scholarly journals Visual Tracking Based on an Improved Online Multiple Instance Learning Algorithm

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Li Jia Wang ◽  
Hua Zhang
Keyword(s):  
Visual Tracking ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Tracking Algorithm ◽  
Inner Product ◽  
Selection Strategy ◽  
Weak Classifier ◽  
Update Strategy ◽  
Appearance Changes

An improved online multiple instance learning (IMIL) for a visual tracking algorithm is proposed. In the IMIL algorithm, the importance of each instance contributing to a bag probability is with respect to their probabilities. A selection strategy based on an inner product is presented to choose weak classifier from a classifier pool, which avoids computing instance probabilities and bag probabilityMtimes. Furthermore, a feedback strategy is presented to update weak classifiers. In the feedback update strategy, different weights are assigned to the tracking result and template according to the maximum classifier score. Finally, the presented algorithm is compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed tracking algorithm runs in real-time and is robust to occlusion and appearance changes.

scholarly journals Visual Tracking Using Wang–Landau Reinforcement Sampler

2020 ◽  
Vol 10 (21) ◽  
pp. 7780
Author(s):  
Dokyeong Kwon ◽  
Junseok Kwon
Keyword(s):  
Visual Tracking ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Tracking System ◽  
Network Architectures ◽  
Tracking Accuracy ◽  
Algorithm Performance ◽  
Q Learning ◽  
Number Of Visits

In this study, we present a novel tracking system, in which the tracking accuracy can be considerably enhanced by state prediction. Accordingly, we present a new Q-learning-based reinforcement method, augmented by Wang–Landau sampling. In the proposed method, reinforcement learning is used to predict a target configuration for the subsequent frame, while Wang–Landau sampler balances the exploitation and exploration degrees of the prediction. Our method can adapt to control the randomness of policy, using statistics on the number of visits in a particular state. Thus, our method considerably enhances conventional Q-learning algorithm performance, which also enhances visual tracking performance. Numerical results demonstrate that our method substantially outperforms other state-of-the-art visual trackers and runs in realtime because our method contains no complicated deep neural network architectures.

scholarly journals Part-Based Visual Tracking via Online Weighted P-N Learning

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Heng Fan ◽  
Jinhai Xiang ◽  
Jun Xu ◽  
Honghong Liao
Keyword(s):  
Visual Tracking ◽  
State Of The Art ◽  
The State ◽  
Tracking Algorithm ◽  
Local Feature ◽  
Experimental Results ◽  
Learning Method ◽  
Target Model ◽  
Tracking Process

We propose a novel part-based tracking algorithm using online weighted P-N learning. An online weighted P-N learning method is implemented via considering the weight of samples during classification, which improves the performance of classifier. We apply weighted P-N learning to track a part-based target model instead of whole target. In doing so, object is segmented into fragments and parts of them are selected as local feature blocks (LFBs). Then, the weighted P-N learning is employed to train classifier for each local feature block (LFB). Each LFB is tracked through the corresponding classifier, respectively. According to the tracking results of LFBs, object can be then located. During tracking process, to solve the issues of occlusion or pose change, we use a substitute strategy to dynamically update the set of LFB, which makes our tracker robust. Experimental results demonstrate that the proposed method outperforms the state-of-the-art trackers.

Visual tracking algorithm based on improved Bhattacharyya coefficient and model update strategy

2015 ◽  
Vol 36 (1) ◽  
pp. 52-57
Author(s):  
Huang An-qi ◽  
◽  
Hou Zhi-qiang ◽  
Yu Wang-sheng ◽  
Liu Xiang
Keyword(s):  
Visual Tracking ◽  
Tracking Algorithm ◽  
Bhattacharyya Coefficient ◽  
Model Update ◽  
Update Strategy

scholarly journals Patch Based Multiple Instance Learning Algorithm for Object Tracking

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Zhenjie Wang ◽  
Lijia Wang ◽  
Hua Zhang
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Partial Occlusion ◽  
Learning Rates ◽  
Classification Score ◽  
Object Based ◽  
Illumination Changes

To deal with the problems of illumination changes or pose variations and serious partial occlusion, patch based multiple instance learning (P-MIL) algorithm is proposed. The algorithm divides an object into many blocks. Then, the online MIL algorithm is applied on each block for obtaining strong classifier. The algorithm takes account of both the average classification score and classification scores of all the blocks for detecting the object. In particular, compared with the whole object based MIL algorithm, the P-MIL algorithm detects the object according to the unoccluded patches when partial occlusion occurs. After detecting the object, the learning rates for updating weak classifiers’ parameters are adaptively tuned. The classifier updating strategy avoids overupdating and underupdating the parameters. Finally, the proposed method is compared with other state-of-the-art algorithms on several classical videos. The experiment results illustrate that the proposed method performs well especially in case of illumination changes or pose variations and partial occlusion. Moreover, the algorithm realizes real-time object tracking.

scholarly journals An Improved Kernelized Correlation Filter Based Visual Tracking Method

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Jianjun Ni ◽  
Xue Zhang ◽  
Pengfei Shi ◽  
Jinxiu Zhu
Keyword(s):  
Visual Tracking ◽  
Template Matching ◽  
Visual Target ◽  
State Of The Art ◽  
Correlation Filter ◽  
Matching Method ◽  
Tracking Method ◽  
Template Update ◽  
Update Strategy ◽  
Visual Target Tracking

Correlation filter based trackers have received great attention in the field of visual target tracking, which have shown impressive advantages in terms of accuracy, robustness, and speed. However, there are still some challenges that exist in the correlation filter based methods, such as target scale variation and occlusion. To deal with these problems, an improved kernelized correlation filter (KCF) tracker is proposed, by employing the GM(1,1) grey model, the interval template matching method, and multiblock scheme. In addition, a strict template update strategy is presented in the proposed method to accommodate the appearance change and avoid template corruption. Finally, some experiments are conducted. The proposed method is compared with the top state-of-the-art trackers, and all the tracking algorithms are evaluated on the object tracking benchmark. The experimental results demonstrate obvious improvements of the proposed KCF-based visual tracking method.

