Wen Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Wen Yao has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haiwei Liu
Beijing Jiaotong University
1 shared publication - Hongbin Zha
Peking University
1 shared publication Huijing Zhao
Peking University, Key Laboratory of Machine Perception (MOE), School of Electronics Engineering and Computer Science, Beijing, 100871, China
1 shared publicationLiu Qinghe
School of Automotive Engineering, Harbin Institute of Technology, Weihai, P.R. China
1 shared publication- Nuo Qun
School of Information Science and Technology, Tibet University, Lhasa, Tibet Autonomous Region, China
1 shared publication - Peng Nan
School of Information Science and Technology, Tibet University, China and Collaborative Innovation Center for Tibet informatization by MOE and Tibet Autonomous Region, China
1 shared publication
Latest Publications
- Open Access
- 17 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 379-385
Research on Fine-grained Classification of Scene Images Fused with Multimodality
- 17 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 379-385
Open AccessResearch on Fine-grained Classification of Scene Images Fused with Multimodality
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 561-564
Influence of Different Proportions of CACC and ACC in the Traffic Flow
This paper aims to investigate the influence of different proportions of cooperative adaptive cruise control vehicles and adaptive cruise control vehicles in the traffic flow. A circular road simulation model was designed in Matlab/Simulink, and the vehicle type was determined based on cooperative adaptive cruise controller and adaptive cruise controller. Then the trend in traffic flow, traffic density, and average speed after the introduction of cooperative adaptive cruise controller are analyzed in accordance with the fundamental diagram model of traffic flow. The simulation results show that with the increase of the proportion of cooperative adaptive cruise control vehicles, the average speed of the entire traffic flow has increased significantly. The traffic capacity has been greatly enhanced, and the road capacity has been improved.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 561-564
Influence of Different Proportions of CACC and ACC in the Traffic Flow
This paper aims to investigate the influence of different proportions of cooperative adaptive cruise control vehicles and adaptive cruise control vehicles in the traffic flow. A circular road simulation model was designed in Matlab/Simulink, and the vehicle type was determined based on cooperative adaptive cruise controller and adaptive cruise controller. Then the trend in traffic flow, traffic density, and average speed after the introduction of cooperative adaptive cruise controller are analyzed in accordance with the fundamental diagram model of traffic flow. The simulation results show that with the increase of the proportion of cooperative adaptive cruise control vehicles, the average speed of the entire traffic flow has increased significantly. The traffic capacity has been greatly enhanced, and the road capacity has been improved.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1723-1730
Camera and LiDAR Fusion for On-road Vehicle Tracking with Reinforcement Learning
We formulate camera and LiDAR fusion tracking as a sequential decision-making process. With our deep reinforcement learning framework, we try to optimize the tracking trajectory to be as accurate, smooth, and long as possible. In contrast to traditional fusion algorithms involving complex feature and strategy design and hyperparameters tuned for different scenarios, our fusion agent can learn the confidence of each input by tracking the results from raw observation in a data-driven fashion. Given the input states of different sensors, our approach chooses one input with a higher expected cumulative reward as the observation of a Kalman filter to iteratively predict the target position. The expected cumulative reward is estimated with a convolutional neural network, trained with a modified DQN algorithm, which takes inputs from both LiDAR and a camera. Through case studies and quantitative result evaluation on our dataset from the 4th Ring Road in Beijing, our algorithm is validated to achieve more accurate and robust tracking performance.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1723-1730
Camera and LiDAR Fusion for On-road Vehicle Tracking with Reinforcement Learning
We formulate camera and LiDAR fusion tracking as a sequential decision-making process. With our deep reinforcement learning framework, we try to optimize the tracking trajectory to be as accurate, smooth, and long as possible. In contrast to traditional fusion algorithms involving complex feature and strategy design and hyperparameters tuned for different scenarios, our fusion agent can learn the confidence of each input by tracking the results from raw observation in a data-driven fashion. Given the input states of different sensors, our approach chooses one input with a higher expected cumulative reward as the observation of a Kalman filter to iteratively predict the target position. The expected cumulative reward is estimated with a convolutional neural network, trained with a modified DQN algorithm, which takes inputs from both LiDAR and a camera. Through case studies and quantitative result evaluation on our dataset from the 4th Ring Road in Beijing, our algorithm is validated to achieve more accurate and robust tracking performance.