HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Li, Chenpu; Xing, Qianjian; Ma, Zhenguo

doi:10.3390/s20072137

Cited by 8 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SiamFC-based CFNet not only combines CF and depth features but also enables end-to-end training in CNN, but it cannot handle the boundary effect of the CF layer [17]. Based on the improvement of SiamFC, SiamFC++ adds the bounding box regression branch and the quality estimation branch, which improves the robustness and reaches the advanced tracking level [18]. is also enables the combined use of the CNN model to more accurately and quickly classify and recognize ultrasound images.…”

Section: Discussionmentioning

confidence: 99%

Classification and Recognition of Doppler Ultrasound Images of Patients with Atrial Fibrillation under Machine Learning

Wang

Zhang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

This study was aimed to explore the value of the twin neural network model in the classification and recognition of cardiac ultrasound images of patients with atrial fibrillation. 80 patients with cardiac atrial fibrillation were selected and randomly divided into experimental group (40 cases) and control group (40 cases). The twin neural network (TNN) model was combined with traditional ultrasound, Doppler spectrum, tissue velocity, and strain imaging technology to obtain the patient’s cardiac structure parameters and analyze and compare related indicators. The results showed that the total atrial emptying fraction (TA-EF value) of the experimental group was 53.08%, which was significantly lower than that of the control group ( P < 0.05 ). There were no significant differences in left atrial diameter (LAD), left ventricular end-diastolic diameter (LVEDD), left atrial maximum volume (LAVmax), and left ventricular ejection fraction (LVEF) between the two groups. In the experimental group, the average peak velocity of mitral valve annulus (Em) was 8.49 cm/s, the peak velocity of lateral wall systole (Vs) was 6.82 cm/s, and the propagation velocity of left ventricular blood flow (Vp) was 51.2 cm/s, which were significantly reduced ( P < 0.05 ). The average values of peak strains in the middle and upper left atrium of the experimental group were significantly lower than those of the control group ( P < 0.05 ). It can be concluded that the combined use of the TNN model can more accurately and quickly classify and recognize ultrasound images.

show abstract

Section: Discussionmentioning

confidence: 99%

Classification and Recognition of Doppler Ultrasound Images of Patients with Atrial Fibrillation under Machine Learning

Wang

Zhang

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…The flexible target range ensures that the returned tracking bounding box matches the real target range more closely, but it is also more susceptible to interference from surrounding objects with similar features. Therefore, several scholars have attempted to propose a series of anti‐interference modules (Li et al, 2020; Tan & Lai, 2019; Wei et al, 2022; Yan et al, 2022). Current deep learning‐based target‐tracking methods tend to use deeper networks as feature extractors to improve the retrieval of targets in the search area.…”

Section: Related Workmentioning

confidence: 99%

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Lin

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

Identifying and tracking objects in surveillance videos is an important means of mining information during surveillance. Currently, most object‐tracking methods rely only on image features, which cannot accurately express the motion of the tracked object in real geographical scenes and are easily influenced by occlusion and surrounding objects having similar features. However, tracked objects, such as pedestrians and vehicles, usually move in geographical space with fixed patterns of motion, and the motion in a short time is constrained by geographical space and time, the motion trajectory is predictable, and the range of motion is limited. Therefore, based on the SiamFC object tracking framework, this study introduces geographical spatiotemporal constraints into the tracking framework and proposes the GeoSiamFC method. The objective of this is to: (1) construct the mapping relationship between geographical space and image space to solve the problem that the pixel movement within the image after perspective imaging cannot accurately express the motion of the tracked object in a real geographical scene; (2) add candidate search areas according to the predicted trajectory location to correct the tracking errors caused by the occlusion of the object; and (3) focus on the search for the range of motion of the mapped pixel within the image space according to the limited geographical range of motion of the tracked objects in a certain time to reduce the interference of similar objects within the search area. In this study, separate experiments were conducted on a common test dataset using multiple methods to deal with challenges such as occlusion and illumination changes. In addition, a robust test dataset with noise addition and luminance adjustment based on the common test dataset was used. The results show that GeoSiamFC outperforms other object‐tracking methods in the common test dataset with a precision score of 0.995 and a success score of 0.756 compared with most other object‐tracking algorithms under the base condition of using only shallow networks. Moreover, GeoSiamFC maintained the highest precision score (0.970) and high success score (0.734) in the more challenging robust test dataset as well. The tracking speed of 59 frames per second far exceeds the real‐time requirement of 25 FPS. Geographical spatiotemporal constraints were considered to improve tracker performance while providing real‐time feedback on the motion trajectory of the target in geographical space. Thus, the proposed method is suitable for real‐time tracking of the motion trajectory of a target in real geographical scenes in various surveillance videos.

show abstract

“…SANT [ 27 ] presents structure-attention networks to learn robust structure information of targets. HKSiamFC [ 28 ] adopts Histogram model to explore target’s prior color information, and makes SiamFC more robust in some complex environments.…”

Section: Related Workmentioning

confidence: 99%

Robust Visual Tracking with Reliable Object Information and Kalman Filter

Chen

Zhang

Yan

2021

Sensors

View full text Add to dashboard Cite

Object information significantly affects the performance of visual tracking. However, it is difficult to obtain accurate target foreground information because of the existence of challenging scenarios, such as occlusion, background clutter, drastic change of appearance, and so forth. Traditional correlation filter methods roughly use linear interpolation to update the model, which may lead to the introduction of noise and the loss of reliable target information, resulting in the degradation of tracking performance. In this paper, we propose a novel robust visual tracking framework with reliable object information and Kalman filter (KF). Firstly, we analyze the reliability of the tracking process, calculate the confidence of the target information at the current estimated location, and determine whether it is necessary to carry out the online training and update step. Secondly, we also model the target motion between frames with a KF module, and use it to supplement the correlation filter estimation. Finally, in order to keep the most reliable target information of the first frame in the whole tracking process, we propose a new online training method, which can improve the robustness of the tracker. Extensive experiments on several benchmarks demonstrate the effectiveness and robustness of our proposed method, and our method achieves a comparable or better performance compared with several other state-of-the-art trackers.

show abstract

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Cited by 8 publications

References 45 publications

Classification and Recognition of Doppler Ultrasound Images of Patients with Atrial Fibrillation under Machine Learning

Classification and Recognition of Doppler Ultrasound Images of Patients with Atrial Fibrillation under Machine Learning

Object tracking in surveillance video based on Siamese network considering geographical spatiotemporal constraints

Robust Visual Tracking with Reliable Object Information and Kalman Filter

Contact Info

Product

Resources

About