Knowledge Commons of Institute of Automation,CAS
Fast Kernelized Correlation Filter without Boundary Effect | |
Ming TANG1,2; Linyu ZHENG1,2; Bin YU1,2; Jinqiao WANG1,2 | |
2021-01 | |
会议名称 | IEEE Winter Conference on Applications of Computer Vision |
会议日期 | 2021-1 |
会议地点 | Online |
摘要 | In recent years, correlation filter based trackers (CF trackers) have attracted much attention from the vision community because of their top performance in both localization accuracy and efficiency. The society of visual tracking, however, still needs to deal with the following difficulty on CF trackers: avoiding or eliminating the boundary effect completely, in the meantime, exploiting non-linear kernels and running efficiently. In this paper, we propose a fast kernelized correlation filter without boundary effect (nBEKCF) to solve this problem. To avoid the boundary effect thoroughly, a set of real and dense patches is sampled through the traditional sliding window and used as the training samples to train nBEKCF to fit a Gaussian response map. Non-linear kernels can be applied naturally in nBEKCF due to its different theoretical foundation from the existing CF trackers’. To achieve the fast training and detection, a set of cyclic bases is introduced to construct the filter. Two algorithms, ACSII and CCIM, are developed to significantly accelerate the calculation of kernel correlation matrices. ACSII and CCIM fully exploit the density of training samples and cyclic structure of bases, and totally run in space domain. The efficiency of CCIM exceeds that of the FFT counterpart re- markably in our task. Extensive experiments on six public datasets, OTB-2013, OTB-2015, NfS, VOT2018, GOT10k, and TrackingNet, show that compared to the CF trackers designed to relax the boundary effect, BACF and SRDCF, our nBEKCF achieves higher localization accuracy without tricks, in the meanwhile, runs at higher FPS. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44885 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.CASIA 2.NLPR |
第一作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ming TANG,Linyu ZHENG,Bin YU,et al. Fast Kernelized Correlation Filter without Boundary Effect[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Fast Kernelized Corr(1455KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论