Search Results

High-speed vehicles in low illumination environments severely blur the images used in object detectors, which poses a potential threat to object detector-based advanced driver assistance systems (ADAS) and autonomous driving systems. Augmenting the training images for object detectors is an efficient way to mitigate the threat from motion blur. However, little attention has been paid to the motion of the vehicle and the position of objects in the traffic scene, which limits the consistence between the resulting augmented images and traffic scenes. In this paper, we present a vehicle kinematics-based image augmentation algorithm by modeling and analyzing the traffic scenes to generate more realistic augmented images and achieve higher robustness improvement on object detectors against motion blur. Firstly, we propose a traffic scene model considering vehicle motion and the relationship between the vehicle and the object in the traffic scene.

In order to avoid the influence of the change of the camera pitch angle and the variation of the height of the ground on the ranging accuracy, improve the real-time performance of the algorithm by substituting the current widely-used monocular vision ranging algorithm which builds the optical model based on the shadow of the vehicle floor and the lane line, as well as avoid the classification of vehicle detection, a vehicle distance measurement algorithm based on monocular vision and license plate width is established. Firstly, the target image acquisition and preprocessing are studied. Then the paper studies the license plate image location segmentation method based on accelerated template matching. On this basis, the algorithm for obtaining the ratio of license plate width to image width is studied, and the function of vehicle distance and license plate ratio width is established.

Highly accurate parking slot detection methods are crucial for Automated Valet Parking (AVP) systems, to meet their demanding safety and functional requirements. While previous efforts have mostly focused on the algorithms’ capabilities to detect different types of slots under varying conditions, i.e. the detection rate, their accuracy has received little attention at this time. This paper highlights the importance of trustworthy slot detection methods, which address both the detection rate and the detection accuracy. To achieve this goal, an accurate slot detection method and a reliable ground-truth slot measurement method have been proposed in this paper. First, based on a 2D laser range finder, datapoints of obstacle vehicles on both sides of a slot have been collected and preprocessed. Second, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm has been improved to efficiently cluster these unevenly-distributed datapoints.

Centrifugal Pendulum Vibration Absorber (CPVA for short) is used to absorb torsional vibrations caused by the shifting motion of the engine. It is increasingly used in modern powertrains. In the research of the dynamic characteristics of the CPVA, it is necessary to obtain the real motion of the pendulum to compensate the fitting performance of mathematical model. The usual method is to install an angle sensor to measure the movement of the pendulum. On the one hand, the installation of the sensor will affect its movement to a certain extent, so that the measurement results do not match the actual motion. On the other hand, the motion of the pendulum is not only the rotational motion around the rotational axis of the CPVA rotor, but also has translation relative to it. As a result, it is difficult to obtain accurate motion only by the angle sensor. We proposed a non-contact centrifugal pendulum motion measurement method.

During the launch of a car, severe torsional vibration sometimes may occur in its driveline due to somewhat the slipping of the clutch, its intuitive sense for an occupant is the longitudinal vibration of the vehicle, referred to as the launch shudder whose characteristic frequency is from 5 to 25 Hz generally. As the main vibration sources of the driveline and its crucial nonlinear components, the variable stiffness and backlash of the gear meshing are considered, their impacts on the launch shudder are analyzed in this paper. Conformal mapping, finite element method and regression method etc. are the main approaches to calculate the variable meshing stiffness of a gear pair. If this stiffness is get, it can usually be substituted for its approximate analytical expression, just with finite harmonic terms, in Fourier Series form into Ordinary Differential Equations(ODEs) to calculate the vehicle responses with its nonlinearity considered.

In order to explore approaches for improving object detection accuracy in intelligent vehicle system, we exploit super-resolution techniques. A novel method is proposed to confirm the conjecture whether some popular super-resolution networks used for environmental perception of intelligent vehicles and robots can indeed improve the detection accuracy. COCO dataset which contains images from complex ordinary environment is utilized for the verification experiment, due to it can adequately verify the generalization of each algorithm and the consistency of experimental results. Using two representative object detection networks to produce the detection results, namely Faster R-CNN and YOLOv3, we devise to reduce the impact of resizing operation. The two networks allow us to compare the performance of object detection between using original and super-resolved images. We quantify the effect of each super-resolution techniques as well.

Smart electric vehicles need more accurate and more timely information as well as control than traditional vehicles, which depends on great environmental sensors such as millimeter-wave radar. In this way, the electromagnetic compatibility of whole vehicle would confront more serious challenges because of its high frequency range. Thus, this paper studies the electromagnetic distribution and electromagnetic interference suppression of smart electric vehicles with the followings. Firstly, the millimeter wave radar is modeled and optimized. Micro strip patch antenna, with small size, light mass and low cost, is used as array element of antenna. Millimeter wave radar is modeled and simulated step by step from array element to line array to planar matrix. Then the Cross Shape - Uniplanar Compact - Electromagnetic Band Gap (CS-UC-EBG) structure is deployed to optimize its electromagnetic characteristics, based on finite time domain difference model theory.

