Visual Object Tracking in RGB-D Data via Genetic Feature Learning

Visual object tracking is a fundamental component in many computer vision applications. Extracting robust features of object is one of the most important steps in tracking. As trackers, only formulated on RGB data, are usually affected by occlusions, appearance, or illumination variations, we propose a novel RGB-D tracking method based on genetic feature learning in this paper. Our approach addresses feature learning as an optimization problem. As owning the advantage of parallel computing, genetic algorithm (GA) has fast speed of convergence and excellent global optimization performance. At the same time, unlike handcrafted feature and deep learning methods, GA can be employed to solve the problem of feature representation without prior knowledge, and it has no use for a large number of parameters to be learned. The candidate solution in RGB or depth modality is represented as an encoding of an image in GA, and genetic feature is learned through population initialization, fitness evaluation, selection, crossover, and mutation. The proposed RGB-D tracker is evaluated on popular benchmark dataset, and experimental results indicate that our method achieves higher accuracy and faster tracking speed.

Download Full-text

Learning Soft Mask Based Feature Fusion with Channel and Spatial Attention for Robust Visual Object Tracking

Sensors ◽

10.3390/s20144021 ◽

2020 ◽

Vol 20 (14) ◽

pp. 4021 ◽

Cited By ~ 2

Author(s):

Mustansar Fiaz ◽

Arif Mahmood ◽

Soon Ki Jung

Keyword(s):

Object Tracking ◽

Spatial Attention ◽

Feature Fusion ◽

State Of The Art ◽

Feature Representation ◽

Visual Object ◽

Target Feature ◽

Visual Object Tracking ◽

Low Level ◽

Benchmark Datasets

We propose to improve the visual object tracking by introducing a soft mask based low-level feature fusion technique. The proposed technique is further strengthened by integrating channel and spatial attention mechanisms. The proposed approach is integrated within a Siamese framework to demonstrate its effectiveness for visual object tracking. The proposed soft mask is used to give more importance to the target regions as compared to the other regions to enable effective target feature representation and to increase discriminative power. The low-level feature fusion improves the tracker robustness against distractors. The channel attention is used to identify more discriminative channels for better target representation. The spatial attention complements the soft mask based approach to better localize the target objects in challenging tracking scenarios. We evaluated our proposed approach over five publicly available benchmark datasets and performed extensive comparisons with 39 state-of-the-art tracking algorithms. The proposed tracker demonstrates excellent performance compared to the existing state-of-the-art trackers.

Download Full-text

Improved Hierarchical Convolutional Features for Robust Visual Object Tracking

Complexity ◽

10.1155/2021/6690237 ◽

2021 ◽

Vol 2021 ◽

pp. 1-16

Author(s):

Jinping Sun

Keyword(s):

Object Tracking ◽

Target Position ◽

Feature Representation ◽

Correlation Filter ◽

Low Rank ◽

Visual Object ◽

Threshold Condition ◽

Current Frame ◽

Visual Object Tracking

The target and background will change continuously in the long-term tracking process, which brings great challenges to the accurate prediction of targets. The correlation filter algorithm based on manual features is difficult to meet the actual needs due to its limited feature representation ability. Thus, to improve the tracking performance and robustness, an improved hierarchical convolutional features model is proposed into a correlation filter framework for visual object tracking. First, the objective function is designed by lasso regression modeling, and a sparse, time-series low-rank filter is learned to increase the interpretability of the model. Second, the features of the last layer and the second pool layer of the convolutional neural network are extracted to realize the target position prediction from coarse to fine. In addition, using the filters learned from the first frame and the current frame to calculate the response maps, respectively, the target position is obtained by finding the maximum response value in the response map. The filter model is updated only when these two maximum responses meet the threshold condition. The proposed tracker is evaluated by simulation analysis on TC-128/OTB2015 benchmarks including more than 100 video sequences. Extensive experiments demonstrate that the proposed tracker achieves competitive performance against state-of-the-art trackers. The distance precision rate and overlap success rate of the proposed algorithm on OTB2015 are 0.829 and 0.695, respectively. The proposed algorithm effectively solves the long-term object tracking problem in complex scenes.

Download Full-text

Multi-domain collaborative feature representation for robust visual object tracking

The Visual Computer ◽

10.1007/s00371-021-02237-9 ◽

2021 ◽

Author(s):

Jiqing Zhang ◽

Kai Zhao ◽

Bo Dong ◽

Yingkai Fu ◽

Yuxin Wang ◽

...

Keyword(s):

Object Tracking ◽

Feature Representation ◽

Visual Object ◽

Visual Object Tracking

Download Full-text

Visual object tracking using Fourier domain phase information

Signal Image and Video Processing ◽

10.1007/s11760-021-01968-5 ◽

2021 ◽

Author(s):

Serdar Cakir ◽

A. Enis Cetin

Keyword(s):

Object Tracking ◽

Visual Object ◽

Fourier Domain ◽

Phase Information ◽

Visual Object Tracking ◽

Domain Phase

Download Full-text

Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters

International Journal of Computer Vision ◽

10.1007/s11263-021-01435-1 ◽

2021 ◽

Author(s):

Tianyang Xu ◽

Zhenhua Feng ◽

Xiao-Jun Wu ◽

Josef Kittler

Keyword(s):

Object Tracking ◽

Augmented Lagrangian Method ◽

Channel Selection ◽

Image Feature ◽

Superior Performance ◽

Appearance Model ◽

Visual Object ◽

Correlation Filters ◽

Visual Object Tracking ◽

Feature Representations

AbstractDiscriminative Correlation Filters (DCF) have been shown to achieve impressive performance in visual object tracking. However, existing DCF-based trackers rely heavily on learning regularised appearance models from invariant image feature representations. To further improve the performance of DCF in accuracy and provide a parsimonious model from the attribute perspective, we propose to gauge the relevance of multi-channel features for the purpose of channel selection. This is achieved by assessing the information conveyed by the features of each channel as a group, using an adaptive group elastic net inducing independent sparsity and temporal smoothness on the DCF solution. The robustness and stability of the learned appearance model are significantly enhanced by the proposed method as the process of channel selection performs implicit spatial regularisation. We use the augmented Lagrangian method to optimise the discriminative filters efficiently. The experimental results obtained on a number of well-known benchmarking datasets demonstrate the effectiveness and stability of the proposed method. A superior performance over the state-of-the-art trackers is achieved using less than $$10\%$$ 10 % deep feature channels.

Download Full-text