CAT: Centerness-Aware Anchor-Free Tracker

Accurate and robust scale estimation in visual object tracking is a challenging task. To obtain a scale estimation of the target object, most methods rely either on a multi-scale searching scheme or on refining a set of predefined anchor boxes. These methods require heuristically selected parameters, such as scale factors of the multi-scale searching scheme, or sizes and aspect ratios of the predefined candidate anchor boxes. On the contrary, a centerness-aware anchor-free tracker (CAT) is designed in this work. First, the location and scale of the target object are predicted in an anchor-free fashion by decomposing tracking into parallel classification and regression problems. The proposed anchor-free design obviates the need for hyperparameters related to the anchor boxes, making CAT more generic and flexible. Second, the proposed centerness-aware classification branch can identify the foreground from the background while predicting the normalized distance from the location within the foreground to the target center, i.e., the centerness. The proposed centerness-aware classification branch improves the tracking accuracy and robustness significantly by suppressing low-quality state estimates. The experiments show that our centerness-aware anchor-free tracker, with its appealing features, achieves salient performance in a wide variety of tracking scenarios.

Download Full-text

Robust real-time visual object tracking via multi-scale fully convolutional Siamese networks

Multimedia Tools and Applications ◽

10.1007/s11042-018-5664-7 ◽

2018 ◽

Vol 77 (17) ◽

pp. 22131-22143 ◽

Cited By ~ 4

Author(s):

Longchao Yang ◽

Peilin Jiang ◽

Fei Wang ◽

Xuan Wang

Keyword(s):

Object Tracking ◽

Real Time ◽

Visual Object ◽

Visual Object Tracking ◽

Multi Scale ◽

Siamese Networks

Download Full-text

Multi-scale Region Proposal Network Trained by Multi-domain Learning for Visual Object Tracking

Neural Information Processing - Lecture Notes in Computer Science ◽

10.1007/978-3-319-70090-8_34 ◽

2017 ◽

pp. 330-339

Author(s):

Yang Fang ◽

Seunghyun Ko ◽

Geun-Sik Jo

Keyword(s):

Object Tracking ◽

Visual Object ◽

Visual Object Tracking ◽

Multi Scale ◽

Domain Learning

Download Full-text

Visual Tracking Based on Complementary Learners with Distractor Handling

Mathematical Problems in Engineering ◽

10.1155/2017/5295601 ◽

2017 ◽

Vol 2017 ◽

pp. 1-13 ◽

Cited By ~ 2

Author(s):

Suryo Adhi Wibowo ◽

Hansoo Lee ◽

Eun Kyeong Kim ◽

Sungshin Kim

Keyword(s):

Visual Tracking ◽

Object Representation ◽

Target Location ◽

Target Object ◽

Tracking Algorithm ◽

Color Histogram ◽

Correlation Filter ◽

Visual Object ◽

Visual Object Tracking ◽

Benchmark Datasets

The representation of the object is an important factor in building a robust visual object tracking algorithm. To resolve this problem, complementary learners that use color histogram- and correlation filter-based representation to represent the target object can be used since they each have advantages that can be exploited to compensate the other’s drawback in visual tracking. Further, a tracking algorithm can fail because of the distractor, even when complementary learners have been implemented for the target object representation. In this study, we show that, in order to handle the distractor, first the distractor must be detected by learning the responses from the color-histogram- and correlation-filter-based representation. Then, to determine the target location, we can decide whether the responses from each representation should be merged or only the response from the correlation filter should be used. This decision depends on the result obtained from the distractor detection process. Experiments were performed on the widely used VOT2014 and VOT2015 benchmark datasets. It was verified that our proposed method performs favorably as compared with several state-of-the-art visual tracking algorithms.