Electromagnetic compatibility of electric vehicles is withstanding great challenges because of multiple ECU and actuators distributed in vehicle. At present, researches on electromagnetic characteristics of vehicle mainly focus on rectification based on the EMC experiment, which take much time and energy. Thus, this paper adopts the way of computer simulation studying the electromagnetism model and electromagnetic characteristics of electric vehicle with following procedure. Firstly, the equivalent model of wiring harness was deduced and built. Harnesses were divided into different groups according to terminal reflection property. The equivalent unit parameter matrix was calculated to build the equivalent wiring harness. The crosstalk and radiation cases were set to check the equivalent harness method.

From the perspective of the three elements of electromagnetic interference, the main function of shielding is to cut off the propagation path of electromagnetic noise. The battery pack casing can be regarded as shielding the electromagnetic interference conducted on its internal and external wiring harnesses, but because the battery pack casing has power lines in and out, the battery pack casing is an incomplete shield. In the field of electromagnetics, shielding can be divided into electrical shielding, magnetic shielding and electromagnetic shielding. Therefore, this paper studies its influence on the electromagnetic radiation emission of the whole vehicle from the perspective of shielding mechanism. Due to the role of the switch components in the power battery system, strong current fluctuation di/dt and voltage fluctuation dv/dt will be generated on the power cable, and these interferences will have an important impact on the radiation emission of the vehicle.

Nowadays researches of automotive electromagnetic field mainly focus on the component level and electromagnetic compatibility, while there is a lack of relevant studies on internal electromagnetic environment of the vehicles. With the increasingly complex internal electromagnetic environment of the vehicle, people are increasingly concerned about its potential impact of human health. This article researches on a type of electric vehicle and the occupants and analyses its electromagnetic radiation effects on human health. Firstly, considering the characters of Pro/E, Hypermesh and FEKO, the “Characteristics grouping subdivision” method is used to establish the entire vehicle body FE model. According to the requirement of MOM/FEM method, the entire vehicle model is optimized to be a high quality body model with simple construction and moderate grid size.

The camera-based advanced driver assistance systems (ADAS) like lane departure warning system (LDWS) and lane keeping assist (LKA) can make vehicles safer and driving easier. Lane detection is indispensable for these lane-based systems for achieving vehicle local localization and behavior prediction. Since the vision is vulnerable to the variable environment conditions such as bad weather, occlusions and illumination, the robustness is important. In this paper, a robust algorithm for detecting and tracking multiple lanes with arbitrary shape is proposed. We extend the previously lane detection and tracking process from the space domain to the temporal-spatial domain by using a more robust and general multi-lane model. First, new slice images containing temporal information are generated from image sequences. Instead of binarization process, we use a more general detector for extracting the lane marker candidates with prior knowledge to generate the binary slice image.

Deep neural network models have been widely used for environment perception of intelligent vehicles. However, due to models’ innate probabilistic property, the lack of transparency, and sensitivity to data, perception results have inevitable uncertainties. To compensate for the weakness of probabilistic models, many pieces of research have been proposed to analyze and quantify such uncertainties. For safety-critical intelligent vehicles, the uncertainty analysis of data and models for environment perception is especially important. Uncertainty estimation can be a way to quantify the risk of environment perception. In this regard, it is essential to deliver a comprehensive survey. This work presents a comprehensive overview of uncertainty estimation in deep neural networks for environment perception of intelligent vehicles.

In this paper, Digital Image Correlation Method (DICM) is employed to measure the shear mechanical property of the new style automotive structural adhesive specimens and traditional spot welded specimens under quasi static uniaxial shear tensile test. This experiment adopts a non-contact measuring method to measure the strain of specimens. A CCD and a computer image processing system are used to capture and record the real-time surface images of the specimens before and after deformation. Digital correlation software is used to process the imagines before and after deformation to obtain the specimen's strain of the moment. And then both the force-displacement curve and the stress-strain curve during the tensile process could be obtained. The test and analysis results show that the new style structural adhesive specimens have a great advantage with the spot welded specimens. It provides experimental evidence for further improvement of this structural adhesive.

