scholarly journals Robust Probabilistic Discriminative Model Prediction Tracker via Improved Model Update Strategy

2021 ◽  
Author(s):  
Shaolong Chen ◽  
Changzhen Qiu ◽  
Yurong Huang ◽  
Zhiyong Zhang
Keyword(s):  
Model Prediction ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Robust Model ◽  
Model Update ◽  
Discriminative Model ◽  
Background Clutter ◽  
Improved Model ◽  
Update Strategy ◽  
The Impact

Abstract In the visual object tracking, the tracking algorithm based on discriminative model prediction have shown favorable performance in recent years. Probabilistic discriminative model prediction (PrDiMP) is a typical tracker based on discriminative model prediction. The PrDiMP evaluates tracking results through output of the tracker to guide online update of the model. However, the tracker output is not always reliable, especially in the case of fast motion, occlusion or background clutter. Simply using the output of the tracker to guide the model update can easily lead to drift. In this paper, we present a robust model update strategy which can effectively integrate maximum response, multi-peaks and detector cues to guide model update of PrDiMP. Furthermore, we have analyzed the impact of different model update strategies on the performance of PrDiMP. Extensive experiments and comparisons with state-of-the-art trackers on the four benchmarks of VOT2018, VOT2019, NFS and OTB100 have proved the effectiveness and advancement of our algorithm.

scholarly journals An adaptive eco with weighted feature for visual tracking

Filomat ◽  
2020 ◽  
Vol 34 (15) ◽  
pp. 5139-5148
Author(s):  
Yan Zhou ◽  
Hongwei Guo ◽  
Dongli Wang ◽  
Chunjiang Liao
Keyword(s):  
Fuzzy Model ◽  
Visual Object ◽  
Adaptive Mechanism ◽  
Feature Maps ◽  
Visual Object Tracking ◽  
Tracking Process ◽  
Model Update ◽  
Fitting In ◽  
Update Strategy ◽  
Self Adaptive

The efficient convolution operator (ECO) have manifested predominant results in visual object tracking. However, in the pursuit of performance improvement, the computational burden of the tracker becomes heavy, and the importance of different feature layers is not considered. In this paper, we propose a self-adaptive mechanism for regulating the training process in the first frame. To overcome the over-fitting in the tracking process, we adopt the fuzzy model update strategy. Moreover, we weight different feature maps to enhance the tracker performance. Comprehensive experiments have conducted on the OTB-2013 dataset. When adopting our ideas to adjust our tracker, the self-adaptive mechanism can avoid unnecessary training iterations, and the fuzzy update strategy reduces one fifth tracking computation compared to the ECO. Within reduced computation, the tracker based our idea incurs less than 1% loss in AUC (area-undercurve).

scholarly journals Visual Object Tracking with Online Updating for Car Sharing Services

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhou Zhu ◽  
Haifeng Zhao ◽  
Fang Hui ◽  
Yan Zhang
Keyword(s):  
Object Tracking ◽  
Visual Object ◽  
Car Sharing ◽  
Current Frame ◽  
Visual Object Tracking ◽  
Fixed Weight ◽  
Proposed Model ◽  
Model Update ◽  
Image Pairs ◽  
Update Strategy

In this paper, we address the problem of online updating of visual object tracker for car sharing services. The key idea is to adjust the updating rate adaptively according to the tracking performance of the current frame. Instead of setting a fixed weight for all the frames in the updating of the object model, we assign the current frame a larger weight if its corresponding tracking result is relatively accurate and unbroken and a smaller weight on the contrary. To implement it, the current estimated bounding box’s intersection over union (IOU) is calculated by an IOU predictor which is trained offline on a large number of image pairs and used as a guidance to adjust the updating weights online. Finally, we imbed the proposed model update strategy in a lightweight baseline tracker. Experiment results on both traffic and nontraffic datasets verify that though the error of predicted IOU is inevitable, the proposed method can still improve the accuracy of object tracking compared with the baseline object tracker.

scholarly journals Discriminative and Robust Online Learning for Siamese Visual Tracking

2020 ◽  
Vol 34 (07) ◽  
pp. 13017-13024 ◽  
Author(s):  
Jinghao Zhou ◽  
Peng Wang ◽  
Haoyang Sun
Keyword(s):  
Discriminative Learning ◽  
Visual Object ◽  
Specific Context ◽  
Visual Object Tracking ◽  
Robust Learning ◽  
Online Module ◽  
Recent Success ◽  
Template Update ◽  
Update Strategy ◽  
Siamese Networks

