scholarly journals Scale-Adaptive Context-Aware Correlation Filter with Output Constraints for Visual Target Tracking

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Jingxiang Xu ◽  
Xuedong Wu ◽  
Zhiyu Zhu ◽  
Kaiyun Yang ◽  
Yanchao Chang ◽  
...  
Keyword(s):  
Target Tracking ◽  
Correlation Filter ◽  
Context Aware ◽  
Tracking Accuracy ◽  
Large Area ◽  
Posterior Probability Distribution ◽  
Output Response ◽  
Tracking Process ◽  
Output Constraints ◽  
Tracking Model

Context-aware correlation filter tracker is one of the most advanced target trackers, and it has significant improvement in tracking accuracy and success rate compared with traditional trackers. However, because the complexity of background in the process of tracking can lead to inaccurate output response of target tracking, an accurate tracking model is difficult to be established. Moreover, the drift problem is easy to occur during the tracking process due to the imprecise tracking model, especially when the target has large area occlusion, fast motion, and deformation. Aiming at the drift problem in the target tracking process, a novel algorithm is proposed in this paper. The developed method derives the specific representation of constraint output by assuming that the output response is Gaussian distribution, and a variable update parameter is obtained based on the output constraint relationship at first, then the tracking filter is selectively updated with changeable update parameters and fixed update parameters, and finally, the target scale is updated with maximizing posterior probability distribution. The effectiveness of developed algorithm is verified by comparing with other trackers on OTB-50 and OTB-100 evaluation benchmark datasets, and the experimental results have shown that the suggested tracker has higher overall object tracking performance than other trackers.

scholarly journals Research on Target Tracking Algorithm Based on Siamese Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Haibo Pang ◽  
Qi Xuan ◽  
Meiqin Xie ◽  
Chengming Liu ◽  
Zhanbo Li
Keyword(s):  
Neural Network ◽  
Target Tracking ◽  
Evaluation Criteria ◽  
Attention Mechanism ◽  
Tracking Algorithm ◽  
Temporal Attention ◽  
Tracking Accuracy ◽  
Current Frame ◽  
Tracking Process ◽  
Recognition Ability

Target tracking is a significant topic in the field of computer vision. In this paper, the target tracking algorithm based on deep Siamese network is studied. Aiming at the situation that the tracking process is not robust, such as drift or miss the target, the tracking accuracy and robustness of the algorithm are improved by improving the feature extraction part and online update part. This paper adds SE-block and temporal attention mechanism (TAM) to the framework of Siamese neural network. SE-block can refine and extract features; different channels are given different weights according to their importance which can improve the discrimination of the network and the recognition ability of the tracker. Temporal attention mechanism can update the target state by adjusting the weights of samples at current frame and historical frame to solve the model drift caused by the existence of similar background. We use cross-entropy loss to distinguish the targets in different sequences so that their distance in the feature domains is longer and the features are easier to identify. We train and test the network on three benchmarks and compare with several state-of-the-art tracking methods. The experimental results demonstrate that the algorithm proposed is superior to other methods in tracking effect diagram and evaluation criteria. The proposed algorithm can solve the occlusion problem effectively while ensuring the real-time performance in the process of tracking.

scholarly journals Adaptive context-aware correlation filter target tracking

2019 ◽  
Vol 1213 ◽  
pp. 052077
Author(s):  
Saijun Zhou ◽  
Chengwang Zhang ◽  
Xuying Xiong ◽  
Ran He ◽  
Jingang Qiu
Keyword(s):  
Target Tracking ◽  
Correlation Filter ◽  
Context Aware

scholarly journals Research on the Particle Filter Single-Station Target Tracking Algorithm Based on Particle Number Optimization

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Lieping Zhang ◽  
Jinghua Nie ◽  
Shenglan Zhang ◽  
Yanlin Yu ◽  
Yong Liang ◽  
...  
Keyword(s):  
Particle Filter ◽  
Target Tracking ◽  
Real Time ◽  
Particle Number ◽  
Tracking Algorithm ◽  
Tracking Accuracy ◽  
Time Performance ◽  
Single Station ◽  
Tracking Model ◽  
Number Of Particles