Lithium-ion batteries (LIBs) with relatively high energy, power density and eco-friendly characteristic are considered as a vital energy source in consumer market of portable electronics and transportation sector especially in electric vehicles (EVs). To meet the higher capacity requirements, the nickel-rich LIBs with higher capacity has been used as the commercial power batteries. However, the battery with higher energy density is more destructive, which could result in thermal runaway accidents and make the battery safety issues become more and more prominent. Thermal runaway of LIBs is one of the key scientific problems in safety issues. Until now, the inducement of thermal runaway process is complicated which perplex researchers and industry a lot. On the one hand, the internal mechanism about thermal runaway should be deeply studied. On the other hand, in-situ monitoring should be developed to supply the mechanism study and early warning.

Automotive window seal has great influence on NVH (Noise-Vibration-Harshness) performance. The aerodynamic effect on ride comfort has attracted increasing research interest recently. A new method for quantifying and transferring aerodynamics-induced load on window seal re-design is proposed. Firstly, by SST (Shear Stress Transport) turbulence model, external turbulent flow field of full scale automotive is established by solving three-dimensional, steady and uncompressible Navier-Stokes equation. With re-exploited mapping algorithm, the aerodynamics pressure on overall auto-body is retrieved and transferred to local glass area to be external loads for seals, thus taking into account the aerodynamics effect of high speed fluid-structure interaction. This method is successfully applied on automotive front window seal design. The re-design header seal decreases the maximum displacements of leeward and windward glass with 9.3% and 34.21%, respectively.

Accurate and reliable localization in GNSS-denied environments is critical for autonomous driving. Nevertheless, LiDAR-based and camera-based methods are easily affected by adverse weather conditions such as rain, snow, and fog. The 4D Radar with all-weather performance and high resolution has attracted more interest. Currently, there are few localization algorithms based on 4D Radar, so there is an urgent need to develop reliable and accurate positioning solutions. This paper introduces RIO-Vehicle, a novel tightly coupled 4D Radar/IMU/vehicle dynamics within the factor graph framework. RIO-Vehicle aims to achieve reliable and accurate vehicle state estimation, encompassing position, velocity, and attitude. To enhance the accuracy of relative constraints, we introduce a new integrated IMU/Dynamics pre-integration model that combines a 2D vehicle dynamics model with a 3D kinematics model.

Visual sensors are widely used in autonomous vehicles (AVs) for object detection due to the advantages of abundant information and low-cost. But the performance of visual sensors is highly affected by low light conditions when AVs driving at nighttime and in the tunnel. The low light conditions decrease the image quality and the performance of object detection, and may cause safety of the intended functionality (SOTIF) problems. Therefore, to analyze the performance limitations of visual sensors in low light conditions, a controlled light experiment on a proving ground is designed. The influences of low light conditions on the two-stage algorithm and the single-stage algorithm are compared and analyzed quantificationally by constructing an evaluation index set from three aspects of missing detection, classification, and positioning accuracy.

Multiple object detection and tracking are central aspects of modeling the environment of autonomous vehicles. Lidar is a necessary component in the autonomous driving system. Without Lidar sensors, we will most probably not see fully self-driving cars become a reality. Lidar sensing gives us high-resolution data by sending out thousands of laser signals. In advanced driver assistance systems or automated driving systems, 3-D point clouds from lidar scans are typically used to measure physical surfaces. Lidar is a powerful sensor that you can use in challenging environments where other sensors might prove inadequate. Lidar can provide a complete 360-degree view of a scene. This paper designs Lidar based multi-target detection and tracking system based on the traditional point cloud processing method including down-sampling, denoising, segmentation, and clustering objects.

Since situational awareness is crucial for autonomous driving in urban environments, multi-target tracking has become an increasingly popular research topic during the last several years. For autonomous driving in urban environments, cars and pedestrians are the two main types of obstacles, and their motion characteristics are not the same. While in the current related multi-target tracking research, the same motion model (such as Constant Velocity model [CV]) or motion model set (such as CV combined with Constant Acceleration model [CA]) is mostly used to track different types of obstacles simultaneously. Besides, in current research, regular motion models are mostly adopted to track pedestrians, such as CV, CA, and so on, the uncertainty in pedestrian motion is not well considered.

The main challenge for future autonomous vehicles is to identify their location and body pose in real time during driving, that is, “where am I? and how will I go?”. We address the problems of pose estimation and scene perception from continuous visual frames in intelligent vehicle. Recent advanced technology in the domain of deep learning proposes to train some learning models for vehicle’s series detection tasks in a supervised or unsupervised manner, which has numerous advances over traditional approaches, mainly reflected in the absence of manual calibration and synchronization of the camera and IMU. In the paper, we propose a novel approach for pose estimation and scene recognition with a deep fusion of multi-modal neural features in the manner of unsupervised. Firstly, low-cost camera and IMU are used to extract original visual and inertial data, then the visual and inertial encoders are utilized to encoder the feature of the two modes.