Improved GM-PHD filter based on threshold separation clusterer for space-based starry-sky background weak point target tracking

Luo, Qingqing; Gao, Zhisheng; Xie, Chunzhi

doi:10.1016/j.dsp.2020.102766

Cited by 13 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The further development of sensors and application of multiple sources has fostered the modernization of the known techniques and algorithms, e.g., JPDA, Joint Probabilistic Data Association [ 15 , 16 , 17 ], as well as inventions of new ones, such as MHT, Multiple Hypothesis Tracker [ 18 , 19 , 20 , 21 , 22 ] or PHD, Probability Hypothesis Density [ 23 , 24 , 25 , 26 ]. With new sensors such as stereo video cameras, tracking smaller objects such as drones and birds has become possible.…”

Section: Background and Related Workmentioning

confidence: 99%

Application of Radar Solutions for the Purpose of Bird Tracking Systems Based on Video Observation

Krenc

Gradolewski²,

Dziak³

et al. 2022

Sensors

View full text Add to dashboard Cite

Wildlife Hazard Management is nowadays a very serious problem, mostly at airports and wind farms. If ignored, it may lead to repercussions in human safety, ecology, and economics. One of the approaches that is widely implemented in small and medium-size airports, as well as on wind turbines is based on a stereo-vision. However, to provide long-term observations allowing the determination of the hot spots of birds’ activity and forecast future events, a robust tracking algorithm is required. The aim of this paper is to review tracking algorithms widely used in Radar Science and assess the possibilities of application of these algorithms for the purpose of tracking birds with a stereo-vision system. We performed a survey-of-related works and simulations determined five state-of-the art algorithms: Kalman Filter, Nearest-Neighbour, Joint-Probabilistic Data Association, and Interacting Multiple Model with the potential for implementation in a stereo-vision system. These algorithms have been implemented and simulated in the proposed case study

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Application of Radar Solutions for the Purpose of Bird Tracking Systems Based on Video Observation

Krenc

Gradolewski²,

Dziak³

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…It can be seen that finding the real target in a dense clutter environment and effectively separating the real target from the wrong Gaussian term are the key to solving the problem. Reference [ 32 ] proposed a threshold separation clustering method. On this basis, this paper proposes a method of clustering Gaussian components of the same label using velocity and distance information and extracting the target state, which can effectively aggregate the real target state and prevent redundant error.…”

Section: Robust Label Gm-phd Filtermentioning

confidence: 99%

“…On this basis, this paper proposes a method of clustering Gaussian components of the same label using velocity and distance information and extracting the target state, which can effectively aggregate the real target state and prevent redundant error. The Gaussian term interferes with the extraction of the target state and can reduce the amount of calculation on the basis of [ 32 ].…”

Section: Robust Label Gm-phd Filtermentioning

confidence: 99%

Label GM-PHD Filter Based on Threshold Separation Clustering

Wang

Zhang

2021

Sensors

View full text Add to dashboard Cite

Gaussian mixture probability hypothesis density (GM-PHD) filtering based on random finite set (RFS) is an effective method to deal with multi-target tracking (MTT). However, the traditional GM-PHD filter cannot form a continuous track in the tracking process, and it is easy to produce a large number of redundant invalid likelihood functions in a dense clutter environment, which reduces the computational efficiency and affects the update result of target probability hypothesis density, resulting in excessive tracking error. Therefore, based on the GM-PHD filter framework, the target state space is extended to a higher dimension. By adding a label set, each Gaussian component is assigned a label, and the label is merged in the pruning and merging step to increase the merging threshold to reduce the Gaussian component generated by dense clutter update, which reduces the computation in the next prediction and update. After pruning and merging, the Gaussian components are further clustered and optimized by threshold separation clustering, thus as to improve the tracking performance of the filter and finally realizing the accurate formation of multi-target tracks in a dense clutter environment. Simulation results show that the proposed algorithm can form a continuous and reliable track in dense clutter environment and has good tracking performance and computational efficiency.

show abstract

“…Accordingly, Mahler implemented a probabilistic hypothesis density (PHD) filter [8] based on the finite set statistics theory (FISST) [9] to handle this problem. Examples of highly sophisticated FISST algorithms are the Cardinalized PHD (CPHD) filter, the Cardinal Balanced Multi-target Multi-Bernoulli (CBMeMBer) filter, and the generalized label multi-Bernoulli (GLMB) filter [10][11][12]. Consequently, their study tracked an unknown number of multiple targets in Poisson false alarms, missed detections, and target emergence, disappearance, and generation.…”

Section: Introductionmentioning

confidence: 99%

RHM-δ-GLMB Tracking Algorithm on the Focal Plane for UAV Cluster Targets

2023

View full text Add to dashboard Cite

This paper offers a new tracking algorithm for clustered targets of focal plane unmanned aerial vehicles (UAVs) by integrating the random hypersurface model (RHM) model into the δ-generalized label multi-Bernoulli (δ-GLMB) filter to guarantee a robust UAV cluster target tracking on such focal planes. We first investigated the infrared imaging features of UAV cluster targets by emphasizing the target imaging size and dispersion. Next, we designed an elliptical RHM-based measurement model to map the measurement, state parameters, scaling factors, and errors to pseudo-measurement "0", followed by establishing a pseudo-measurement equation to reflect the target's extended shape size. Then, in order to enhance measurement estimation accuracy, the RHM model was implemented with the δ-GLMB filter and Gamma-Gaussian mixture, which can perform a real-time estimate of the targets' centroid motion state and extended state. We also used the grid-based fast density-based spatial clustering of applications with noise (DBSCAN) segmentation algorithm to overcome the distance-based segmentation method restrictions for infrared radiation (IR) measurement data and diminish the algorithm's complexity even more in the measurement update. Extensive simulations demonstrated that this algorithm outperformed existing matching filtering algorithms in the target centroid motion and extended states. Our investigations also revealed that the algorithm was less vulnerable to clutter and more adaptive, making it more straightforward to accomplish reliable tracking of UAV cluster targets.

show abstract

Improved GM-PHD filter based on threshold separation clusterer for space-based starry-sky background weak point target tracking

Cited by 13 publications

References 28 publications

Application of Radar Solutions for the Purpose of Bird Tracking Systems Based on Video Observation

Application of Radar Solutions for the Purpose of Bird Tracking Systems Based on Video Observation

Label GM-PHD Filter Based on Threshold Separation Clustering

RHM-δ-GLMB Tracking Algorithm on the Focal Plane for UAV Cluster Targets

Contact Info

Product

Resources

About