scholarly journals Object Tracking Based on Vector Convolutional Network and Discriminant Correlation Filters

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1818 ◽  
Author(s):  
Yuan Liu ◽  
Xiubao Sui ◽  
Xiaodong Kuang ◽  
Chengwei Liu ◽  
Guohua Gu ◽  
...  
Keyword(s):  
Object Tracking ◽  
Search Strategy ◽  
High Efficiency ◽  
Image Features ◽  
Correlation Filters ◽  
Convolutional Network ◽  
Speed Up ◽  
Online Tracking ◽  
Fast Motion ◽  
Coarse To Fine

Due to the fast speed and high efficiency, discriminant correlation filter (DCF) has drawn great attention in online object tracking recently. However, with the improvement of performance, the costs are the increase in parameters and the decline of speed. In this paper, we propose a novel visual tracking algorithm, namely VDCFNet, and combine DCF with a vector convolutional network (VCNN). We replace one traditional convolutional filter with two novel vector convolutional filters in the convolutional stage of our network. This enables our model with few memories (only 59 KB) trained offline to learn the generic image features. In the online tracking stage, we propose a coarse-to-fine search strategy to solve drift problems under fast motion. Besides, we update model selectively to speed up and increase robustness. The experiments on OTB benchmarks demonstrate that our proposed VDCFNet can achieve a competitive performance while running over real-time speed.

scholarly journals High-speed tracking based on multi-CF filters and attention mechanism

2019 ◽  
Author(s):  
Songyuan Fan ◽  
Rui Wang ◽  
Zhihao Wu ◽  
Seungmin Rho ◽  
Shaohui Liu ◽  
...  
Keyword(s):  
High Speed ◽  
Feature Maps ◽  
Correlation Filters ◽  
Convolutional Network ◽  
Speed Tracking ◽  
Training Samples ◽  
Long Time ◽  
Fast Motion ◽  
Evaluation Mechanism

Abstract Recently, correlation filters and deep convolutional network show good performance for visual tracking. Many real-time and high accuracy tracking algorithms are realized; however, there are still some challenges to build a robust tracker. In this paper, we present a novel tracking framework named multi-attention filter (MAF) to solve some challenges for tracking like object drift in a long time, lack of training samples and fast motion. Our framework consists of two components, a basic CNN network to extract feature maps and a set of classifiers to distinguish between the target and the background. First, to solve the problem of object drift in a long time, a simple but effective evaluation mechanism is proposed to the framework, the evaluation mechanism checks the tracking results and corrects it when needed. In addition, the results from different classifiers are fused to predict the object location according to intersection over union. Second, to overcome the lack of training samples, MAF stores some positive and negative samples in two queues, one named long-term queue and another named short-term queue. Third, to deal with fast motion of the target, attention mechanisms including channel attention and location attention are added to the tracker. In our experiments on the popular benchmarks including OTB-2013 and OTB-2015. MFA achieves state of the art among trackers, and as a correlation filter framework, MAF is very flexible and has great rooms for improvement and generalization.

scholarly journals Motion-Aware Correlation Filters for Online Visual Tracking

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3937 ◽  
Author(s):  
Yihong Zhang ◽  
Yijin Yang ◽  
Wuneng Zhou ◽  
Lifeng Shi ◽  
Demin Li
Keyword(s):  
Object Tracking ◽  
Visual Tracking ◽  
Model Updating ◽  
Visual Object ◽  
Adaptive Model ◽  
Correlation Filters ◽  
Current Frame ◽  
Visual Object Tracking ◽  
Fast Motion ◽  
Better Than

