Multi-sensor Fusion Tracking Algorithm by Square Root Cubature Kalman Filter for Intelligent Vehicle

He, Lin; Wang, Yansong; Shi, Qin; He, Zejia; Wei, Yujiang; Wang, Mingwei

doi:10.1109/cvci54083.2021.9661224

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the KF is limited to accurately estimating linear systems only and is not suitable for nonlinear systems. A multi-sensor fusion tracking algorithm based on the square root cubature Kalman filter (SRCKF) is purposed for nonlinearity of the vehicle target tracking system [30]. In fact, the motion of traffic participants varies in different scenarios; the motion process model match and noise statistics estimation are crucial for accurate state estimation.…”

Section: Background and Previous Workmentioning

confidence: 99%

Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera

Duan

2023

Sensors

View full text Add to dashboard Cite

This study presents a novel multimodal heterogeneous perception cross-fusion framework for intelligent vehicles that combines data from millimeter-wave radar and camera to enhance target tracking accuracy and handle system uncertainties. The framework employs a multimodal interaction strategy to predict target motion more accurately and an improved joint probability data association method to match measurement data with targets. An adaptive root-mean-square cubature Kalman filter is used to estimate the statistical characteristics of noise under complex traffic scenarios with varying process and measurement noise. Experiments conducted on a real vehicle platform demonstrate that the proposed framework improves reliability and robustness in challenging environments. It overcomes the challenges of insufficient data fusion utilization, frequent leakage, and misjudgment of dangerous obstructions around vehicles, and inaccurate prediction of collision risks. The proposed framework has the potential to advance the state of the art in target tracking and perception for intelligent vehicles.

show abstract

Section: Background and Previous Workmentioning

confidence: 99%

Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera

Duan

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…1 , local tracks are automatically generated and processed on each sensor during data measurement in distributed fusion tracking systems. These sensors subsequently transmit their respective track information to the fusion centre for track correlation and fusion ( Lin et al, 2021 ). Each sensor and the fusion centre operate independently in this process with their filters.…”

Section: Introductionmentioning

confidence: 99%

Multi-sensor network tracking research utilizing searchable encryption algorithm in the cloud computing environment

Sun,

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Presently, the focus of target detection is shifting towards the integration of information acquired from multiple sensors. When faced with a vast amount of data from various sensors, ensuring data security during transmission and storage in the cloud becomes a primary concern. Data files can be encrypted and stored in the cloud. When using data, the required data files can be returned through ciphertext retrieval, and then searchable encryption technology can be developed. However, the existing searchable encryption algorithms mainly ignore the data explosion problem in a cloud computing environment. The issue of authorised access under cloud computing has yet to be solved uniformly, resulting in a waste of computing power by data users when processing more and more data. Furthermore, to save computing resources, ECS (encrypted cloud storage) may only return a fragment of results in response to a search query, lacking a practical and universal verification mechanism. Therefore, this article proposes a lightweight, fine-grained searchable encryption scheme tailored to the cloud edge computing environment. We generate ciphertext and search trap gates for terminal devices based on bilinear pairs and introduce access policies to restrict ciphertext search permissions, which improves the efficiency of ciphertext generation and retrieval. This scheme allows for encryption and trapdoor calculation generation on auxiliary terminal devices, with complex calculations carried out on edge devices. The resulting method ensures secure data access, fast search in multi-sensor network tracking, and accelerates computing speed while maintaining data security. Ultimately, experimental comparisons and analyses demonstrate that the proposed method improves data retrieval efficiency by approximately 62%, reduces the storage overhead of the public key, ciphertext index, and verifiable searchable ciphertext by half, and effectively mitigates delays in data transmission and computation processes.

show abstract

A Cluster-Based Distributed State Estimation Method Utilizing Cooperative Target Tracking

Zhu,

Yu,

Dong

et al. 2024

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Multi-sensor Fusion Tracking Algorithm by Square Root Cubature Kalman Filter for Intelligent Vehicle

Cited by 4 publications

References 4 publications

Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera

Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera

Multi-sensor network tracking research utilizing searchable encryption algorithm in the cloud computing environment

A Cluster-Based Distributed State Estimation Method Utilizing Cooperative Target Tracking

Contact Info

Product

Resources

About