World Electric Vehicle Journal

Research

16 pages, 7052 KiB

Open AccessArticle

CCBA-NMS-YD: A Vehicle Pedestrian Detection and Tracking Method Based on Improved YOLOv7 and DeepSort

by Zhenhao Yuan, Zhiwen Wang and Ruonan Zhang

World Electr. Veh. J. 2024, 15(7), 309; https://doi.org/10.3390/wevj15070309 - 14 Jul 2024

Viewed by 218

In this paper, we propose a vehicle pedestrian detection and tracking method based on the improved YOLOv7 and DeepSort algorithms. We aim to improve the quality of vehicle pedestrian detection and tracking, addressing the challenges that current commercially available autonomous driving technologies face [...] Read more.

In this paper, we propose a vehicle pedestrian detection and tracking method based on the improved YOLOv7 and DeepSort algorithms. We aim to improve the quality of vehicle pedestrian detection and tracking, addressing the challenges that current commercially available autonomous driving technologies face in complex and changing road traffic situations. First, the NMS (non-maximum suppression) algorithm in YOLOv7 is replaced with a modified Soft-NMS algorithm to ensure that targets can be accurately detected at high densities, and second, the CCBA (coordinate channel attention module) attention mechanism is incorporated to improve the feature extraction and perception capabilities of the network. Finally, a multi-scale feature network is introduced to extract features of small targets more accurately. Finally, the MobileNetV3 lightweight module is introduced into the feature extraction network of DeepSort, which not only reduces the number of model parameters and network complexity, but also improves the tracking performance of the target. The experimental results show that the improved YOLOv7 algorithm improves the average detection accuracy by 3.77% compared to that of the original algorithm; on the MOT20 dataset, the refined DeepSort model achieves a 1.6% increase in MOTA and a 1.9% improvement in MOTP; in addition, the model volume is one-eighth of the original algorithm. In summary, our model is able to achieve the desired real-time and accuracy, which is more suitable for autonomous driving. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

19 pages, 2500 KiB

Open AccessArticle

Real-Time Multimodal 3D Object Detection with Transformers

by Hengsong Liu and Tongle Duan

World Electr. Veh. J. 2024, 15(7), 307; https://doi.org/10.3390/wevj15070307 - 12 Jul 2024

Viewed by 305

Abstract

The accuracy and real-time performance of 3D object detection are key factors limiting its widespread application. While cameras capture detailed color and texture features, they lack depth information compared to LiDAR. Multimodal detection combining both can improve results but incurs significant computational overhead, [...] Read more.

The accuracy and real-time performance of 3D object detection are key factors limiting its widespread application. While cameras capture detailed color and texture features, they lack depth information compared to LiDAR. Multimodal detection combining both can improve results but incurs significant computational overhead, affecting real-time performance. To address these challenges, this paper presents a real-time multimodal fusion model called Fast Transfusion that combines the benefits of LiDAR and camera sensors and reduces the computational burden of their fusion. Specifically, our Fast Transfusion method uses QConv (Quick Convolution) to replace the convolutional backbones compared to other models. QConv concentrates the convolution operations at the feature map center, where the most information resides, to expedite inference. It also utilizes deformable convolution to better match the actual shapes of detected objects, enhancing accuracy. And the model incorporates EH Decoder (Efficient and Hybrid Decoder) which decouples multiscale fusion into intra-scale interaction and cross-scale fusion, efficiently decoding and integrating features extracted from multimodal data. Furthermore, our proposed semi-dynamic query selection refines the initialization of object queries. On the KITTI 3D object detection dataset, our proposed approach reduced the inference time by 36 ms and improved 3D AP by 1.81% compared to state-of-the-art methods. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

15 pages, 2393 KiB

Open AccessArticle

Experimental Study on Structure Optimization and Dynamic Characteristics of Articulated Steering for Hydrogen Fuel Cell Engineering Vehicles

by Qinguo Zhang, Xiaoyang Wang, Zheming Tong, Zhewu Cheng and Xiaojian Liu

World Electr. Veh. J. 2024, 15(7), 306; https://doi.org/10.3390/wevj15070306 - 12 Jul 2024

Viewed by 298

Abstract

The prominent problem of articulated steering structure of engineering vehicle is that there is pressure oscillation in the hydraulic system during steering, which seriously affects the performance of steering system. To solve this problem, the maximum stroke difference of left and right cylinders [...] Read more.

