A new target tracking filter based on deep learning

Cui, Yaqi; He, Yuehan; Tang, Tiantian; Liu, Yu

doi:10.1016/j.cja.2021.10.023

Cited by 18 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BGGIW is used to approximate newborn intensity and potential target intensity as related in [12]. There are some other tracking methods, such as energy-based auto regressive neural network [17][18], deep learning method [19][20][21][22] and genetic algorithm [23].…”

Section: Related Workmentioning

confidence: 99%

GCI-GGIW-PMBM：An Intelligent Multiple Extended Target Tracking Scheme for Mobile Aquaculture Sensor Networks

Zhu

Peng³

2023

Preprint

View full text Add to dashboard Cite

Poisson multi-Bernoulli Mixture (PMBM) filter, accompanying with its improvements, has been known as an available or practical point and extended multi-target tracking algorithm. This paper presents an improved PMBM scheme carried adaptive detection probability and random birth distributions, coupling with an associated distribution fused scheme for tracking extended multiple targets. Firstly, the augmented state of unknown and changing target detection probability is described by Gamma (GAM) distribution. Then, extended target states are described by Inverse Wishart (IW) distribution on account of the augmented state, besides dynamic states of multiple targets presented by Gaussian distribution. And then, an adaptive newborn distribution is adopted to describe the newborn targets appeared arbitrarily. Consequently, the detailed recursion and closed-form solutions of the proposed filter can be obtained through approximating the intensity of newborn and potential targets to Gamma Gaussian Inverse Wishart (GGIW) pattern. Furthermore, a novel distribution fused scheme Generalized Covariance Intersection (GCI), whose associated states and cardinality are fused by anchors abiding by the respective fused weights, is performed in such an extensive aquaculture tracking sensor system with limited computational and processing capacity. Availability and effectiveness of GCI-GGIW-PMBM filter can be verified by comprehensive simulations. Comparisons with other multiple extended target tracking filters also illustrate that tracking behaviors are improved to a great extent, especially energy efficiency is enhanced largely, and tracking accuracy is relatively improved.

show abstract

Section: Related Workmentioning

confidence: 99%

GCI-GGIW-PMBM：An Intelligent Multiple Extended Target Tracking Scheme for Mobile Aquaculture Sensor Networks

Zhu

Peng³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The literature [11] converts the track association problem into a classification problem in machine learning and designs a new track association algorithm, which mainly consists of three parts: scene embedding network, feature lifting network, and association judgment network. According to the simulation results, the method can effectively improve the correct rate of association, which is a big improvement over the traditional track association algorithm, and it has better adaptability for mixed scenes, which is more beneficial to the application in practice.…”

Section: Improvement Solutionsmentioning

confidence: 99%

Research and development trend of machine learning based track data association algorithm

Zhu

Cai

Cheng

et al. 2023

International Conference on Computer Vision, Application, and Algorithm (CVAA 2022)

View full text Add to dashboard Cite

As the number of the measurement target sensors continues to grow and complicated, and the original track data association algorithm is complexity of the target increases, the process of track association is gradually difficult to meet the actual demand, so it is important to further analyze the multiple target tracking data association algorithm. Machine learning has become a research hotspot in various fields in recent years. In the field of data association, machine learning algorithms can also be used to achieve the processing of track data. Machine learning algorithms can effectively improve the correct association rate compared to traditional methods. Firstly, the basic content of the track data association problem is described; secondly, two common types of research under the multiple target tracking data association problems based on machine learning are analyzed and summarized; after that, the future development trend is predicted given the current research status; finally, the overall research content is summarized.

show abstract

“…For example, deep convolutional neural networks are utilized to extract target features to improve the accuracy and robustness of tracking [21]. However, most studies performed to improve the efficiency and accuracy of moving target retrieval have been based on tracking-by-detection strategies [22][23][24]. The application of topology-related theories and methods has opened up a new path for target tracking research, and many valuable research results have been obtained.…”

Section: Introductionmentioning

confidence: 99%

A Moving Target Tracking Framework Based on a Set and Its Topological Space

et al. 2023

View full text Add to dashboard Cite

Moving target tracking is a technology that matches frames and images based on target characteristics. This technology is widely utilized in intelligent transportation, logistics transportation, public security, sports event broadcasting, and other fields. Existing research focuses primarily on improving target detection and tracking algorithms to improve target retrieval and tracking efficiency. However, the majority of studies focus on global and full-range retrieval. More importantly, in large video scenes with multiple camera collaborations, these methods rarely consider the efficiency of target retrieval and tracking. Based on relevant theories and methods of video GIS, set theory, and topology, in this paper, a set and its topology space covering road networks, cameras, videos, and key frames were constructed. Additionally, the positioning, tracking, and track representation of a moving target based on the set and its topology space were solved. Compared to the feature vector algorithm, video summarization and Meanshift algorithm, the experimental findings reveal that the target retrieval performance, algorithm stability, and robustness are improved.

show abstract

A new target tracking filter based on deep learning

Cited by 18 publications

References 10 publications

GCI-GGIW-PMBM：An Intelligent Multiple Extended Target Tracking Scheme for Mobile Aquaculture Sensor Networks

GCI-GGIW-PMBM：An Intelligent Multiple Extended Target Tracking Scheme for Mobile Aquaculture Sensor Networks

Research and development trend of machine learning based track data association algorithm

A Moving Target Tracking Framework Based on a Set and Its Topological Space

Contact Info

Product

Resources

About