Trajectory prediction of cyclist based on dynamic Bayesian network and long short-term memory model at unsignalized intersections

Gao, Hongbo; Su, Hang; Cai, Yingfeng; Wu, Renfei; Hao, Zhengyuan; Xu, Yongneng; Wu, Wei; Wang, Jianqing; Li, Zhijun; Kan, Zhen

doi:10.1007/s11432-020-3071-8

Cited by 70 publications

(24 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other algorithms: In order to predict future trajectories, Dynamic Bayesian Networks (DBN) and other models have also begun to be used in some research. Hongbo GAO et al [31] used a fusion algorithm including DBN and LSTM to infer the intention distribution of cyclists at unsignaled intersections. Sinda Rebello et al [37] adopted DBN and HMM to estimate the reliability of the prediction function, but this method can only be used in the case of having recorded system-specific process data or state data.…”

Section: Prediction Algorithmmentioning

confidence: 99%

Intelligent Vehicle Moving Trajectory Prediction Based on Residual Attention Network

Yang

Gao

et al. 2022

WEVJ

View full text Add to dashboard Cite

Skilled drivers have the driving behavioral characteristic of pre-sighted following, and similarly intelligent vehicles need accurate prediction of future trajectories. The LSTM (Long Short-Term Memory) is a common model of trajectory prediction. The existing LSTM models pay less attention to the interactions between the target and the surrounding vehicles. Furthermore, the impacts on future trajectories of the target vehicle have also barely been a focus of the current models. On these bases, a Residual Attention-based Long Short-Term Memory (RA-LSTM) model was proposed, an interaction tensor based on the surroundings of the target vehicle at the predictive moments was constructed and the weight coefficients of the interaction tensor for the surrounding vehicles relative to the target vehicle were calculated and re-programmed in this study. The proposed RA-LSTM model can implicitly represent the different degrees of influence of the surrounding vehicles on the target vehicle; the probability distributions of the future trajectory coordinates of the target vehicle is predicted based on the extracted interaction features. The RA-LSTM model was tested and verified in multiple scenarios by using the NGSIM (next generation simulation) public dataset, and the results showed that the prediction accuracy of the proposed model is significantly improved compared with the current LSTM models.

show abstract

Section: Prediction Algorithmmentioning

confidence: 99%

Intelligent Vehicle Moving Trajectory Prediction Based on Residual Attention Network

Yang

Gao

et al. 2022

WEVJ

View full text Add to dashboard Cite

show abstract

“…The state of the next time step is estimated based on the system model. A vehicle kinematic model with on-board sensor inputs is used for time updates, as depicted in Equation (3).…”

Section: Motion Updatementioning

confidence: 99%

“…Knowing an ego-vehicle's position, which is referred to as vehicle localisation, is indispensable for autonomous driving applications [1,2,3] and adaptive driver assistance systems (ADAS). Accurate localisation can help a navigation system provide more precise routing instructions.…”

Section: Introductionmentioning

confidence: 99%

Ego‐lane index‐aware vehicular localisation using the DeepRoad Network for urban environments

Lee

Choi

Seo

2021

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Accurate real-time localisation is crucial for various autonomous driving applications. Numerous methods for localization, combining various kinds of input such as data from environmental sensors, inertial measurement units, and the Global Positioning System, have been proposed. Given the present state of affairs with regards to map compactness and sensor affordability, lane map-matching-based methods with cameras used as environmental sensors have been widely proposed. In previous methods, however, lanes detected by cameras could falsely correspond to other lanes in a map. This would result in inaccuracies such as a two-lane or three-lane deviation from the actual pose. This paper proposes a localisation method integrating the ego-lane index to avoid lane deviations during lane map matching. A novel ego-lane index identification algorithm and methodology to integrate the ego-lane index information into the lane-based map-matching function is presented. It is demonstrated that incorporating ego-lane index information improves the accuracy of map-matching localisation. The efficacy of our approach in diverse environments, including complex urban scenarios, was successfully demonstrated. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The results showed that too many decomposition levels consumed too much time and memory, and too little decomposition levels could not capture spatial details well. Such methods are mainly applied to infrared images and medical image processing [20][21][22]. Li et al proposed a multi-scale de-fogging fusion method for a single image, in which dark channels, clarity and significant features were used as the weight map for fusion, and multi-scale fusion was carried out from top to bottom through the multi-level pyramid decomposition strategy [23].…”

Section: Introductionmentioning

confidence: 99%

Image fusion algorithm of circular colour correction based on vehicle vision sensors

Kong

Lin

et al. 2022

Cognitive Comp and Systems

View full text Add to dashboard Cite

In order to solve the problems of different visual angles, such as large brightness and colour difference, and obvious image splicing trace, an algorithm of ring image fusion based on colour correction is proposed in this paper. According to the algorithm in this paper, a Matlab toolbox was made for image fusion simulation experiment. Structural similarity (SSIM) was used to evaluate the effectiveness of this method in reducing illumination and contrast difference and the mean value of SSIM was 0.8166. The algorithm is measured in the development board and accelerated by graphic processing unit to achieve the computing efficiency of 18 ms per frame and meet the real-time requirements of the system.

show abstract

Trajectory prediction of cyclist based on dynamic Bayesian network and long short-term memory model at unsignalized intersections

Cited by 70 publications

References 24 publications

Intelligent Vehicle Moving Trajectory Prediction Based on Residual Attention Network

Intelligent Vehicle Moving Trajectory Prediction Based on Residual Attention Network

Ego‐lane index‐aware vehicular localisation using the DeepRoad Network for urban environments

Image fusion algorithm of circular colour correction based on vehicle vision sensors

Contact Info

Product

Resources

About