Xu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xu Zhang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chuanxue Song
College of Automotive Engineering, Jilin University, Changchun 130022, China
4 shared publications - Feng Xiao
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China
4 shared publications - Jingwei Cao
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China
4 shared publications - Shixin Song
School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130022, China
3 shared publications - Da Wang
Jilin University
2 shared publications - Silun Peng
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China
2 shared publications
Latest Publications
- Open Access
- 14 August 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (16) , 3234
Robust Object Tracking Algorithm for Autonomous Vehicles in Complex Scenes
Object tracking is an essential aspect of environmental perception technology for autonomous vehicles. The existing object tracking algorithms can only be applied well to simple scenes. When the scenes become complex, the algorithms have poor tracking performance and insufficient robustness, and the problems of tracking drift and object loss are prone to occur. Therefore, a robust object tracking algorithm for autonomous vehicles in complex scenes is proposed. Firstly, we study the Siam-FC network and related algorithms, and analyze the problems that need to be addressed in object tracking. Secondly, the construction of a double-template Siamese network model based on multi-feature fusion is described, as is the use of the improved MobileNet V2 as the feature extraction backbone network, and the attention mechanism and template online update mechanism are introduced. Finally, relevant experiments were carried out based on public datasets and actual driving videos, with the aim of fully testing the tracking performance of the proposed algorithm on different objects in a variety of complex scenes. The results showed that, compared with other algorithms, the proposed algorithm had high tracking accuracy and speed, demonstrated stronger robustness and anti-interference abilities, and could still accurately track the object in real time without the introduction of complex structures. This algorithm can be effectively applied in intelligent vehicle driving assistance, and it will help to promote the further development and improvement of computer vision technology in the field of environmental perception.
- 14 August 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (16) , 3234
Open AccessRobust Object Tracking Algorithm for Autonomous Vehicles in Complex Scenes
Object tracking is an essential aspect of environmental perception technology for autonomous vehicles. The existing object tracking algorithms can only be applied well to simple scenes. When the scenes become complex, the algorithms have poor tracking performance and insufficient robustness, and the problems of tracking drift and object loss are prone to occur. Therefore, a robust object tracking algorithm for autonomous vehicles in complex scenes is proposed. Firstly, we study the Siam-FC network and related algorithms, and analyze the problems that need to be addressed in object tracking. Secondly, the construction of a double-template Siamese network model based on multi-feature fusion is described, as is the use of the improved MobileNet V2 as the feature extraction backbone network, and the attention mechanism and template online update mechanism are introduced. Finally, relevant experiments were carried out based on public datasets and actual driving videos, with the aim of fully testing the tracking performance of the proposed algorithm on different objects in a variety of complex scenes. The results showed that, compared with other algorithms, the proposed algorithm had high tracking accuracy and speed, demonstrated stronger robustness and anti-interference abilities, and could still accurately track the object in real time without the introduction of complex structures. This algorithm can be effectively applied in intelligent vehicle driving assistance, and it will help to promote the further development and improvement of computer vision technology in the field of environmental perception.
- Open Access
- 8 November 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21) , 7923
Stability Control for Vehicle Dynamic Management with Multi-Objective Fuzzy Continuous Damping Control
Vehicle dynamic management (VDM) is a vehicle chassis integrated control system based on electronic stability program (ESP) and continuous damping control (CDC) that has been developed in recent years. In this work, the ideal yaw angle rate and sideslip angle of the mass center are calculated deriving an ideal monorail model with two degrees of freedom. Then, a direct yaw moment proportional-integral-differential control strategy for ESP is proposed as the foundation of VDM. In addition, a multi-objective fuzzy continuous damping control (MFCDC) is proposed to achieve comfort, handling stability, and rollover prevention. The effect of the MFCDC strategy is analyzed and verified through a sine wave steer input test, double line change test, and fishhook test. The results indicate that MFCDC-ESP has a significant advantage in preventing rollover. MFCDC-ESP can maintain the optimized distribution of damping force through its own compensation under possible instability and predict the critical stable state to some extent. MFCDC-ESP exhibits strong real-time sensitivity to the control state of the damping force of each wheel. Hence, it can ensure the comfort of passengers under good driving conditions and exert strong adaptability and control effects under extreme working conditions.
- 8 November 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21) , 7923
Open AccessStability Control for Vehicle Dynamic Management with Multi-Objective Fuzzy Continuous Damping Control
Vehicle dynamic management (VDM) is a vehicle chassis integrated control system based on electronic stability program (ESP) and continuous damping control (CDC) that has been developed in recent years. In this work, the ideal yaw angle rate and sideslip angle of the mass center are calculated deriving an ideal monorail model with two degrees of freedom. Then, a direct yaw moment proportional-integral-differential control strategy for ESP is proposed as the foundation of VDM. In addition, a multi-objective fuzzy continuous damping control (MFCDC) is proposed to achieve comfort, handling stability, and rollover prevention. The effect of the MFCDC strategy is analyzed and verified through a sine wave steer input test, double line change test, and fishhook test. The results indicate that MFCDC-ESP has a significant advantage in preventing rollover. MFCDC-ESP can maintain the optimized distribution of damping force through its own compensation under possible instability and predict the critical stable state to some extent. MFCDC-ESP exhibits strong real-time sensitivity to the control state of the damping force of each wheel. Hence, it can ensure the comfort of passengers under good driving conditions and exert strong adaptability and control effects under extreme working conditions.
