|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2020 Vol.21 No.10 P.1467-1484
Asymmetric discriminative correlation filters for visual tracking
Abstract: Discriminative correlation filters (DCF) are efficient in visual tracking and have advanced the field significantly. However, the symmetry of correlation (or convolution) operator results in computational problems and does harm to the generalized translation equivariance. The former problem has been approached in many ways, whereas the latter one has not been well recognized. In this paper, we analyze the problems with the symmetry of circular convolution and propose an asymmetric one, which as a generalization of the former has a weak generalized translation equivariance property. With this operator, we propose a tracker called the asymmetric discriminative correlation filter (ADCF), which is more sensitive to translations of targets. Its asymmetry allows the filter and the samples to have different sizes. This flexibility makes the computational complexity of ADCF more controllable in the sense that the number of filter parameters will not grow with the sample size. Moreover, the normal matrix of ADCF is a block matrix with each block being a two-level block Toeplitz matrix. With this well-structured normal matrix, we design an algorithm for multiplying an N×N two-level block Toeplitz matrix by a vector with time complexity O(NlogN) and space complexity O(N), instead of O(N2). Unlike DCF-based trackers, introducing spatial or temporal regularization does not increase the essential computational complexity of ADCF. Comparative experiments are performed on a synthetic dataset and four benchmarks, including OTB-2013, OTB-2015, VOT-2016, and Temple-Color, and the results show that our method achieves state-of-the-art visual tracking performance.
Key words: Visual tracking, Discriminative correlation filter (DCF), Asymmetric DCF (ADCF)
四川大学视觉合成图形图像技术国防重点学科实验室,中国成都市,610065
摘要:判别相关滤波器(DCF)是视频跟踪领域一种有效方法,显著推动了视频跟踪领域进展。然而,卷积算子的对称性会带来计算上的问题,并破坏广义的平移等变性。针对前一问题,人们提出许多解决方法,但对后一问题不够重视。本文分析循环卷积的对称性带来的问题,提出一种非对称卷积运算,且证明这种运算具有弱的广义平移等变性。利用提出的卷积运算,构造一个非对称判别相关滤波跟踪器(ADCF)。它对目标的平移更加敏感,且其非对称性允许滤波器和输入样本有不同空域大小,这使得ADCF的计算复杂性,从滤波器参数数量不随输入样本增大而增加的意义上说,更加可控。且ADCF对应的正规矩阵具有两级块Toeplitz矩阵结构,利用该结构可设计时间复杂度为O(NlogN)、空间复杂度为O(N)的矩阵-向量乘法。此外,有别于基于DCF的跟踪器,ADCF引进空域和时域正则化项,本质上不会增加计算复杂度。在4个公开基准数据集(OTB-2013,OTB-2015,VOT-2016和Temple-Color)和一个合成数据集上进行对比实验,结果表明所提方法取得最优视频跟踪性能。
关键词组:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.1900507
CLC number:
TP391
Download Full Text:
Downloaded:
2946
Download summary:
<Click Here>Downloaded:
1553Clicked:
5774
Cited:
0
On-line Access:
2024-08-27
Received:
2023-10-17
Revision Accepted:
2024-05-08
Crosschecked:
2020-09-02