Given that the tracking accuracy and real-time performance of the particle filter (PF) target tracking algorithm are greatly affected by the number of sampled particles, a PF target tracking algorithm based on particle number optimization under the single-station environment was proposed in this study. First, a single-station target tracking model was established, and the corresponding PF algorithm was designed. Next, a tracking simulation experiment was carried out on the PF target tracking algorithm under different numbers of particles with the root mean square error (RMSE) and filtering time as the evaluation indexes. On this basis, the optimal number of particles, which could meet the accuracy and real-time performance requirements, was determined and taken as the number of particles of the proposed algorithm. The MATLAB simulation results revealed that compared with the unscented Kalman filter (UKF), the single-station PF target tracking algorithm based on particle number optimization not only was of high tracking accuracy but also could meet the real-time performance requirement.

scholarly journals Multitarget Real-Time Tracking Algorithm for UAV IoT

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Tao Hong ◽  
Qiye Yang ◽  
Peng Wang ◽  
Jinmeng Zhang ◽  
Wenbo Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Target Tracking ◽  
Real Time ◽  
High Speed ◽  
Rapid Development ◽  
Machine Learning Algorithms ◽  
Urban Life ◽  
Tracking Accuracy ◽  
Tracking Model ◽  
Real Time Tracking

Unmanned aerial vehicles (UAVs) have increased the convenience of urban life. Representing the recent rapid development of drone technology, UAVs have been widely used in fifth-generation (5G) cellular networks and the Internet of Things (IoT), such as drone aerial photography, express drone delivery, and drone traffic supervision. However, owing to low altitude and low speed, drones can only limitedly monitor and detect small target objects, resulting in frequent intrusion and collision. Traditional methods of monitoring the safety of drones are mostly expensive and difficult to implement. In smart city construction, a large number of smart IoT cameras connected to 5G networks are installed in the city. Captured drone images are transmitted to the cloud via a high-speed and low-latency 5G network, and machine learning algorithms are used for target detection and tracking. In this study, we propose a method for real-time tracking of drone targets by using the existing monitoring network to obtain drone images in real time and employing deep learning methods by which drones in urban environments can be guided. To achieve real-time tracking of UAV targets, we employed the tracking-by-detection mode in machine learning, with the network-modified YOLOv3 (you only look once v3) as the target detector and Deep SORT as the target tracking correlation algorithm. We established a drone tracking dataset that contains four types of drones and 2800 pictures in different environments. The tracking model we trained achieved 94.4% tracking accuracy in real-time UAV target tracking and a tracking speed of 54 FPS. These results comprehensively demonstrate that our tracking model achieves high-precision real-time UAV target tracking at a reduced cost.

scholarly journals Long-Term Target Tracking of UAVs Based on Kernelized Correlation Filter

Mathematics ◽  
2021 ◽  
Vol 9 (23) ◽  
pp. 3006
Author(s):  
Junqiang Yang ◽  
Wenbing Tang ◽  
Zuohua Ding
Keyword(s):  
Target Tracking ◽  
Template Matching ◽  
Control Method ◽  
Target Position ◽  
Correlation Filter ◽  
Background Information ◽  
The Status ◽  
Tracking Model ◽  
Update Strategy

