Soft Mask Correlation Filter for Visual Object Tracking

Correlation filters have shown excellent performance in visual object tracking both in speed and accuracy. However, the traditional correlation filters learn from the shifted patches rather than real background patches, which may reduce the discrimination in challenging situations. In this paper, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Huo, Yang, Wang, Yuehuan, Yan, Xiaoyun, Dai, Kaiheng
Format: Conference Proceeding
Language:English
Subjects:
Agriculture
Benchmark testing
boundary effects
Correlation
correlation filter
Object tracking
soft mask
Target tracking
tracking
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Correlation filters have shown excellent performance in visual object tracking both in speed and accuracy. However, the traditional correlation filters learn from the shifted patches rather than real background patches, which may reduce the discrimination in challenging situations. In this paper, we propose a Soft Mask Correlation Filter (SMCF) which can effectively model the object by real image patches. The soft mask is conducted on the entire frame densely and crops real background patches for training. It enables the correlation filter to pay more attention to the center part of the object rather than an axis aligned rectangle which contains background pixels. Both quantitative and qualitative evaluations conducted on tracking benchmarks demonstrate the superior performance of our method compared to the state-of-the-art trackers.
ISSN:2381-8549
DOI:10.1109/ICIP.2018.8451607