码迷,mamicode.com
首页 > 其他好文 > 详细

基于核化相关滤波器的跟踪-效果直逼Struck和TLD跟踪器

时间:2015-02-09 12:56:52      阅读:382      评论:0      收藏:0      [点我收藏+]

标签:struck tld   核化相关滤波器跟踪   

原文:http://cvlab.hanyang.ac.kr/tracker_benchmark_v10.html

作者ECCV2012的文章就被我关注过,速度惊人的快。2015年新作出来了。发文以供同行参阅。

Kernelized Correlation Filters

Jo?o F. Henriques, Rui Caseiro, Pedro Martins, Jorge Batista

ECCV 2012, TPAMI 2015


技术分享
Qualitative comparison of the proposed KCF tracker with other state-of-the-art trackers, TLD and Struck, on a benchmark of 50 videos. The proposed method is much faster and admits a considerably simpler implementation.


The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches.

Such sets of samples are riddled with redundancies — any overlapping pixels are constrained to be the same. Based on this simple observation, we propose an analytic model for datasets of thousands of translated patches.

By showing that the resulting data matrix is circulant, we can diagonalize it with the Discrete Fourier Transform, reducing both storage and computation by several orders of magnitude. Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers. For kernel regression, however, we derive a new Kernelized Correlation Filter (KCF), that unlike other kernel algorithms has the exact same complexity as its linear counterpart. Building on it, we also propose a fast multi-channel extension of linear correlation filters, via a linear kernel, which we call Dual Correlation Filter (DCF).

Both KCF and DCF outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite running at hundreds of frames-per-second, and being implemented in a few lines of code. To encourage further developments, our tracking framework was made open-source.


Video. You can view an example video on YouTube here. It is for the ECCV‘12 version of the tracker, which only supported a single channel. In the precision plot below, it corresponds to the "KCF on raw pixels" curve. The new version ("KCF/DCF on HOG") is significantly improved.

Source code. Below you can download the Matlab code (both the ECCV‘12 and the new version), the Python port byRodrigo Benenson, and the Java port by Peter Abeles (as part of theBoofCV library).


技术分享
Precision at different thresholds for 4 variants of the proposed method (in bold) on a 50 videos benchmark.


High-Speed Tracking with Kernelized Correlation Filters
J. F. Henriques, R. Caseiro, P. Martins, J. Batista
TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

技术分享Paper (PDF)
技术分享Preprint onarXiv (2014)
技术分享Code version 2 (Matlab)
技术分享Reference (Bibtex)

Exploiting the Circulant Structure of Tracking-by-detection with Kernels
J. F. Henriques, R. Caseiro, P. Martins, J. Batista
ECCV - European Conference on Computer Vision, 2012

技术分享Paper (PDF)
技术分享Code version 1 (Matlab)
技术分享Code (Python)
技术分享Code (Java /doc)
技术分享Poster (PDF)
技术分享Supplement (PDF)
技术分享More properties (PDF)
技术分享Reference (Bibtex)


基于核化相关滤波器的跟踪-效果直逼Struck和TLD跟踪器

标签:struck tld   核化相关滤波器跟踪   

原文地址:http://blog.csdn.net/huixingshao/article/details/43668181

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!