During the target tracking process of unmanned aerial vehicles (UAVs), the target may disappear from view or be fully occluded by other objects, resulting in tracking failure. Therefore, determining how to identify tracking failure and re-detect the target is the key to the long-term target tracking of UAVs. Kernelized correlation filter (KCF) has been very popular for its satisfactory speed and accuracy since it was proposed. It is very suitable for UAV target tracking systems with high real-time requirements. However, it cannot detect tracking failure, so it is not suitable for long-term target tracking. Based on the above research, we propose an improved KCF to match long-term target tracking requirements. Firstly, we introduce a confidence mechanism to evaluate the target tracking results to determine the status of target tracking. Secondly, the tracking model update strategy is designed to make the model suffer from less background information interference, thereby improving the robustness of the algorithm. Finally, the Normalized Cross Correlation (NCC) template matching is used to make a regional proposal first, and then the tracking model is used for target re-detection. Then, we successfully apply the algorithm to the UAV system. The system uses binocular cameras to estimate the target position accurately, and we design a control method to keep the target in the UAV’s field of view. Our algorithm has achieved the best results in both short-term and long-term evaluations of experiments on tracking benchmarks, which proves that the algorithm is superior to the baseline algorithm and has quite good performance. Outdoor experiments show that the developed UAV system can achieve long-term, autonomous target tracking.

scholarly journals Multi-Sensor Optimization Scheduling for Target Tracking Based on PCRLB and a Novel Intercept Probability Factor

Electronics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 140 ◽  
Author(s):  
Gongguo Xu ◽  
Ce Pang ◽  
Xiusheng Duan ◽  
Ganlin Shan
Keyword(s):  
Target Tracking ◽  
Pso Algorithm ◽  
Sensor Scheduling ◽  
Tracking Accuracy ◽  
Active Sensors ◽  
Intercept Probability ◽  
Multi Target Tracking ◽  
Fast Solution ◽  
Tracking Model ◽  
Set Up

In order to improve the survivability of active sensors, the problem of low probability of intercept (LPI) for a multi-sensor network system is studied in this paper. Two kinds of operational requirements are taken into account, the first of which is to ensure the survivability of sensors and the second is to improve the tracking accuracy of targets as much as possible. Firstly, the sensor tracking model and the posterior Carmér-Rao lower bound (PCRLB) of the target are presented to evaluate the sensor tracking benefits in next time. Then, a novel intercept probability factor (IPF) is proposed for multi-sensor multi-target tracking scenarios. At the basis of PCRLB and IPF, a myopic multi-sensor scheduling model for target tracking is set up to control the intercepted probability of sensors and improve the target tracking accuracy. At last, a fast solution algorithm based on an improved particle swarm optimization (PSO) algorithm is given to obtain the optimal scheduling actions. Simulation of experimental results show that the proposed model can effectively control the intercepted risk of every sensor, which can also obtain better target tracking performance than existing multi-sensor scheduling methods.

scholarly journals Multi-target tracking algorithm in intelligent transportation based on wireless sensor network

Open Physics ◽  
2018 ◽  
Vol 16 (1) ◽  
pp. 1000-1008 ◽  
Author(s):  
Yang Lei ◽  
Yuan Wu ◽  
Ahmad Jalal Khan Chowdhury
Keyword(s):  
Target Tracking ◽  
Information Exchange ◽  
Intelligent Transportation System ◽  
Tracking Error ◽  
Intelligent Transportation ◽  
Tracking Algorithm ◽  
Tracking Accuracy ◽  
Multiple Targets ◽  
Tracking Process ◽  
Multi Target Tracking

Abstract The traditional extended Kalman algorithm for multi-target tracking in the field of intelligent transportation does not consider the occlusion problem of the multi-target tracking process, and has the disadvantage of low multi-target tracking accuracy. A multi-target tracking algorithm using wireless sensors in an intelligent transportation system is proposed. Based on the dynamic clustering structure, the measurement results of each sensor are the superimposed results of sound signals and environmental noise from multiple targets. During the tracking process, each target corresponds to a particle filter. When the target spacing is relatively close to each other, each master node realizes distributed multi-target tracking through information exchange. At the same time, it is also necessary to consider the overlap between adjacent frames. Since the moving target speed is too fast, the target occlusion has the least influence on the tracking accuracy, and can accurately track multiple targets. The experimental results show that the proposed algorithm has a target tracking error of 0.5 m to 1 m, and the tracking result has high precision.

scholarly journals Target tracking accuracy and latency with different 4D ultrasound systems – a robotic phantom study

