Correlation Filter With Motion Detection for Robust Tracking of Shape-Deformed Targets

Abstract

Target tracking is an important area of research in computer vision where stable target's tracking has been well solved. But in real world, it is difficult to ensure that the camera or lens could be fixed and the target could maintain its shape in whole video sequence. And as a result, in these unstable cases, robust tracking algorithms have to deal with the problem of target shape-deforming. Once the scenes video sequence contains shape-deformed target, tracking become a real challenging problem. Most previous tracking algorithms based on craft features only used HOG or/and CN features. This paper proposed an algorithm named as Correlation Filtering with Motion Detection (CFMD). This algorithm takes into account the camera shake and target motion information of the video sequence. After removing the effects of lens shake and camera movement, this algorithm can predict the motion information of the target, thereby effectively improving the tracking accuracy and robustness. In CFMD, the target position is determined by the weighted outputs of motion detection and correlation filter tracker. We evaluated our CMFD algorithm on the OTB-100 and VOT-2018 dataset compared with other target tracking algorithms, including Kernel Correlation Filter (KCF), Scale Adaptive with Multiple Features tracker (SAMF), Discriminative Scale Space Tracker (DSST), and Sum of Template and Pixel-wise LEarners (Staple), Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking(STRCF), Multi-Cue Correlation Filters for Robust Visual Tracking(MCCT). The experimental results showed that our algorithm owns the property of robust tracking of shape-deformed targets in video sequences containing lens shaking or camera moving and it achieves the state-of-the-art precision and tracking effects. INDEX TERMS Robust target tracking, shape-deformed target, correlation filter, motion detection.

A robust target tracking algorithm based on spatial regularization and adaptive updating model

“…To solves the impact of scale variation on tracking performance, the adaptive scale variation correlation filter tracker (SAMF) [19] and scale judgment space tracker (DSST) [20] introduced scale estimation in KCF. SAMF [19] with 7thick scales is used in a translation filter to detect multi-scale image blocks and selects the translation position and target scale corresponding to the largest response value. DSST [20] simultaneously trains the translation filter and the scale filter, respectively using 35 fine scales.…”

Multi-Channel Feature Dimension Adaption for Correlation Tracking

“…V ISUAL tracking is one of the fundamental computer vision tasks that has received much attention [1]- [3]. It is a task aiming to continually detect a target in a video sequence only its initial position is given.…”

Research on Visual Tracking Algorithm Based on Peak Sidelobe Ratio

“…[29] proposed a multi-cue CPF for short visual tracker and combined the correlation filter and particle filter to prove the tracker's effectiveness. Yuan et al [30] matched current frames and previous frames and added a motion detection algorithm to correlation filter tracking. It has greatly advantage for fast motion scenes.…”