Road-Map Aided GM-PHD Filter for Multivehicle Tracking With Automotive Radar

Shi, Kun; Shi, Zhiguo; Yang, Chaoqun; He, Shibo; Chen, Jiming; An-jun, Chen

doi:10.1109/tii.2021.3073032

Cited by 18 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, clustering techniques are necessary to extract target state estimates. To address these limitations, Vo et al introduced the GM-PHD filter, which analytically propagates weights, means, and covariances using Kalman filtering [16][17][18][19]. For multi-sensor multi-target tracking, Mahler proposed the iterated corrector PHD (IC-PHD) filter [20].…”

Section: Introductionmentioning

confidence: 99%

Gaussian Mixture Probability Hypothesis Density Filter for Heterogeneous Multi-Sensor Registration

Zeng,

Wang,

Wei

et al. 2024

Mathematics

View full text Add to dashboard Cite

Spatial registration is a prerequisite for data fusion. Existing methods primarily focus on similar sensor scenarios and rely on accurate data association assumptions. To address the heterogeneous sensor registration in complex data association scenarios, this paper proposes a Gaussian mixture probability hypothesis density (GM-PHD)-based algorithm for heterogeneous sensor bias registration, accompanied by an adaptive measurement iterative update algorithm. Firstly, by constructing augmented target state motion and measurement models, a closed-form expression for prediction is derived based on Gaussian mixture (GM). In the subsequent update, a two-level Kalman filter is used to achieve an approximate decoupled estimation of the target state and measurement bias, taking into account the coupling between them through pseudo-likelihood. Notably, for heterogeneous sensors that cannot directly use sequential update techniques, sequential updates are first performed on sensors that can obtain complete measurements, followed by filtering updates using extended Kalman filter (EKF) sequential update techniques for incomplete measurements. When there are differences in sensor quality, the GM-PHD fusion filter based on measurement iteration update is sequence-sensitive. Therefore, the optimal subpattern assignment (OSPA) metric is used to optimize the fusion order and enhance registration performance. The proposed algorithms extend the multi-target information-based spatial registration algorithm to heterogeneous sensor scenarios and address the impact of different sensor-filtering orders on registration performance. Our proposed algorithms significantly improve the accuracy of bias estimation compared to the registration algorithm based on significant targets. Under different detection probabilities and clutter intensities, the average root mean square error (RMSE) of distance and angular biases decreased by 11.8% and 8.6%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Gaussian Mixture Probability Hypothesis Density Filter for Heterogeneous Multi-Sensor Registration

Zeng,

Wang,

Wei

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…Wireless sensor networks (WSNs) have become a crucial technology in the proliferation of Internet of Things (IoT) use cases and application scenarios across a wide range of fields. These WSN-based IoT applications include smart industrial monitoring [ 1 ], smart transportation [ 2 ], real-time tracking and mapping [ 3 ], smart agricultural irrigation [ 4 ], smart grids [ 5 ], smart homes and smart buildings [ 6 ], smart cities [ 2 , 7 ], smart exploration [ 8 ], and military reconnaissance [ 9 ], as well as applications related to safety, stability maintenance, surveying, medical, and health [ 10 ]. WSNs are considered a key enabling technology for IoT due to their numerous applications.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Clustering Hierarchical Protocol for Data Collection from Remote Wireless Sensor Networks Based Internet of Things Applications

Shah

Abbas

et al. 2023

Sensors

View full text Add to dashboard Cite

Recently, unmanned aerial vehicles (UAVs) have emerged as a viable solution for data collection from remote Internet of Things (IoT) applications. However, the successful implementation in this regard necessitates the development of a reliable and energy-efficient routing protocol. This paper proposes a reliable and an energy-efficient UAV-assisted clustering hierarchical (EEUCH) protocol designed for remote wireless sensor networks (WSNs) based IoT applications. The proposed EEUCH routing protocol facilitates UAVs to collect data from ground sensor nodes (SNs) that are equipped with wake-up radios (WuRs) and deployed remotely from the base station (BS) in the field of interest (FoI). During each round of the EEUCH protocol, the UAVs arrive at the predefined hovering positions at the FoI, perform clear channel assignment, and broadcast wake-up calls (WuCs) to the SNs. Upon receiving the WuCs by the SNs’ wake-up receivers, the SNs perform carrier sense multiple access/collision avoidance before sending joining requests to ensure reliability and cluster-memberships with the particular UAV whose WuC is received. The cluster-member SNs turn on their main radios (MRs) for data packet transmission. The UAV assigns time division multiple access (TDMA) slots to each of its cluster-member SNs whose joining request is received. Each SN must send the data packets in its assigned TDMA slot. When data packets are successfully received by the UAV, it sends acknowledgments to the SNs, after which the SNs turn off their MRs, completing a single round of the protocol. The proposed EEUCH routing protocol with WuR eliminates the issue of cluster overlapping, improves the overall performance, and increases network stability time by a factor of 8.7. It also improves energy efficiency by a factor of 12.55, resulting in a longer network lifespan compared to Low Energy Adaptive Clustering Hierarchy (LEACH) protocol. Moreover, EEUCH collects 5.05 times more data from the FoI than LEACH. These results are based on simulations in which the EEUCH protocol outperformed the existing six benchmark routing protocols proposed for homogeneous, two-tier, and three-tier heterogeneous WSNs.

show abstract

“…GM-PHD) [18]. Considering the unreliability of SMC-PHD filter clustering technique to extract target [19], we mainly focus on GM-PHD filter which provides a more reliable way for state extraction. In conventional GM-PHD filter, target birth intensity is known a priori, but that is too restrictive for real application because targets may randomly appear at any time and in any position.…”

Section: Introductionmentioning

confidence: 99%

Underwater multi-source DOA tracking using uniform linear array based on improved GM-PHD filter

Zhang

Liang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Uniform linear array (ULA) is commonly used for collecting underwater acoustic signals, and the direction-of-arrival (DOA) is obtained by array signal processing methods. The ULA-based multi-source DOA tracking suffers from the performance degradation caused by the presence of false tracks from port-starboard ambiguity. To address this problem, we propose a bearing ambiguity discrimination algorithm. Firstly, the sum of real bearing motion velocity between truth and ambiguous targets is established with the Gaussian distribution. Secondly, an improved Gaussian mixture probability hypothesis density (GM-PHD) filter, which can adaptively generate target birth intensity, is utilized to select truth and ambiguous bearings generated by the same target from the estimated posterior intensity. Thirdly, truth and ambiguous bearings are discriminated according to the fact that the change of array heading will lead to a significant change in ambiguous bearing. Simulation and real experimental results illustrate that the proposed algorithm can provide unambiguous target-generated tracks and accurately estimate the number of targets.

show abstract

Road-Map Aided GM-PHD Filter for Multivehicle Tracking With Automotive Radar

Cited by 18 publications

References 28 publications

Gaussian Mixture Probability Hypothesis Density Filter for Heterogeneous Multi-Sensor Registration

Gaussian Mixture Probability Hypothesis Density Filter for Heterogeneous Multi-Sensor Registration

An Innovative Clustering Hierarchical Protocol for Data Collection from Remote Wireless Sensor Networks Based Internet of Things Applications

Underwater multi-source DOA tracking using uniform linear array based on improved GM-PHD filter

Contact Info

Product

Resources

About