- Open Access
- 16 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (20) , 7230
Continuous Damping Control for Rollover Prevention with Optimal Distribution Strategy of Damping Force
Vehicle rollover has always been a highly dangerous condition that can cause severe traffic casualties. In this work, a 14-degree-of-freedom vehicle model in MATLAB/Simulink is constructed with the vehicle suspension system dynamics. The validity of the model is verified by comparing with the CarSim model. Then an optimal distribution of damping force strategy with continuous damping control is proposed by combining the traditional lateral load transfer ratio control with optimized equations of suspension damping force. The damping force compensation of the left and right sides is the core of the optimal distribution of damping force strategy. The effectiveness and optimization effect of the optimal distribution of damping force strategy is proved by the simulation results under the fishhook and crosswind tests. The result shows that continuous damping control has evident control effects on vehicle rollover compared with passive suspension. The optimal distribution of the damping force strategy with continuous damping control has a great better performance than traditional continuous damping control, and it provides a certain assistance to vehicle handling stability.
- 16 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (20) , 7230
Open AccessContinuous Damping Control for Rollover Prevention with Optimal Distribution Strategy of Damping Force
Vehicle rollover has always been a highly dangerous condition that can cause severe traffic casualties. In this work, a 14-degree-of-freedom vehicle model in MATLAB/Simulink is constructed with the vehicle suspension system dynamics. The validity of the model is verified by comparing with the CarSim model. Then an optimal distribution of damping force strategy with continuous damping control is proposed by combining the traditional lateral load transfer ratio control with optimized equations of suspension damping force. The damping force compensation of the left and right sides is the core of the optimal distribution of damping force strategy. The effectiveness and optimization effect of the optimal distribution of damping force strategy is proved by the simulation results under the fishhook and crosswind tests. The result shows that continuous damping control has evident control effects on vehicle rollover compared with passive suspension. The optimal distribution of the damping force strategy with continuous damping control has a great better performance than traditional continuous damping control, and it provides a certain assistance to vehicle handling stability.
- Open Access
Pedestrian Detection Algorithm for Intelligent Vehicles in Complex Scenarios
Pedestrian detection is an important aspect of the development of intelligent vehicles. To address problems in which traditional pedestrian detection is susceptible to environmental factors and are unable to meet the requirements of accuracy in real time, this study proposes a pedestrian detection algorithm for intelligent vehicles in complex scenarios. YOLOv3 is one of the deep learning-based object detection algorithms with good performance at present. In this article, the basic principle of YOLOv3 is elaborated and analyzed firstly to determine its limitations in pedestrian detection. Then, on the basis of the original YOLOv3 network model, many improvements are made, including modifying grid cell size, adopting improved k-means clustering algorithm, improving multi-scale bounding box prediction based on receptive field, and using Soft-NMS algorithm. Finally, based on INRIA person and PASCAL VOC 2012 datasets, pedestrian detection experiments are conducted to test the performance of the algorithm in various complex scenarios. The experimental results show that the mean Average Precision (mAP) value reaches 90.42%, and the average processing time of each frame is 9.6 ms. Compared with other detection algorithms, the proposed algorithm exhibits accuracy and real-time performance together, good robustness and anti-interference ability in complex scenarios, strong generalization ability, high network stability, and detection accuracy and detection speed have been markedly improved. Such improvements are significant in protecting the road safety of pedestrians and reducing traffic accidents, and are conducive to ensuring the steady development of the technological level of intelligent vehicle driving assistance.
Open AccessPedestrian Detection Algorithm for Intelligent Vehicles in Complex Scenarios
Pedestrian detection is an important aspect of the development of intelligent vehicles. To address problems in which traditional pedestrian detection is susceptible to environmental factors and are unable to meet the requirements of accuracy in real time, this study proposes a pedestrian detection algorithm for intelligent vehicles in complex scenarios. YOLOv3 is one of the deep learning-based object detection algorithms with good performance at present. In this article, the basic principle of YOLOv3 is elaborated and analyzed firstly to determine its limitations in pedestrian detection. Then, on the basis of the original YOLOv3 network model, many improvements are made, including modifying grid cell size, adopting improved k-means clustering algorithm, improving multi-scale bounding box prediction based on receptive field, and using Soft-NMS algorithm. Finally, based on INRIA person and PASCAL VOC 2012 datasets, pedestrian detection experiments are conducted to test the performance of the algorithm in various complex scenarios. The experimental results show that the mean Average Precision (mAP) value reaches 90.42%, and the average processing time of each frame is 9.6 ms. Compared with other detection algorithms, the proposed algorithm exhibits accuracy and real-time performance together, good robustness and anti-interference ability in complex scenarios, strong generalization ability, high network stability, and detection accuracy and detection speed have been markedly improved. Such improvements are significant in protecting the road safety of pedestrians and reducing traffic accidents, and are conducive to ensuring the steady development of the technological level of intelligent vehicle driving assistance.