The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding space. Despite the recent success, each method agonizes over its intrinsic constraint. The online-only approaches suffer from a lack of generalization of the model they learn thus are inferior in target regression, while the offline-only approaches (e.g., convolutional siamese trackers) lack the target-specific context information thus are not discriminative enough to handle distractors, and robust enough to deformation. Therefore, we propose an online module with an attention mechanism for offline siamese networks to extract target-specific features under L2 error. We further propose a filter update strategy adaptive to treacherous background noises for discriminative learning, and a template update strategy to handle large target deformations for robust learning. Effectiveness can be validated in the consistent improvement over three siamese baselines: SiamFC, SiamRPN++, and SiamMask. Beyond that, our model based on SiamRPN++ obtains the best results over six popular tracking benchmarks and can operate beyond real-time.

scholarly journals Visual Object Tracking Based on 2DPCA and ML

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Ming-Xin Jiang ◽  
Min Li ◽  
Hong-Yu Wang
Keyword(s):  
Object Tracking ◽  
Principal Component ◽  
Likelihood Estimation ◽  
Subspace Learning ◽  
Tracking Algorithm ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Error Matrix ◽  
Template Update ◽  
Update Strategy

We present a novel visual object tracking algorithm based on two-dimensional principal component analysis (2DPCA) and maximum likelihood estimation (MLE). Firstly, we introduce regularization into the 2DPCA reconstruction and develop an iterative algorithm to represent an object by 2DPCA bases. Secondly, the model of sparsity constrained MLE is established. Abnormal pixels in the samples will be assigned with low weights to reduce their effects on the tracking algorithm. The object tracking results are obtained by using Bayesian maximum a posteriori (MAP) probability estimation. Finally, to further reduce tracking drift, we employ a template update strategy which combines incremental subspace learning and the error matrix. This strategy adapts the template to the appearance change of the target and reduces the influence of the occluded target template as well. Compared with other popular methods, our method reduces the computational complexity and is very robust to abnormal changes. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm achieves more favorable performance than several state-of-the-art methods.

scholarly journals Robust Long-Term Visual Object Tracking via Low-Rank Sparse Learning for Re-Detection

2021 ◽  
Vol 11 (4) ◽  
pp. 1963
Author(s):  
Shanshan Luo ◽  
Baoqing Li ◽  
Xiaobing Yuan ◽  
Huawei Liu
Keyword(s):  
Object Tracking ◽  
High Speed ◽  
Evaluation Method ◽  
Low Rank ◽  
Sparse Learning ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Training Samples ◽  
The Impact

The Discriminative Correlation Filter (DCF) has been universally recognized in visual object tracking, thanks to its excellent accuracy and high speed. Nevertheless, these DCF-based trackers perform poorly in long-term tracking. The reasons include the following aspects—first, they have low adaptability to significant appearance changes in long-term tracking and are prone to tracking failure; second, these trackers lack a practical re-detection module to find the target again after tracking failure. In our work, we propose a new long-term tracking strategy to solve these issues. First, we make the best of the static and dynamic information of the target by introducing the motion features to our long-term tracker and obtain a more robust tracker. Second, we introduce a low-rank sparse dictionary learning method for re-detection. This re-detection module can exploit a correlation among these training samples and alleviate the impact of occlusion and noise. Third, we propose a new reliability evaluation method to model an adaptive update, which can switch expediently between the tracking module and the re-detection module. Massive experiments demonstrate that our proposed approach has an obvious improvement in precision and success rate over these state-of-the-art trackers.

scholarly journals ACSiamRPN: Adaptive Context Sampling for Visual Object Tracking

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1528
Author(s):  
Xiaofei Qin ◽  
Yipeng Zhang ◽  
Hang Chang ◽  
Hao Lu ◽  
Xuedian Zhang
Keyword(s):  
Object Tracking ◽  
Long Range ◽  
Global Maximum ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Siamese Network ◽  
Information Embedding ◽  
Selection Step ◽  
Block Based ◽  
The Impact

In visual object tracking fields, the Siamese network tracker, based on the region proposal network (SiamRPN), has achieved promising tracking effects, both in speed and accuracy. However, it did not consider the relationship and differences between the long-range context information of various objects. In this paper, we add a global context block (GC block), which is lightweight and can effectively model long-range dependency, to the Siamese network part of SiamRPN so that the object tracker can better understand the tracking scene. At the same time, we propose a novel convolution module, called a cropping-inside selective kernel block (CiSK block), based on selective kernel convolution (SK convolution, a module proposed in selective kernel networks) and use it in the region proposal network (RPN) part of SiamRPN, which can adaptively adjust the size of the receptive field for different types of objects. We make two improvements to SK convolution in the CiSK block. The first improvement is that in the fusion step of SK convolution, we use both global average pooling (GAP) and global maximum pooling (GMP) to enhance global information embedding. The second improvement is that after the selection step of SK convolution, we crop out the outermost pixels of features to reduce the impact of padding operations. The experiment results show that on the OTB100 benchmark, we achieved an accuracy of 0.857 and a success rate of 0.643. On the VOT2016 and VOT2019 benchmarks, we achieved expected average overlap (EAO) scores of 0.394 and 0.240, respectively.