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Svenja Ipsen ◽  
Sven Böttger ◽  
Holger Schwegmann ◽  
Floris Ernst
Keyword(s):  
Target Tracking ◽  
Real Time ◽  
Template Matching ◽  
Image Data ◽  
Distinct Advantage ◽  
Reference Trajectory ◽  
Data Streaming ◽  
Tracking Accuracy ◽  
Time Data ◽  
4D Ultrasound

AbstractUltrasound (US) imaging, in contrast to other image guidance techniques, offers the distinct advantage of providing volumetric image data in real-time (4D) without using ionizing radiation. The goal of this study was to perform the first quantitative comparison of three different 4D US systems with fast matrix array probes and real-time data streaming regarding their target tracking accuracy and system latency. Sinusoidal motion of varying amplitudes and frequencies was used to simulate breathing motion with a robotic arm and a static US phantom. US volumes and robot positions were acquired online and stored for retrospective analysis. A template matching approach was used for target localization in the US data. Target motion measured in US was compared to the reference trajectory performed by the robot to determine localization accuracy and system latency. Using the robotic setup, all investigated 4D US systems could detect a moving target with sub-millimeter accuracy. However, especially high system latency increased tracking errors substantially and should be compensated with prediction algorithms for respiratory motion compensation.

scholarly journals Spatio-Temporal Context, Correlation Filter and Measurement Estimation Collaboration Based Visual Object Tracking

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2841
Author(s):  
Khizer Mehmood ◽  
Abdul Jalil ◽  
Ahmad Ali ◽  
Baber Khan ◽  
Maria Murad ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Environmental Changes ◽  
Correlation Filter ◽  
Temporal Context ◽  
Visual Object ◽  
Target Model ◽  
Change Of Scale ◽  
Tracking Model ◽  
Spatio Temporal

Despite eminent progress in recent years, various challenges associated with object tracking algorithms such as scale variations, partial or full occlusions, background clutters, illumination variations are still required to be resolved with improved estimation for real-time applications. This paper proposes a robust and fast algorithm for object tracking based on spatio-temporal context (STC). A pyramid representation-based scale correlation filter is incorporated to overcome the STC’s inability on the rapid change of scale of target. It learns appearance induced by variations in the target scale sampled at a different set of scales. During occlusion, most correlation filter trackers start drifting due to the wrong update of samples. To prevent the target model from drift, an occlusion detection and handling mechanism are incorporated. Occlusion is detected from the peak correlation score of the response map. It continuously predicts target location during occlusion and passes it to the STC tracking model. After the successful detection of occlusion, an extended Kalman filter is used for occlusion handling. This decreases the chance of tracking failure as the Kalman filter continuously updates itself and the tracking model. Further improvement to the model is provided by fusion with average peak to correlation energy (APCE) criteria, which automatically update the target model to deal with environmental changes. Extensive calculations on the benchmark datasets indicate the efficacy of the proposed tracking method with state of the art in terms of performance analysis.

An Improved Joint Target Tracking and Classification Algorithm Based on Data Fusion

2014 ◽  
Vol 904 ◽  
pp. 325-329
Author(s):  
Hong Wei Quan ◽  
Lin Chen ◽  
Dong Liang Peng
Keyword(s):  
Data Fusion ◽  
Target Tracking ◽  
Classification Algorithm ◽  
Target Classification ◽  
Tracking Accuracy ◽  
Traditional Methods ◽  
System Models ◽  
Target State ◽  
Classification Probability

This paper addresses the problem of the joint target tracking and classification based on data fusion. In traditional methods, a separate suite of sensors and system models are used, target tracking and target classification are usually treated as separate problems. In our JTC framework, the link between target state and class is considered and the feasibility of JTC techniques is discussed. The tracking accuracy and classification probability are improved to some extent with the more accurate classification results from classifier based on data fusion feedback to state filter.

Sign in / Sign up

Export Citation Format

Share Document