Feature Projection and SVR-Based Model Update for Object Tracking

Object tracking has always been an interesting and essential research topic in the domain of computer vision, of which the model update mechanism is an essential work, therefore the robustness of it has become a crucial factor influencing the quality of tracking of a sequence. This review analyses on recent tracking model update strategies, where target model update occasion is first discussed, then we give a detailed discussion on update strategies of the target model based on the mainstream tracking frameworks, and the background update frameworks are discussed afterwards. The experimental performances of the trackers in recent researches acting on specific sequences are listed in this review, where the superiority and some failure cases on each of them are discussed, and conclusions based on those performances are then drawn. It is a crucial point that design of a proper background model as well as its update strategy ought to be put into consideration. A cascade update of the template corresponding to each deep network layer based on the contributions of them to the target recognition can also help with more accurate target location, where target saliency information can be utilized as a tool for state estimation.

Download Full-text

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

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33018457 ◽

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.

Download Full-text

A Visual Object Tracking Method Based on Improved Bhattacharyya Coefficient and Model Update Strategy

10.1109/isdea.2014.30 ◽

2014 ◽

Author(s):

Huang An-Qi ◽

Hou Zhi-Qiang ◽

Yu Wang-Sheng ◽

Liu Xiang

Keyword(s):

Object Tracking ◽

Visual Object ◽

Visual Object Tracking ◽

Tracking Method ◽

Bhattacharyya Coefficient ◽

Model Update ◽

Update Strategy

Download Full-text

A model update scheme of color-based particle filter for multi-color object tracking

2012 International Symposium on Intelligent Signal Processing and Communications Systems ◽

10.1109/ispacs.2012.6473461 ◽

2012 ◽

Cited By ~ 2

Author(s):

Satoshi Hirose ◽

Nozomu Hamada

Keyword(s):

Particle Filter ◽

Object Tracking ◽

Model Update

Download Full-text

Kernel based articulated object tracking with scale adaptation and model update

2008 IEEE International Conference on Acoustics, Speech and Signal Processing ◽

10.1109/icassp.2008.4517767 ◽

2008 ◽

Author(s):

Anbang Yao ◽

Guijin Wang ◽

Xinggang Lin ◽

Hao Wang

Keyword(s):

Object Tracking ◽

Scale Adaptation ◽

Model Update ◽

Articulated Object Tracking

Download Full-text

rStaple: A Robust Complementary Learning Method for Real-Time Object Tracking

Applied Sciences ◽

10.3390/app10093021 ◽

2020 ◽

Vol 10 (9) ◽

pp. 3021

Author(s):

Wangpeng He ◽

Heyi Li ◽

Wei Liu ◽

Cheng Li ◽

Baolong Guo

Keyword(s):

Object Tracking ◽

Real Time ◽

Target Position ◽

Color Histogram ◽

Correlation Filter ◽

Correlation Filters ◽

Training Samples ◽

Model Update ◽

Score Map ◽

Scale Detection

Object tracking is a challenging research task because of drastic appearance changes of the target and a lack of training samples. Most online learning trackers are hampered by complications, e.g., drifting problem under occlusion, being out of view, or fast motion. In this paper, a real-time object tracking algorithm termed “robust sum of template and pixel-wise learners” (rStaple) is proposed to address those problems. It combines multi-feature correlation filters with a color histogram. Firstly, we extract a combination of specific features from the searching area around the target and then merge feature channels to train a translation correlation filter online. Secondly, the target state is determined by a discriminating mechanism, wherein the model update procedure stops when the target is occluded or out of view, and re-activated when the target re-appears. In addition, by calculating the color histogram score in the searching area, a significant enhancement is adopted for the score map. The target position can be estimated by combining the enhanced color histogram score with the correlation filter response map. Finally, a scale filter is trained for multi-scale detection to obtain the final tracking result. Extensive experimental results on a large benchmark dataset demonstrates that the proposed rStaple is superior to several state-of-the-art algorithms in terms of accuracy and efficiency.

Download Full-text

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

Mathematical Problems in Engineering ◽

10.1155/2017/6329864 ◽

2017 ◽

Vol 2017 ◽

pp. 1-9 ◽

Cited By ~ 1

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.

Download Full-text