Search Results

Intelligent sweeper vehicle is gradually applied to human life, in which the accuracy of garbage identification and classification can improve cleaning efficiency and save labor cost. Although Deep Learning has made significant progress in computer vision and the application of semantic network segmentation can improve waste identification rate and classification accuracy. Due to the loss of some spatial information during the convolution process, coupled with the lack of specific datasets for garbage identification, the training of the network and the improvement of recognition and classification accuracy are affected. Based on the Unet algorithm, in this paper we adjust the number of input and output channels in the convolutional layer to improve the speed during the feature extraction part. In addition, manually generated datasets are used to greatly improve the robustness of the model.

The acquisition of vehicle dimensions in a vehicle’s moving process has a wide application in road monitoring, transportation, vehicle model recognition and non-contact overload recognition. At present, the detection of the vehicle dimensions mostly adopts the methods of human visual inspection and tool detection, which has a low detection efficiency and difficult to replicate on a large scale. Based on the image background subtraction method, this paper proposes a vehicle dimensions detection method, which can realize real-time detection of road vehicle dimensions. This method uses an adaptive Gaussian Mixture Model (GMM) to establish a background model based on the video stream. Initially, the moving target image is obtained by the background subtraction method, and then the edge detection under the Canny operator and Hough transform circle detection are performed on the image to obtain the pixel dimension of the vehicle's outline.

An accurate and timely positioning of the vehicle is required at all times for autonomous driving. The global navigation satellite system (GNSS), even when integrated with costly inertial measurement units (IMUs), would often fail to provide high-accuracy positioning due to GNSS-challenged environments such as urban canyons. As a result, visual odometry is proposed as an effective complimentary approach. Although it’s widely recognized that visual odometry should be developed based on both visible and infrared images to address issues such as frequent changes in ambient lightening conditions, the mechanism of visible-infrared fusion is often poorly designed. This study proposes a Generative Adversarial Network (GAN) based model comprises a generator, which aims to produce a fused image combining infrared intensities and visible gradients, and a discriminator whose target is to force the fused image to retain as many details that exist mostly in visible images as possible.

In ITS, image processing technology is applied to a wide variety of areas such as visual-based intelligent vehicle navigation, visual-based traffic monitoring and visual-based traffic management. In the recognition system of the vehicle body characteristics, most of the recognition is the license plate and the car emblem, etc. This paper proposes an image recognition application method for the vertical motion of the car while driving, mainly including vertical height detection and vertical displacement velocity acceleration recognition. The edge detection model of the image object is established by using the gray image to obtain the car motion segmentation image. At the same time, an image length and actual length coordinate conversion model is established, which can calculate an arbitrary actual length of the image object. In this paper, Yuejin Shangjun X500 van was selected as the test vehicle, and the video data was captured with a camera.

Preventing skidding is essential for studying the safety of driving in curves. However, the adhesion of the vehicle during the driving process on the wet and slippery road will be significantly reduced, resulting in lateral slippage due to the low adhesion coefficient of the road surface, the speed exceeding the turning critical, and the turning radius being too small when passing through the corner. Therefore, to reduce the incidence of traffic accidents of passenger cars driving in curves on rainy and snowy days and achieve the purpose of planning safe driving speed, this paper proposes a curve active safety system based on a deep learning algorithm and vehicle dynamics model. First,we a convolutional neural network (CNN) model is constructed to extract and judge the characteristics of snow and ice adhesion on roads.

As motor assembly of Battery Electric Vehicle (BEV) replaces engine system of Internal Combustion Engine (ICE) vehicle, interior structure-borne noise induced by road random excitation becomes more prominent under middle and high speed. The research is focused on central driving type BEV. In order to improve interior noise in middle and low frequency range, dynamic load of BEV body must be identified. Consequently the structural noise induced by road excitation is conducted. The limitations of common identification method for dynamic body load are analyzed. The applied several identification methods are proposed for deterministic dynamic load such as engine or motor. Random dynamic load generated by road excitation is different from deterministic dynamic load. The deterministic load identification method cannot be applied to the random load directly. An identification method of dynamic body load for BEV is presented based on power spectrum decomposition.

Before the new car rolls from the line, due to assembly errors, inaccurate four-wheel positioning, etc., the vehicle will run off on a flat road, which will affect the driving comfort and safety. At present, most automobile manufacturers choose to perform the deviation test in the process of vehicle rolls from the line. Compared with other detection methods, the online deviation test system is developed with high precision of laser ranging, fast response and good reliability, which can realize fast and high-precision detection of vehicle deviation. In this paper, test system software is developed based on the LABVIEW, a variety of communication methods to build the communication system, using information check and queue task processing to control, to meet the test needs. Firstly, the calculation model of the deviation of the test system is established.

For the thin ice on the road in winter, the traditional road deicing vehicle relies on mechanical and chemical methods for melting ice, which is inclined to damage the pavement and has insidious influence on environment. The thermal deicing vehicle has been adopted in recent years. Although the deicing method is available, the deicing efficiency is unacceptable while the energy consumption is huge. The study adopts the new idea of “bottom-to-top” for melting the intersection area between the road surface and the bottom ice layer by the microwave heating firstly and then cleaning them out using high pres. vapor cutting so as to save the cost of energy and enhance the traffic safety. First of all, the mathematical model of the melting process of the intersection of the pavement and the ice layer was established according to the microwave heating characteristics.

