scholarly journals Scale Adaptive Kernelized Correlation Filter Tracker with Feature Fusion

2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Tongxue Zhou ◽  
Ming Zhu ◽  
Dongdong Zeng ◽  
Hang Yang
Keyword(s):  
Adaptive Learning ◽  
Feature Fusion ◽  
Color Naming ◽  
Correlation Filter ◽  
Appearance Model ◽  
Detection Mechanism ◽  
Extensive Evaluation ◽  
Complex Scenes ◽  
Precision Rate ◽  
Template Size

Visual tracking is one of the most important components in numerous applications of computer vision. Although correlation filter based trackers gained popularity due to their efficiency, there is a need to improve the overall tracking capability. In this paper, a tracking algorithm based on the kernelized correlation filter (KCF) is proposed. First, fused features including HOG, color-naming, and HSV are employed to boost the tracking performance. Second, to tackle the fixed template size, a scale adaptive scheme is proposed which strengthens the tracking precision. Third, an adaptive learning rate and an occlusion detection mechanism are presented to update the target appearance model in presence of occlusion problem. Extensive evaluation on the OTB-2013 dataset demonstrates that the proposed tracker outperforms the state-of-the-art trackers significantly. The results show that our tracker gets a 14.79% improvement in success rate and a 7.43% improvement in precision rate compared to the original KCF tracker, and our tracker is robust to illumination variations, scale variations, occlusion, and other complex scenes.

Anti-Occlusion Algorithm for Object Tracking Based on Multi-Feature Fusion

2014 ◽  
Vol 610 ◽  
pp. 393-400
Author(s):  
Jie Cao ◽  
Xuan Liang
Keyword(s):  
Object Tracking ◽  
Feature Fusion ◽  
Experimental Results ◽  
Occlusion Detection ◽  
Fusion Algorithm ◽  
Fusion Strategy ◽  
Complex Background ◽  
Complex Scenes

Complex background, especially when the object is similar to the background in color or the target gets blocked, can easily lead to tracking failure. Therefore, a fusion algorithm based on features confidence and similarity was proposed, it can adaptively adjust fusion strategy when occlusion occurs. And this confidence is used among occlusion detection, to overcome the problem of inaccurate occlusion determination when blocked by analogue. The experimental results show that the proposed algorithm is more robust in the case of the cover, but also has good performance under other complex scenes.

Correlation filter tracking based on adaptive learning rate and location refiner

2018 ◽  
Vol 26 (8) ◽  
pp. 2100-2111 ◽  
Author(s):  
刘教民 LIU Jiao-min ◽  
郭剑威 GUO Jian-wei ◽  
师 硕 SHI Shuo
Keyword(s):  
Adaptive Learning ◽  
Learning Rate ◽  
Correlation Filter ◽  
Adaptive Learning Rate

LSTM guided ensemble correlation filter tracking with appearance model pool

2020 ◽  
Vol 195 ◽  
pp. 102935
Author(s):  
Monika Jain ◽  
Subramanyam A.V. ◽  
Simon Denman ◽  
Sridha Sridharan ◽  
Clinton Fookes
Keyword(s):  
Correlation Filter ◽  
Appearance Model ◽  
Ensemble Correlation

Adaptive Image Feature Reduction for Object Tracking

2014 ◽  
Vol 989-994 ◽  
pp. 3605-3608
Author(s):  
Cong Lin ◽  
Chi Man Pun
Keyword(s):  
Object Tracking ◽  
Adaptive Learning ◽  
Computational Cost ◽  
Texture Feature ◽  
Feature Reduction ◽  
Image Feature ◽  
Distribution Model ◽  
Appearance Model ◽  
Art Object

A novel adaptive image feature reduction approach for object tracking using vectorized texture feature is proposed in this paper. Our contributions are three-fold: 1) a statistical discriminative appearance model using texture feature was proposed. 2) Majority of dimensions of the features are removed by judging their errors of the chosen distribution model. The remaining dimensions are most discriminative ones for classification task. The dimension reduction has advantages of reducing the computational cost in classification stage. 3) An adaptive learning rate was proposed to handle drifts caused by long term occlusion. Preliminary experimental results are satisfactory and compared to state-of-the-art object tracking methods.

scholarly journals Robust Object Tracking Algorithm for Autonomous Vehicles in Complex Scenes

2021 ◽  
Vol 13 (16) ◽  
pp. 3234
Author(s):  
Jingwei Cao ◽  
Chuanxue Song ◽  
Shixin Song ◽  
Feng Xiao ◽  
Xu Zhang ◽  
...  
Keyword(s):  
Object Tracking ◽  
Autonomous Vehicles ◽  
Feature Fusion ◽  
Environmental Perception ◽  
Tracking Algorithm ◽  
Tracking Performance ◽  
Tracking Accuracy ◽  
Complex Scenes ◽  
Driving Assistance ◽  
Public Datasets