Download Full-text

Visual Object Tracking Using Fast Three-Dimensional Discrete Cosine Transform

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.1689 ◽

2014 ◽

Vol 602-605 ◽

pp. 1689-1692

Author(s):

Cong Lin ◽

Chi Man Pun

Keyword(s):

Object Tracking ◽

Discrete Cosine Transform ◽

Three Dimensional ◽

Video Stream ◽

Target Object ◽

Visual Object ◽

Visual Object Tracking ◽

Cosine Transform ◽

Color Video ◽

Real Time Application

A novel visual object tracking method for color video stream based on traditional particle filter is proposed in this paper. Feature vectors are extracted from coefficient matrices of fast three-dimensional Discrete Cosine Transform (fast 3-D DCT). The feature, as experiment showed, is very robust to occlusion and rotation and it is not sensitive to scale changes. The proposed method is efficient enough to be used in a real-time application. The experiment was carried out on some common used datasets in literature. The results are satisfied and showed the estimated trace follows the target object very closely.

Download Full-text

Distractor-Aware Deep Regression for Visual Tracking

Sensors ◽

10.3390/s19020387 ◽

2019 ◽

Vol 19 (2) ◽

pp. 387 ◽

Cited By ~ 1

Author(s):

Ming Du ◽

Yan Ding ◽

Xiuyun Meng ◽

Hua-Liang Wei ◽

Yifan Zhao

Keyword(s):

Object Tracking ◽

Visual Tracking ◽

Test Data ◽

Loss Function ◽

State Of The Art ◽

Target Object ◽

Visual Object ◽

Visual Object Tracking ◽

Training Samples ◽

Better Than

In recent years, regression trackers have drawn increasing attention in the visual-object tracking community due to their favorable performance and easy implementation. The tracker algorithms directly learn mapping from dense samples around the target object to Gaussian-like soft labels. However, in many real applications, when applied to test data, the extreme imbalanced distribution of training samples usually hinders the robustness and accuracy of regression trackers. In this paper, we propose a novel effective distractor-aware loss function to balance this issue by highlighting the significant domain and by severely penalizing the pure background. In addition, we introduce a full differentiable hierarchy-normalized concatenation connection to exploit abstractions across multiple convolutional layers. Extensive experiments were conducted on five challenging benchmark-tracking datasets, that is, OTB-13, OTB-15, TC-128, UAV-123, and VOT17. The experimental results are promising and show that the proposed tracker performs much better than nearly all the compared state-of-the-art approaches.

Download Full-text

A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking

Electronics ◽

10.3390/electronics9050854 ◽

2020 ◽

Vol 9 (5) ◽

pp. 854

Author(s):

Yuxiang Yang ◽

Weiwei Xing ◽

Shunli Zhang ◽

Qi Yu ◽

Xiaoyu Guo ◽

...

Keyword(s):

Object Tracking ◽

Low Frequency ◽

Linear Representation ◽

Visual Object ◽

Tracking Accuracy ◽

Discriminative Ability ◽

Visual Object Tracking ◽

Training Samples ◽

Complex Scenes ◽

Siamese Networks

Visual object tracking by Siamese networks has achieved favorable performance in accuracy and speed. However, the features used in Siamese networks have spatially redundant information, which increases computation and limits the discriminative ability of Siamese networks. Addressing this issue, we present a novel frequency-aware feature (FAF) method for robust visual object tracking in complex scenes. Unlike previous works, which select features from different channels or layers, the proposed method factorizes the feature map into multi-frequency and reduces the low-frequency information that is spatially redundant. By reducing the low-frequency map’s resolution, the computation is saved and the receptive field of the layer is also increased to obtain more discriminative information. To further improve the performance of the FAF, we design an innovative data-independent augmentation for object tracking to improve the discriminative ability of tracker, which enhanced linear representation among training samples by convex combinations of the images and tags. Finally, a joint judgment strategy is proposed to adjust the bounding box result that combines intersection-over-union (IoU) and classification scores to improve tracking accuracy. Extensive experiments on 5 challenging benchmarks demonstrate that our FAF method performs favorably against SOTA tracking methods while running around 45 frames per second.

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