The non-contact overload recognition method refers to the method of detecting the vibration state of the vehicle through visual recognition without touching the vehicle, and then calculating the vehicle load in combination with the vehicle dynamics model to determine whether the passing vehicle is overloaded. Due to the convenience of detection, low cost of infrastructure and informatization, this method has great advantages in the field of overload identification. However, the model used in this recognition method is the single mass vibration model at present, which will have a large error due to the interaction between the front and rear suspension, and the position of the center of mass needs to be acquired in the recognition process, which is difficult in the actual identification process. In this paper, a vehicle vibration model containing two modes of vibration is proposed, and uses Sobol algorithm to analyze the parameter sensitivity of the model.

When dump trucks unload dusty materials, dust particles with a diameter of 1 to 75 microns slide out of the dump body and float into the air. Dust particles naturally settle down spending a few hours, which causes air pollution. People who work in this environment daily suffer serious physical harm. To study the movement of dust particles during the unloading process, a scaled-down model is used to simulate the process of dump truck unloading gravel, and a high frame rate camera is used to record the movement trajectory of dust particles during the unloading process. In this paper, by observing the movement process of unloading dust particles by dump trucks, based on the principle of dynamics, a mathematical model describing the unloading of dust particles in the dump body and a mathematical model of the diffusion of dust particles in the air are established. Take the small gravel sampled at the construction site as an example of the experiment.

Dangerous driving behavior will cause serious traffic accidents, which will not only threaten life and property but also cause traffic congestion and reduce road capacity. Speed detection is an important detection method to identify whether a driver is driving dangerously. Traditional speed detection methods need additional sensors, which will increase the cost of speed measurement. This paper proposes a vehicle speed estimation algorithm based on the imaginary projection plane (IPP). The IPP will be established according to the height, field angle, and vertical tilt angle of the camera and will be used to establish the mapping relationship between the world coordinates and image coordinates of the vehicle. By combining YOLOv4 and DeepSORT, the vehicle license plate is detected and tracked, and the center point of the vehicle license plate is taken as the feature point of vehicle speed estimation. The vehicle speed is estimated according to the IPP.

Signage recognition is one of the hot topics in recent years. It has important applications in intelligent traffic and autonomous driving of smart cars. This paper designs a road marking recognition method combining OPSA point set distance and wavelet transform. The method consists of three main phases: 1) image denoising, restoration, 2) feature extraction, and 3) image recognition. First, a Gaussian-smoothing filter used to attenuate or remove irrelevant information in the image, enhance related information in the image, and achieve image denoising. In the feature extraction stage, the feature extraction and recognition method based on wavelet transform adopted to overcome the deficiency of the traditional Fourier feature extraction method, ensure that high frequency information is not lost, and low frequency information is not lost. Finally, the OSPA point set used to identify distance markers.

Studies show that driving in foggy environment is a security risk, and when driving in foggy environment, the drivers are easy to accelerate unconsciously. The safety information prompted to the driver is mainly from fog lights, road warning signs and the traffic radio. In order to increase the quality of the safety tips to prevent drivers from unintended acceleration and ensure the security of driving in foggy environment, the study proposes a safety speed assessment method for driving in foggy environment, combining the information of driving environment, vehicle’s speed and the multimedia system. The method uses camera which is installed on the front windshield pillar to collect the image about the environment, and uses the dark channel prior theory to calculate the visibility. And by using the environment visibility, the safety speed can be calculated based on the kinematics theory. And it is appropriate for vehicles which have different braking performance.

In this paper, we propose a method of dynamics simulation and analysis based on superelement modeling to increase the efficiency of dynamics simulation for vehicle body structure. Using this method, a certain multi-purpose vehicle (MPV) body structure was divided into several subsystems, and the modal parameters and frequency response functions of which were obtained through superelement condensation, residual structure solution, and superelement data restoration. The study shows that compared to the traditional modeling method, the computational time for vehicle body modal analysis can be reduced by 6.9% without reducing accuracy; for the purpose of structural optimization, the computational time can be reduced by 87.7% for frequency response analyses of optimizations; consistency between simulation and testing can be achieved on peak frequency points and general trends for the vibration frequency responses of interior front row floors under accelerating conditions.

In summer, when vehicle parks in direct sunlight, the closed cabin temperature would rise sharply, which affects the occupants step-in-car comfort Solar powered vehicle parking ventilation system adopts the solar energy to drive the original ventilator. Thus, the cabin temperature could be dramatically decreased and the riding comfort could be also improved. This research analyzed the modified crew cabin thermal transfer model. Then the performance of the solar powered ventilation system is analyzed and optimized combined with the power supply characteristics of the photovoltaic element. The storage and reuse of the solar power is achieved on condition that the cabin temperature could be steadily controlled. The research shows that, the internal temperature is mainly affected by the solar radiation intensity and the environment temperature.

Automotive Front Lighting System(AFS) can receive the steering signal and the vehicular speed signal to adjust the position of headlamps automatically. AFS will provide drivers more information of front road to protect drivers safe when driving at night. AFS works when there is a steering signal input. However, drivers often need the front road's information before they turn the steering wheel when vehicles are going to go through a sharp corner, AFS will not work in such a situation. This paper studied how to optimize the working time of AFS based on GIS (Geographic Information System) and GPS(Geographic Information System) to solve the problem. This paper analyzed the process of the vehicle is about to go through a corner. Low beams and high beams were discussed respectively.

In the process of truck overload and over-limit detection, it is necessary to detect the characteristics of the vehicle's size, type, and wheel number. In addition, in some vehicle vision-based load recognition systems, the vehicle load can be calculated by detecting the vibration frequency of specific parts of the vehicle or the change in the length of the suspension during the vehicle's forward process. Therefore, it is essential to quickly and accurately identify vehicle features through the camera. This paper proposes a vehicle feature recognition method based on image semantic segmentation and Python, which can identify the length, height, number of wheels and vibration frequency at specific parts of the vehicle based on the vehicle driving video captured by the roadside camera.