scholarly journals Feature Fusion-Based Siamese Region Proposal Network for Ultrasound Tracking

2021 ◽  
Author(s):  
Xinglong Zhu ◽  
Ruirui Kang ◽  
Yifan Wang ◽  
Danni Ai ◽  
Tianyu Fu ◽  
...  
Keyword(s):  
Object Tracking ◽  
Feature Fusion ◽  
Ultrasound Image ◽  
The Self ◽  
Network Module ◽  
Training Strategy ◽  
Liver Ultrasound ◽  
Unsupervised Training ◽  
Image Navigation ◽  
Ultrasound Tracking

Object tracking based on ultrasound image navigation can effectively reduce damage to healthy tissues in radiotherapy. In this study, we propose a deep Siamese network based on feature fusion. Whilst adopting MobileNetV2 as the backbone, an unsupervised training strategy is introduced to enrich the volume of the samples. The region proposal network module is designed to predict the location of the target, and a non-maximum suppression-based postprocessing algorithm is designed to refine the tracking results. Moreover, the proposed method is evaluated in the Challenge on Liver Ultrasound Tracking dataset and the self-collected dataset, which proves the need for the improvement and the effectiveness of the algorithm.

Design of UAV Single Object Tracking Algorithm Based on Feature Fusion

2021 ◽  
Author(s):  
Changze Li ◽  
Xiaoxiong Liu ◽  
Xingwang Zhang ◽  
Bin Qin
Keyword(s):  
Object Tracking ◽  
Feature Fusion ◽  
Tracking Algorithm ◽  
Single Object

Anti-Occlusion Algorithm for Object Tracking Based on Multi-Feature Fusion

2014 ◽  
Vol 610 ◽  
pp. 393-400
Author(s):  
Jie Cao ◽  
Xuan Liang
Keyword(s):  
Object Tracking ◽  
Feature Fusion ◽  
Experimental Results ◽  
Occlusion Detection ◽  
Fusion Algorithm ◽  
Fusion Strategy ◽  
Complex Background ◽  
Complex Scenes

Complex background, especially when the object is similar to the background in color or the target gets blocked, can easily lead to tracking failure. Therefore, a fusion algorithm based on features confidence and similarity was proposed, it can adaptively adjust fusion strategy when occlusion occurs. And this confidence is used among occlusion detection, to overcome the problem of inaccurate occlusion determination when blocked by analogue. The experimental results show that the proposed algorithm is more robust in the case of the cover, but also has good performance under other complex scenes.

Distractor-Aware Object Tracking Based on Multi-Feature Fusion and Scale-Adaption

2017 ◽  
Vol 37 (5) ◽  
pp. 0515005
Author(s):  
李双双 Li Shuangshuang ◽  
赵高鹏 Zhao Gaopeng ◽  
王建宇 Wang Jianyu
Keyword(s):  
Object Tracking ◽  
Feature Fusion

Long-Term Object Tracking Based On Feature Fusion

2018 ◽  
Vol 38 (11) ◽  
pp. 1115002
Author(s):  
葛宝义 Ge Baoyi ◽  
左宪章 Zuo Xianzhang ◽  
胡永江 Hu Yongjiang
Keyword(s):  
Object Tracking ◽  
Feature Fusion

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

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4021 ◽  
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.

Sign in / Sign up

Export Citation Format

Share Document