The discriminative correlation filters-based methods struggle deal with the problem of fast motion and heavy occlusion, the problem can severely degrade the performance of trackers, ultimately leading to tracking failures. In this paper, a novel Motion-Aware Correlation Filters (MACF) framework is proposed for online visual object tracking, where a motion-aware strategy based on joint instantaneous motion estimation Kalman filters is integrated into the Discriminative Correlation Filters (DCFs). The proposed motion-aware strategy is used to predict the possible region and scale of the target in the current frame by utilizing the previous estimated 3D motion information. Obviously, this strategy can prevent model drift caused by fast motion. On the base of the predicted region and scale, the MACF detects the position and scale of the target by using the DCFs-based method in the current frame. Furthermore, an adaptive model updating strategy is proposed to address the problem of corrupted models caused by occlusions, where the learning rate is determined by the confidence of the response map. The extensive experiments on popular Object Tracking Benchmark OTB-100, OTB-50 and unmanned aerial vehicles (UAV) video have demonstrated that the proposed MACF tracker performs better than most of the state-of-the-art trackers and achieves a high real-time performance. In addition, the proposed approach can be integrated easily and flexibly into other visual tracking algorithms.

Multi-Scale Anti-Occlusion Correlation Filters Object Tracking Method Based on Complementary Features

2020 ◽  
pp. 2155002
Author(s):  
Xiuhua Hu ◽  
Yuan Chen ◽  
Yan Hui ◽  
Yingyu Liang ◽  
Guiping Li ◽  
...  
Keyword(s):  
Object Tracking ◽  
Scale Model ◽  
Correlation Filters ◽  
Motion Feature ◽  
Tracking Method ◽  
Object State ◽  
Multi Scale ◽  
Tracking Process ◽  
Object Appearance ◽  
Response Peak

Aiming to tackle the problem of tracking drift easily caused by complex factors during the tracking process, this paper proposes an improved object tracking method under the framework of kernel correlation filter. To achieve discriminative information that is not sensitive to object appearance change, it combines dimensionality-reduced Histogram of Oriented Gradients features and Lab color features, which can be used to exploit the complementary characteristics robustly. Based on the idea of multi-resolution pyramid theory, a multi-scale model of the object is constructed, and the optimal scale for tracking the object is found according to the confidence maps’ response peaks of different sizes. For the case that tracking failure can easily occur when there exists inappropriate updating in the model, it detects occlusion based on whether the occlusion rate of the response peak corresponding to the best object state is less than a set threshold. At the same time, Kalman filter is used to record the motion feature information of the object before occlusion, and predict the state of the object disturbed by occlusion, which can achieve robust tracking of the object affected by occlusion influence. Experimental results show the effectiveness of the proposed method in handling various internal and external interferences under challenging environments.

scholarly journals Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters

2021 ◽  
Author(s):  
Tianyang Xu ◽  
Zhenhua Feng ◽  
Xiao-Jun Wu ◽  
Josef Kittler
Keyword(s):  
Object Tracking ◽  
Augmented Lagrangian Method ◽  
Channel Selection ◽  
Image Feature ◽  
Superior Performance ◽  
Appearance Model ◽  
Visual Object ◽  
Correlation Filters ◽  
Visual Object Tracking ◽  
Feature Representations

AbstractDiscriminative Correlation Filters (DCF) have been shown to achieve impressive performance in visual object tracking. However, existing DCF-based trackers rely heavily on learning regularised appearance models from invariant image feature representations. To further improve the performance of DCF in accuracy and provide a parsimonious model from the attribute perspective, we propose to gauge the relevance of multi-channel features for the purpose of channel selection. This is achieved by assessing the information conveyed by the features of each channel as a group, using an adaptive group elastic net inducing independent sparsity and temporal smoothness on the DCF solution. The robustness and stability of the learned appearance model are significantly enhanced by the proposed method as the process of channel selection performs implicit spatial regularisation. We use the augmented Lagrangian method to optimise the discriminative filters efficiently. The experimental results obtained on a number of well-known benchmarking datasets demonstrate the effectiveness and stability of the proposed method. A superior performance over the state-of-the-art trackers is achieved using less than $$10\%$$ 10 % deep feature channels.

Sign in / Sign up

Export Citation Format

Share Document