原文传递
A Lane Assessment Method Using Visual Information Based on a Dynamic Bayesian Network
| 题名： | A Lane Assessment Method Using Visual Information Based on a Dynamic Bayesian Network |
| 其他题名： | Althoff,M.,Stursberg,O.,&Buss,M.(2009,3–5 June).Safety assessment of driving behavior in multi-lane traffic for autonomous vehicles.Proceedings of IEEE Intelligent Vehicles Symposium,Xian,China. |
| 正文语种： | 英文 |
| 作者： | VOICHITA POPESCU |
| 关键词： | Bayesian Network;High-Level Situation Assessment;Temporal Filtering;Visual Evidence |
| 摘要： | The perception and the interpretation of the vehicle's surrounding are the core modules in any advanced driving assistance system, and the first two stages of every autonomous driving solution. The purpose of the perception stage is to assess the state of the relevant objects (objects' positions, shape, class, orientation, speed) using the primary sensorial information. The purpose of the interpretation stage is to use the objects assessment in order to achieve situation assessment, that is, identification of the instantaneous relations between the traffic environment elements as well as their evolution in time. The work presented in this article lies within the interpretation layer; our aim is to identify on which of the road's lanes is the ego-vehicle currently traveling. We refer to the own vehicle as the ego-vehicle and to its current driving lane as the ego-lane. The ego-vehicle is equipped with a stereovision perception system, and the proposed solution is to identify the ego-lane number by matching the visually detected lane landmarks with the corresponding map landmarks, available from an original extended digital map. Additionally, the visually detected vehicles are used for egolane number identification. The proposed solution is a probabilistic one, in the form of a Bayesian network, which uses as evidence the visual cues provided by the stereovision perception system. In order to incorporate the dynamic nature of the problem, a temporal dimension was added to the network, resulting in a dynamic Bayesian model. Experimental results illustrate the efficiency of the proposed method in complex situations, and the improved efficiency of the dynamic approach over the static one. |
| 出版年： | 2015 |
| 论文唯一标识： | J-96Y2015V19N03002 |
| doi： | 10.1080/15472450.2013.856724 |
| 期刊名称： | Journal of Intelligent Transportation Systems Technology Planning and Operations |
| 拼音刊名(出版物代码)： | J-96 |
| 卷： | 19 |
| 期： | 03 |
| 页码： | 225-239 |
相关文献
- Bayesian Modeling Approach for Forecast of Structural Stress Response Using Structural Health Monitoring Data
- Optimizing multi-agent based urban traffic signal control system
- Bayesian Operational Modal Analysis with Interactive Optimization for Model Updating of Large-Size UHV Transmission Towers
- Bayesian Model Updating for Structural Dynamic Applications Combing Differential Evolution Adaptive Metropolis and Kriging Model
- Lane Selection Model Based on Phase-Field Coupling and Set Pair Logic
- Cycle-Based Estimation on Lane-Level Queue Length at Isolated Signalized Intersection Using License Plate Recognition Data
检索历史
应用推荐
