Robust Visual Tracking with Double Bounding Box Model

Research on Obstacle Avoidance of Space Manipulators Based on Cylindrical Bounding Box Model

2018 IEEE International Conference on Mechatronics and Automation (ICMA) ◽

10.1109/icma.2018.8484351 ◽

2018 ◽

Cited By ~ 1

Author(s):

Jing Liu ◽

Ruimin Liu ◽

Xin Shen ◽

Linmin Meng

Keyword(s):

Obstacle Avoidance ◽

Box Model ◽

Bounding Box ◽

Space Manipulators

Download Full-text

Enhanced Bounding Box Estimation with Distribution Calibration for Visual Tracking

Sensors ◽

10.3390/s21238100 ◽

2021 ◽

Vol 21 (23) ◽

pp. 8100

Author(s):

Bin Yu ◽

Ming Tang ◽

Guibo Zhu ◽

Jinqiao Wang ◽

Hanqing Lu

Keyword(s):

Visual Tracking ◽

Large Scale ◽

State Of The Art ◽

Estimation Method ◽

Target Object ◽

Reference Information ◽

Bounding Box ◽

The Mean ◽

Modulation Vector ◽

Initial Target

Bounding box estimation by overlap maximization has improved the state of the art of visual tracking significantly, yet the improvement in robustness and accuracy is restricted by the limited reference information, i.e., the initial target. In this paper, we present DCOM, a novel bounding box estimation method for visual tracking, based on distribution calibration and overlap maximization. We assume every dimension in the modulation vector follows a Gaussian distribution, so that the mean and the variance can borrow from those of similar targets in large-scale training datasets. As such, sufficient and reliable reference information can be obtained from the calibrated distribution, leading to a more robust and accurate target estimation. Additionally, an updating strategy for the modulation vector is proposed to adapt the variation of the target object. Our method can be built on top of off-the-shelf networks without finetuning and extra parameters. It yields state-of-the-art performance on three popular benchmarks, including GOT-10k, LaSOT, and NfS while running at around 40 FPS, confirming its effectiveness and efficiency.

Download Full-text

Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks

International Journal of Computer Vision ◽

10.1007/s11263-021-01559-4 ◽

2022 ◽

Author(s):

Ying Cui ◽

Dongyan Guo ◽

Yanyan Shao ◽

Zhenhua Wang ◽

Chunhua Shen ◽

...

Keyword(s):

Visual Tracking ◽

Parameter Tuning ◽

Classification Problem ◽

Backbone Networks ◽

Bounding Box ◽

Classification And Regression ◽

Ablation Study ◽

Joint Classification ◽

Object Status ◽

Siamese Networks

AbstractVisual tracking of generic objects is one of the fundamental but challenging problems in computer vision. Here, we propose a novel fully convolutional Siamese network to solve visual tracking by directly predicting the target bounding box in an end-to-end manner. We first reformulate the visual tracking task as two subproblems: a classification problem for pixel category prediction and a regression task for object status estimation at this pixel. With this decomposition, we design a simple yet effective Siamese architecture based classification and regression framework, termed SiamCAR, which consists of two subnetworks: a Siamese subnetwork for feature extraction and a classification-regression subnetwork for direct bounding box prediction. Since the proposed framework is both proposal- and anchor-free, SiamCAR can avoid the tedious hyper-parameter tuning of anchors, considerably simplifying the training. To demonstrate that a much simpler tracking framework can achieve superior tracking results, we conduct extensive experiments and comparisons with state-of-the-art trackers on a few challenging benchmarks. Without bells and whistles, SiamCAR achieves leading performance with a real-time speed. Furthermore, the ablation study validates that the proposed framework is effective with various backbone networks, and can benefit from deeper networks. Code is available at https://github.com/ohhhyeahhh/SiamCAR.

Download Full-text

Visual Tracking with Bounding-Box Fine Adjustment

2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) ◽

10.1109/cisp-bmei.2018.8633166 ◽

2018 ◽

Author(s):

Tianhui Qi ◽

Hui Zhang ◽

Jiafeng Li ◽

Li Zhuo

Keyword(s):

Visual Tracking ◽

Bounding Box ◽

Fine Adjustment

Download Full-text

Minimum Barrier Distance-Based Object Descriptor for Visual Tracking

Applied Sciences ◽

10.3390/app8112233 ◽

2018 ◽

Vol 8 (11) ◽

pp. 2233 ◽

Cited By ~ 1

Author(s):

Zhengzheng Tu ◽

Linlin Guo ◽

Chenglong Li ◽

Ziwei Xiong ◽

Xiao Wang

Keyword(s):

Visual Tracking ◽

Seed Set ◽

Background Information ◽

Support Vector ◽

Support Vector Machine Algorithm ◽

Tracking Tasks ◽

Bounding Box ◽

Benchmark Datasets ◽

The Difference ◽

Structured Support Vector Machine

In most visual tracking tasks, the target is tracked by a bounding box given in the first frame. The complexity and redundancy of background information in the bounding box inevitably exist and affect tracking performance. To alleviate the influence of background, we propose a robust object descriptor for visual tracking in this paper. First, we decompose the bounding box into non-overlapping patches and extract the color and gradient histograms features for each patch. Second, we adopt the minimum barrier distance (MBD) to calculate patch weights. Specifically, we consider the boundary patches as the background seeds and calculate the MBD from each patch to the seed set as the weight of each patch since the weight calculated by MBD can represent the difference between each patch and the background more effectively. Finally, we impose the weight on the extracted feature to get the descriptor of each patch and then incorporate our MBD-based descriptor into the structured support vector machine algorithm for tracking. Experiments on two benchmark datasets demonstrate the effectiveness of the proposed approach.

Download Full-text