Object tracking is an essential aspect of environmental perception technology for autonomous vehicles. The existing object tracking algorithms can only be applied well to simple scenes. When the scenes become complex, the algorithms have poor tracking performance and insufficient robustness, and the problems of tracking drift and object loss are prone to occur. Therefore, a robust object tracking algorithm for autonomous vehicles in complex scenes is proposed. Firstly, we study the Siam-FC network and related algorithms, and analyze the problems that need to be addressed in object tracking. Secondly, the construction of a double-template Siamese network model based on multi-feature fusion is described, as is the use of the improved MobileNet V2 as the feature extraction backbone network, and the attention mechanism and template online update mechanism are introduced. Finally, relevant experiments were carried out based on public datasets and actual driving videos, with the aim of fully testing the tracking performance of the proposed algorithm on different objects in a variety of complex scenes. The results showed that, compared with other algorithms, the proposed algorithm had high tracking accuracy and speed, demonstrated stronger robustness and anti-interference abilities, and could still accurately track the object in real time without the introduction of complex structures. This algorithm can be effectively applied in intelligent vehicle driving assistance, and it will help to promote the further development and improvement of computer vision technology in the field of environmental perception.

scholarly journals A Fast Object Tracker Based on Integrated Multiple Features and Dynamic Learning Rate

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Jianming Zhang ◽  
You Wu ◽  
Xiaokang Jin ◽  
Feng Li ◽  
Jin Wang
Keyword(s):  
Object Tracking ◽  
Large Scale ◽  
Model Updating ◽  
Color Naming ◽  
Learning Rate ◽  
Appearance Model ◽  
Dynamic Learning ◽  
Tracking Algorithms ◽  
Single Feature ◽  
Confidence Degree

Object tracking is a vital topic in computer vision. Although tracking algorithms have gained great development in recent years, its robustness and accuracy still need to be improved. In this paper, to overcome single feature with poor representation ability in a complex image sequence, we put forward a multifeature integration framework, including the gray features, Histogram of Gradient (HOG), color-naming (CN), and Illumination Invariant Features (IIF), which effectively improve the robustness of object tracking. In addition, we propose a model updating strategy and introduce a skewness to measure the confidence degree of tracking result. Unlike previous tracking algorithms, we judge the relationship of skewness values between two adjacent frames to decide the updating of target appearance model to use a dynamic learning rate. This way makes our tracker further improve the robustness of tracking and effectively prevents the target drifting caused by occlusion and deformation. Extensive experiments on large-scale benchmark containing 50 image sequences show that our tracker is better than most existing excellent trackers in tracking performance and can run at average speed over 43 fps.

scholarly journals Coupled-Region Visual Tracking Formulation Based on a Discriminative Correlation Filter Bank

Electronics ◽  
2018 ◽  
Vol 7 (10) ◽  
pp. 244 ◽  
Author(s):  
Jian Wei ◽  
Feng Liu
Keyword(s):  
Visual Tracking ◽  
Filter Bank ◽  
Correlation Filter ◽  
Appearance Model ◽  
Intrinsic Structure ◽  
Target Region ◽  
Global Target ◽  
Estimation Scheme ◽  
Discriminative Correlation Filter ◽  
Partially Occluded

The visual tracking algorithm based on discriminative correlation filter (DCF) has shown excellent performance in recent years, especially as the higher tracking speed meets the real-time requirement of object tracking. However, when the target is partially occluded, the traditional single discriminative correlation filter will not be able to effectively learn information reliability, resulting in tracker drift and even failure. To address this issue, this paper proposes a novel tracking-by-detection framework, which uses multiple discriminative correlation filters called discriminative correlation filter bank (DCFB), corresponding to different target sub-regions and global region patches to combine and optimize the final correlation output in the frequency domain. In tracking, the sub-region patches are zero-padded to the same size as the global target region, which can effectively avoid noise aliasing during correlation operation, thereby improving the robustness of the discriminative correlation filter. Considering that the sub-region target motion model is constrained by the global target region, adding the global region appearance model to our framework will completely preserve the intrinsic structure of the target, thus effectively utilizing the discriminative information of the visible sub-region to mitigate tracker drift when partial occlusion occurs. In addition, an adaptive scale estimation scheme is incorporated into our algorithm to make the tracker more robust against potential challenging attributes. The experimental results from the OTB-2015 and VOT-2015 datasets demonstrate that our method performs favorably compared with several state-of-the-art trackers.

Sign in / Sign up

Export Citation Format

Share Document