested simultaneously. It has important applications in visual tracking. Though many trackers show great robustness on recent benchmarks, few of them make high precision and run in real-time, which is harmful to practical applications. In this paper, we propose a fast and sub-pixel precision tracker. It uses the time-shift property of Fourier transform to convert the displacement of target in space domain into the period of the response in Fourier domain. Then an improved Hough transform is introduced to measure this period, so that the displacement with sub-pixel precision can be calculated. Furthermore, a method obtaining benchmarks utilizing the intelligent dual-resolution camera is proposed to verify the high-precision of our tracker. Many experiments have been done to compare the proposed tracker with some state-of-the-art sub-pixel precision trackers, and the results have shown that the proposed tracker outperform the best tracker by 15.4% in average median distance precision, while feasible for real-time tracking with the speed faster than 80 fps. What’s more, the proposed tracker have been evaluated on the dual-resolution camera, the results show that it can make the observation of targets in the high-resolution image more complete.