The prominent problem of articulated steering structure of engineering vehicle is that there is pressure oscillation in the hydraulic system during steering, which seriously affects the performance of steering system. To solve this problem, the maximum stroke difference of left and right cylinders and the minimum maximum cylinder pressure are the optimization objectives, and the position of cylinder hinge point is the design variable. The multi-objective optimization design of articulated steering system is carried out by using the particle swarm optimization algorithm. After optimization, the maximum pressure of the steering system is reduced by 13.5%, and the oscillation amplitude is reduced by 16%, so the optimization effect is obvious. The dynamic characteristics of the hydraulic steering system under different loads, such as pressure and flow rate, are obtained through field steering tests of wheel loaders. The results show that the load has an important effect on the pressure response of the system, and the causes and influencing factors of pressure and flow fluctuation are determined. The relationship between mileage and hydrogen consumption is obtained, which provides data support for vehicle control strategy. The high-pressure overflow power consumption accounts for 60% of the total work, and the work lost on the steering gear reaches 36 kJ. The test results verify the rationality and correctness of the optimization method of steering mechanism and provide data support for the improvement in steering hydraulic system. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

24 pages, 13355 KiB

Open AccessArticle

Enhanced Object Detection in Autonomous Vehicles through LiDAR—Camera Sensor Fusion

by Zhongmou Dai, Zhiwei Guan, Qiang Chen, Yi Xu and Fengyi Sun

World Electr. Veh. J. 2024, 15(7), 297; https://doi.org/10.3390/wevj15070297 - 3 Jul 2024

Viewed by 609

Abstract

To realize accurate environment perception, which is the technological key to enabling autonomous vehicles to interact with their external environments, it is primarily necessary to solve the issues of object detection and tracking in the vehicle-movement process. Multi-sensor fusion has become an essential [...] Read more.

To realize accurate environment perception, which is the technological key to enabling autonomous vehicles to interact with their external environments, it is primarily necessary to solve the issues of object detection and tracking in the vehicle-movement process. Multi-sensor fusion has become an essential process in efforts to overcome the shortcomings of individual sensor types and improve the efficiency and reliability of autonomous vehicles. This paper puts forward moving object detection and tracking methods based on LiDAR—camera fusion. Operating based on the calibration of the camera and LiDAR technology, this paper uses YOLO and PointPillars network models to perform object detection based on image and point cloud data. Then, a target box intersection-over-union (IoU) matching strategy, based on center-point distance probability and the improved Dempster–Shafer (D–S) theory, is used to perform class confidence fusion to obtain the final fusion detection result. In the process of moving object tracking, the DeepSORT algorithm is improved to address the issue of identity switching resulting from dynamic objects re-emerging after occlusion. An unscented Kalman filter is utilized to accurately predict the motion state of nonlinear objects, and object motion information is added to the IoU matching module to improve the matching accuracy in the data association process. Through self-collected data verification, the performances of fusion detection and tracking are judged to be significantly better than those of a single sensor. The evaluation indexes of the improved DeepSORT algorithm are 66% for MOTA and 79% for MOTP, which are, respectively, 10% and 5% higher than those of the original DeepSORT algorithm. The improved DeepSORT algorithm effectively solves the problem of tracking instability caused by the occlusion of moving objects. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

26 pages, 3589 KiB

Open AccessArticle

Joint Estimation of Driving State and Road Surface Adhesion Coefficient of a Four-Wheel Independent and Steering-Drive Electric Vehicle

by Zhixin Chen, Gang Li, Zhihua Zhang and Ruolan Fan

World Electr. Veh. J. 2024, 15(6), 249; https://doi.org/10.3390/wevj15060249 - 7 Jun 2024

Viewed by 500

Abstract

Vehicle running state parameters and road surface state are crucial to the stability of four-wheel independent drive and steering electric vehicle control. Therefore, this study explores the estimation of vehicle driving state parameters and road surface adhesion coefficients using a combination of federal [...] Read more.

Vehicle running state parameters and road surface state are crucial to the stability of four-wheel independent drive and steering electric vehicle control. Therefore, this study explores the estimation of vehicle driving state parameters and road surface adhesion coefficients using a combination of federal Kalman filtering and an intelligent bionic antlion optimization algorithm. Firstly, according to the research purpose of the paper and the focus on the accuracy of the establishment of the three degrees of freedom dynamics model, fully considering the road conditions, the paper adopts the Dugoff tire model and finally completes the establishment of the vehicle state estimation model. Secondly, the drive state estimation algorithm is developed utilizing the principles of federal Kalman filtering and volume Kalman filtering. At the same time, robust estimation theory is introduced into the sub-filter, and the antlion optimization module is designed at the lower layer of the main filter to enhance the accuracy of estimates. It is easy to see that the design of the Antlion federal Kalman travel state estimation algorithm has noticeably enhanced accuracy and traceability, according to the result. Thirdly, a joint estimation algorithm of state estimation and road surface adhesion coefficient has been devised to enhance the stability and precision of the estimation process. Finally, the results showed that the joint estimation algorithm has high accuracy in estimating vehicle driving state parameters such as the center of mass lateral deflection angle and road surface adhesion coefficient by simulation. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

11 pages, 1299 KiB

Open AccessEditor’s ChoiceArticle

Vehicle Dynamics in Electric Cars Development Using MSC Adams and Artificial Neural Network

by Santiago J. Cachumba-Suquillo, Mariel Alfaro-Ponce, Sergio G. Torres-Cedillo, Jacinto Cortés-Pérez and Moises Jimenez-Martinez

World Electr. Veh. J. 2023, 14(10), 293; https://doi.org/10.3390/wevj14100293 - 15 Oct 2023

Viewed by 2416

Abstract

Recently, there has been renewed interest in lightweight structures; however, a small structure change can strongly affect vehicle dynamic behavior. Therefore, this study provides new insights into non-parametric modeling based on artificial neural networks (ANNs). This work is then motivated by the requirement [...] Read more.