scholarly journals A Robust Visual Tracking Algorithm Based on Spatial-Temporal Context Hierarchical Response Fusion

Algorithms ◽  
2018 ◽  
Vol 12 (1) ◽  
pp. 8 ◽  
Author(s):  
Wancheng Zhang ◽  
Yanmin Luo ◽  
Zhi Chen ◽  
Yongzhao Du ◽  
Daxin Zhu ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Correlation Filter ◽  
Temporal Context ◽  
Visual Object ◽  
Correlation Filters ◽  
Visual Object Tracking ◽  
Illumination Changes ◽  
Model Update ◽  
Benchmark Datasets ◽  
Hierarchical Features

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual object tracking. However, visual tracking is still challenging when the target objects undergo complex scenarios such as occlusion, deformation, scale changes and illumination changes. In this paper, we utilize the hierarchical features of convolutional neural networks (CNNs) and learn a spatial-temporal context correlation filter on convolutional layers. Then, the translation is estimated by fusing the response score of the filters on the three convolutional layers. In terms of scale estimation, we learn a discriminative correlation filter to estimate scale from the best confidence results. Furthermore, we proposed a re-detection activation discrimination method to improve the robustness of visual tracking in the case of tracking failure and an adaptive model update method to reduce tracking drift caused by noisy updates. We evaluate the proposed tracker with DCFs and deep features on OTB benchmark datasets. The tracking results demonstrated that the proposed algorithm is superior to several state-of-the-art DCF methods in terms of accuracy and robustness.

scholarly journals Re2EMA: Regularized and Reinitialized Exponential Moving Average for Target Model Update in Object Tracking

2019 ◽  
Vol 33 ◽  
pp. 8457-8464
Author(s):  
Jianglei Huang ◽  
Wengang Zhou
Keyword(s):  
Object Tracking ◽  
Moving Average ◽  
Transformation Matrix ◽  
Visual Object ◽  
Optimal Model ◽  
Visual Object Tracking ◽  
Target Model ◽  
Model Update ◽  
Optimal Target

Target model update plays an important role in visual object tracking. However, performing optimal model update is challenging. In this work, we propose to achieve an optimal target model by learning a transformation matrix from the last target model to the newly generated one, which results into a minimization objective. In this objective, there exists two challenges. The first is that the newly generated target model is unreliable. To overcome this problem, we propose to impose a penalty to limit the distance between the learned target model and the last one. The second is that as time evolves, we can not decide whether the last target model has been corrupted or not. To get out of this dilemma, we propose a reinitialization term. Besides, to control the complexity of the transformation matrix, we also add a regularizer. We find that the optimization formula’s solution, with some simplifications, degenerates to EMA. Finally, despite the simplicity, extensive experiments conducted on several commonly used benchmarks demonstrate the effectiveness of our proposed approach in relatively long term scenarios.

scholarly journals Convolutional Shallow Features for Performance Improvement of Histogram of Oriented Gradients in Visual Object Tracking

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Suryo Adhi Wibowo ◽  
Hansoo Lee ◽  
Eun Kyeong Kim ◽  
Sungshin Kim
Keyword(s):  
Object Tracking ◽  
Target Object ◽  
Visual Object ◽  
Feature Descriptor ◽  
Histogram Of Oriented Gradients ◽  
Visual Object Tracking ◽  
Maximum Value ◽  
Model Update ◽  
Feature Based ◽  
Final Response

Histogram of oriented gradients (HOG) is a feature descriptor typically used for object detection. For object tracking, this feature has certain drawbacks when the target object is influenced by a change in motion or size. In this paper, the use of convolutional shallow features is proposed to improve the performance of HOG feature-based object tracking. Because the proposed method works based on a correlation filter, the response maps for each feature are summed in order to obtain the final response map. The location of the target object is then predicted based on the maximum value of the optimized final response map. Further, a model update is used to overcome the change in appearance of the target object during tracking. A performance evaluation of the proposed method is obtained by using Visual Object Tracking 2015 (VOT2015) benchmark dataset and its protocols. The results are then provided based on their accuracy-robustness (AR) rank. Furthermore, through a comparison with several state-of-the-art tracking algorithms, the proposed method was shown to achieve the highest rank in terms of accuracy and a third rank for robustness. In addition, the proposed method significantly improves the robustness of HOG-based features.

Sign in / Sign up

Export Citation Format

Share Document