Enhanced MIL Visual Tracking via Distribution Fields Descriptor

2014 ◽  
Vol 571-572 ◽  
pp. 725-728
Author(s):  
Kang Sun ◽  
Nian Nian Sun
Keyword(s):  
Visual Tracking ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Experimental Results ◽  
Video Sequences ◽  
Object Model ◽  
Object Appearance ◽  
Distribution Field

This paper presents an enhanced multiple instance learning (MIL) tracker with a suitable representation of object appearance called distribution field descriptor (DF). To address transformations of object template (rotation, scaling), we firstly replace the smoothed histograms used in DF with smoothed bins according the theory of averaged shifted histograms. Secondly, due to the DF specificity and landscape smoothness, we adopt DF descriptor instead of traditional Haar-like one to represent the object appearance. By build object model using selected discriminative layers, our tracker is more robust while needing fewer features than the original tracker. The experimental results show higher performances of our tracker than those of five state-of-the-art ones on several challenging video sequences.

scholarly journals Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Suguo Zhu ◽  
Junping Du
Keyword(s):  
Particle Filter ◽  
Sparse Representation ◽  
Visual Tracking ◽  
Spatial Information ◽  
State Of The Art ◽  
Experimental Results ◽  
Selection Strategy ◽  
Illumination Change ◽  
Spatial Pooling ◽  
Hybrid Framework

Many modern visual tracking algorithms incorporate spatial pooling, max pooling, or average pooling, which is to achieve invariance to feature transformations and better robustness to occlusion, illumination change, and position variation. In this paper, max-average pooling method and Weight-selection strategy are proposed with a hybrid framework, which is combined with sparse representation and particle filter, to exploit the spatial information of an object and make good compromises to ensure the correctness of the results in this framework. Challenges can be well considered by the proposed algorithm. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm compared with the state-of-the-art methods on challenging sequences.

scholarly journals Drift-free tracking via the construction of an effective dictionary

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092965
Author(s):  
Li Zhao ◽  
Pengcheng Huang ◽  
Fei Liu ◽  
Hui Huang ◽  
Huiling Chen
Keyword(s):  
Sparse Representation ◽  
Visual Tracking ◽  
Tracking Algorithm ◽  
Linear Combinations ◽  
Computational Burden ◽  
Tracking Algorithms ◽  
Tracking Process ◽  
Appearance Changes

Template dictionary construction is an important issue in sparse representation (SP)-based tracking algorithms. In this article, a drift-free visual tracking algorithm is proposed via the construction of an effective template dictionary. The constructed dictionary is composed of three categories of atoms (templates): nonpolluted atoms, variational atoms, and noise atoms. Moreover, the linear combinations of nonpolluted atoms are also added to the dictionary for the diversity of atoms. All the atoms are selectively updated to capture appearance changes and alleviate the model drifting problem. A bidirectional tracking process is used and each process is optimized by two-step SP, which greatly reduces the computational burden. Compared with other related works, the constructed dictionary and tracking algorithm are both robust and efficient.

scholarly journals Robust Visual Tracking Using the Bidirectional Scale Estimation

2017 ◽  
Vol 2017 ◽  
pp. 1-10
Author(s):  
An Zhiyong ◽  
Guan Hao ◽  
Li Jinjiang
Keyword(s):  
Computer Vision ◽  
Object Tracking ◽  
Visual Tracking ◽  
Ridge Regression ◽  
State Of The Art ◽  
Benchmark Dataset ◽  
Tracking Algorithm ◽  
Conservative Strategy ◽  
Scale Estimation ◽  
Scale Variation

Object tracking with robust scale estimation is a challenging task in computer vision. This paper presents a novel tracking algorithm that learns the translation and scale filters with a complementary scheme. The translation filter is constructed using the ridge regression and multidimensional features. A robust scale filter is constructed by the bidirectional scale estimation, including the forward scale and backward scale. Firstly, we learn the scale filter using the forward tracking information. Then the forward scale and backward scale can be estimated using the respective scale filter. Secondly, a conservative strategy is adopted to compromise the forward and backward scales. Finally, the scale filter is updated based on the final scale estimation. It is effective to update scale filter since the stable scale estimation can improve the performance of scale filter. To reveal the effectiveness of our tracker, experiments are performed on 32 sequences with significant scale variation and on the benchmark dataset with 50 challenging videos. Our results show that the proposed tracker outperforms several state-of-the-art trackers in terms of robustness and accuracy.

scholarly journals Robust Visual Tracking with Discrimination Dictionary Learning

2018 ◽  
Vol 2018 ◽  
pp. 1-10
Author(s):  
Yuanyun Wang ◽  
Chengzhi Deng ◽  
Jun Wang ◽  
Wei Tian ◽  
Shengqian Wang
Keyword(s):  
Linear Combination ◽  
Visual Tracking ◽  
Dictionary Learning ◽  
State Of The Art ◽  
Tracking Algorithm ◽  
Robust Tracking ◽  
Tracking Algorithms ◽  
Stable Representation ◽  
Target Templates ◽  
Appearance Models

It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to represent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary atoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries can learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates. Additionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with l1 constraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art tracking algorithms.

Sign in / Sign up

Export Citation Format

Share Document