Recently, there has been renewed interest in lightweight structures; however, a small structure change can strongly affect vehicle dynamic behavior. Therefore, this study provides new insights into non-parametric modeling based on artificial neural networks (ANNs). This work is then motivated by the requirement for a reliable substitute for virtual instrumentation in electric car development to enable the prediction of the current value of the vehicle slip from a given time history of the vehicle (input) and previous values of synthetic data (feedback). The training data are generated from a multi-body simulation using MSC Adams Car; the simulation involves a double lane-change maneuver. This test is commonly used to evaluate vehicle stability. Based on dynamic considerations, this study implements the nonlinear autoregressive exogenous (NARX) identification scheme used in time-series modeling. This work presents an ANN that is able to predict the side slip angle from simulated training data generated employing MSC Adams Car. This work is a specific solution to overtake maneuvers, avoiding the loss of vehicle control and increasing driving safety. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

17 pages, 3324 KiB

Open AccessArticle

Active Control for an Electric Vehicle with an Observer for Torque Energy-Saving

by Juan Miguel González-López, Sergio Sandoval Pérez, Ramón O. Jiménez Betancourt and Gilberto Barreto

World Electr. Veh. J. 2023, 14(10), 288; https://doi.org/10.3390/wevj14100288 - 10 Oct 2023

Viewed by 1508

Abstract

Vehicle dynamics play an important role in determining a vehicle’s stability. It is necessary to identify and obtain models related to vehicle dynamics to evaluate the performance of electric vehicles, as well as how to control them. This paper presents fundamentals of vehicle [...] Read more.

Vehicle dynamics play an important role in determining a vehicle’s stability. It is necessary to identify and obtain models related to vehicle dynamics to evaluate the performance of electric vehicles, as well as how to control them. This paper presents fundamentals of vehicle dynamics, proposing a three-degree-of-freedom nonlinear observer and controller to control lateral velocity and tire torque in comparison to a PID control, while also utilizing a Lyapunov function to determine the stability of the controlled state feedback system concerning the observer, which estimates state errors. This work demonstrates the mathematical development of estimations that will be fed into the algorithms of two active nonlinear controls (state feedback and PID), utilizing the results from Matlab-Simulink simulations of tire torque, lateral and angular velocities based on longitudinal velocity measurements, and employing dynamic gains, such as response to a steering maneuver by the driver following the international standards ISO 7401/2011 and ISO 3888-2. It is concluded that the observer is robust and exhibits energy-saving efficiency in tire torque, even under conditions of variable tire-ground friction. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

14 pages, 3473 KiB

Open AccessArticle

An FPGA-Based Hardware Low-Cost, Low-Consumption Target-Recognition and Sorting System

by Yulu Wang, Yi Han, Jun Chen, Zhou Wang and Yi Zhong

World Electr. Veh. J. 2023, 14(9), 245; https://doi.org/10.3390/wevj14090245 - 4 Sep 2023

Cited by 2 | Viewed by 1721

Abstract

In autonomous driving systems, high-speed and real-time image processing, along with object recognition, are crucial technologies. This paper builds upon the research achievements in industrial item-sorting systems and proposes an object-recognition and sorting system for autonomous driving. In industrial sorting lines, goods-sorting robots [...] Read more.

In autonomous driving systems, high-speed and real-time image processing, along with object recognition, are crucial technologies. This paper builds upon the research achievements in industrial item-sorting systems and proposes an object-recognition and sorting system for autonomous driving. In industrial sorting lines, goods-sorting robots often need to work at high speeds to efficiently sort large volumes of items. This poses a challenge to the robot’s real-time vision and sorting capabilities, making it both practical and economically viable to implement a real-time and low-cost sorting system in a real-world industrial sorting line. Existing sorting systems have limitations such as high cost, high computing resource consumption, and high power consumption. These issues mean that existing sorting systems are typically used only in large industrial plants. In this paper, we design a high-speed, low-cost, low-resource-consumption FPGA (Field-Programmable Gate Array)-based item-sorting system that achieves similar performance to current mainstream sorting systems but at a lower cost and consumption. The recognition component employs a morphological-recognition method, which segments the image using a frame difference algorithm and then extracts the color and shape features of the items. To handle sorting, a six-degrees-of-freedom robotic arm is introduced into the sorting segment. The improved cubic B-spline interpolation algorithm is employed to plan the motion trajectory and consequently control the robotic arm to execute the corresponding actions. Through a series of experiments, this system achieves an average recognition delay of 25.26 ms, ensures smooth operation of the gripping motion trajectory, minimizes resource consumption, and reduces implementation costs. Full article

(This article belongs to the Special Issue Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advanced Vehicle Dynamics Identification, Control and Observer Methods for Autonomous, Electrified Vehicles

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI