Real-time Car Research Articles

Real Time Car Model and Plate Detection System by Using Deep Learning Architectures

Real Time Car Model and Plate Detection System by Using Deep Learning Architectures

System Telemetry for Mobile Devices Using the GPS Neo-6M and DHT11 Modules A Case Study by IMEI Team

Telemetry systems are used during Formula One (F1) and Shell Eco Marathon (SEM) races to monitor car conditions and performance during the race. This telemetry system is designed to monitor the performance of the car in real time by obtaining data about speed, steering room temperature, and other parameters. The purpose of making this tool is to be able to strategize during a good and efficient race. In this research on telemetry system development, several sensors and electronic devices are used to monitor car performance. This telemetry system consists of several sensors installed on the car, such as the U-blox Neo 6m GPS sensor and the DHT 11 sensor. These sensors collect data and transmit it to the control unit, which then sends the data to the server. The method used in this research includes several stages, namely telemetry system development, trials and testing, and data analysis. The main result of this research is the development of a telemetry system that can monitor the performance of electric cars in real-time. This telemetry system can provide useful information for the driver on the track and the team at the track. In addition, the results of this research also show that the telemetry system developed can produce accurate and reliable data. An electric car telemetry system can be a very useful tool for electric car users and manufacturers in improving the efficiency and performance of electric cars. In this study, the development of the telemetry system has successfully produced a tool that can monitor the performance of electric cars in real time and provide useful information for users and electric car manufacturers. It is hoped that the results of this research can help in developing more efficient and environmentally friendly electric car technology in the future

Vehicle Real-time Condition Monitoring Based on CAN Bus

Because the automobile in the driving process there will be some hidden dangers, once the hidden dangers occur is likely to have a safety accident, then the driver’s safety will be endangered. In order to avoid this situation, this paper introduces multi-sensor communication under the CAN bus, using the CAN interface of STM32F103 MCU to transmit data with multi-sensor in real time. The high performance and reliability of CAN have been recognized, and it has been widely used in the field of automobile communication. It provides powerful technical support for the real-time and reliable data exchange of distributed control systems among nodes. Displaying the final result on the display when communicating with multiple sensors allows the driver to monitor the status of the car in real time and process it in the first place, providing a safety guide for driving.

A novel EEG decoding method for a facial-expression-based BCI system using the combined convolutional neural network and genetic algorithm.

Multiple types of brain-control systems have been applied in the field of rehabilitation. As an alternative scheme for balancing user fatigue and the classification accuracy of brain–computer interface (BCI) systems, facial-expression-based brain control technologies have been proposed in the form of novel BCI systems. Unfortunately, existing machine learning algorithms fail to identify the most relevant features of electroencephalogram signals, which further limits the performance of the classifiers. To address this problem, an improved classification method is proposed for facial-expression-based BCI (FE-BCI) systems, using a convolutional neural network (CNN) combined with a genetic algorithm (GA). The CNN was applied to extract features and classify them. The GA was used for hyperparameter selection to extract the most relevant parameters for classification. To validate the superiority of the proposed algorithm used in this study, various experimental performance results were systematically evaluated, and a trained CNN-GA model was constructed to control an intelligent car in real time. The average accuracy across all subjects was 89.21 ± 3.79%, and the highest accuracy was 97.71 ± 2.07%. The superior performance of the proposed algorithm was demonstrated through offline and online experiments. The experimental results demonstrate that our improved FE-BCI system outperforms the traditional methods.

Design and Construction of Smart Vehicle Security System Using GPS and Spy Cam

Aims: Vehicle security is critical in today's world because car thefts are on the rise. robbery, and impersonation are among the crimes committed against automobiles. As a result, keeping track of and safeguarding vehicles has grown to be a significant problem in modern life.
 Study Design: The system combines GPS (Global Positioning Service), GSM (Global System for Mobile Communications), and Spy Cam technologies interfaced with an Arduino UNO to track the location of a car in real time.
 Methodology: Short Message Service (SMS) messages are sent to the user or Vehicle authority mobile phone together with images of the current vehicle operator when SMS with the word "Track" is composed and sent to the SIM number inserted into the GSM module. BLYNK Android application serves as database for storing and retrieving cloud information when requested.
 Results: The vehicle current location and the image of the current user will be displayed on Google Maps application of the sender. This technology enhances mobile vehicle security and avoid loss and impersonation. An SMS security warning is also sent to the owner when there is a lot of movement in front of the camera.
 Conclusion: This system helps in detection and reporting of vehicle theft in real time. It can be employed in individual cars since it is affordable; also vehicle safety authorities can employ this technology to help them secure vehicles better.

Area mapping for autonomous disinfection robot

This article presents an autonomous obstacle avoidance robot with infrared sensors. With the help of these robots, the automotive industry has developed, using various types of sensors, both parking using ultrasonic sensor models, to Lidar sensors that map the immediate proximity of the car in real time. These sensors, through different trail simulations, adjusts the direction of the car to avoid various obstacles, or to avoid the following traffic jams.

“Brains” for Robots: Application of the Mivar Expert Systems for Implementation of Autonomous Intelligent Robots

Recently the contemporary robotic systems can manipulate different objects and make decisions in a range of situations due to significant advances in innovation technologies and artificial intelligence. The new expert technologies can handle millions of instructions on computers and smartphones, which allow them to be used as a tool to create “decision-making systems” for autonomous robots. The goal of this paper was to create a dynamic algorithm of robot actions that can be used in the decision module has been considered. It is proposed to use Mivar expert systems of a new generation for high-level control. The experiment results showed that Mivar decision-making systems can control groups of small robots and even an unmanned autonomous car in real time. The algorithms created in the Mivar environment can be very flexible, and their build-up depends only on engineering approaches. In addition to traditional low-level robot control systems, a Mivar decision-making system has been implemented, which can be considered as universal “Brains” for autonomous intelligent robots and now knowledge bases can be created and various robots can be trained for practical tasks. • On the basis of Mivar expert systems based on rules, logical brains for robots in the form of decision-making systems have been created. • A method for combining multiple domains to create intelligent autonomous robots capable of reasoning at the rate of 5 million production rules per second is proposed. • Fundamentally new Mivar expert systems with linear inference complexity and extremely low hardware requirements are described and implemented in traditional low-level robot control systems.

Application of Digital Learning in the Vehicle Operator Training System

This article describes an improved system for training vehicle operators, and identifies factors that affect road safety in the conditions of the road network. The author’s version of the system for training vehicle operators, when studying the section "Fundamentals of traffic safety" through the use of digital training, which allows you to manage the process of mastering theoretical and practical material. The methods used to improve the reliability of vehicle operators, taking into account individual personal qualities, are presented. The experience of using digital training in preparation for driving a car in real time is reflected.

МОДЕЛЬ ВОСПРИЯТИЯ ВОДИТЕЛЕМ ДОРОЖНОЙ СИТУАЦИИ НА ПЕРВОНАЧАЛЬНОМ ЭТАПЕ ПОДГОТОВКИ

This article analyzes the requirements for drivers, taking into account their professional activities. The model of the driver's perception of the road situation when driving a car in real time is considered. The purpose of this work is to prepare candidates for drivers for safe, confident driving. The paper suggests the author's method of training candidates for drivers at the initial stage of training.

Determination of rational locomotive operating modes and resource costs based on information from global positioning systems

The article is devoted to the study of energy-efficient use of traction rolling stock for driving trains. It deals with the optimal driving mode and the main parameters of traction calculations. Based on the use of GPS/GLONASS satellite navigation units, a method for determining the basic resistance of cars in real time is proposed. The possibility of using the results obtained on locomotives with analog devices and no movement tracking is analyzed. The “Traction Calculations” software package in the C# programming language was modified in order to reduce the time and facilitate calculations of the locomotive traction service. In the course of the study, the equation of the main resistance of the cars of train No. 3612 was determined. On the basis of the uncoupled rolling stock, the dependences of speed, time, heating and current of traction electric motors, fuel consumption by the CHME3 locomotive of the Kharkiv-Sortirovochny locomotive depot for the transportation of cars from the Kharkiv-Sortirovochny station to Merefa station were calculated, with recommendations for the driver to use the position of the driver’s controller in order to reduce costs and fulfill the train schedule.

Automated Testing of Ultrawideband Positioning for Autonomous Driving

Autonomous vehicles need accurate and dependable positioning, and these systems need to be tested extensively. We have evaluated positioning based on ultrawideband (UWB) ranging with our self-driving model car using a highly automated approach. Random drivable trajectories were generated, while the UWB position was compared against the Real-Time Kinematic Satellite Navigation (RTK-SN) positioning system which our model car also is equipped with. Fault injection was used to study the fault tolerance of the UWB positioning system. Addressed challenges are automatically generating test cases for real-time hardware, restoring the state between tests, and maintaining safety by preventing collisions. We were able to automatically generate and carry out hundreds of experiments on the model car in real time and rerun them consistently with and without fault injection enabled. Thereby, we demonstrate one novel approach to perform automated testing on complex real-time hardware.

Telemetric System for Silesian Greenpower’s Vehicle

The paper presents stages of creating a measurement system for a light-weight electric vehicle of the Silesian Greenpower team. The aim of the work was to design a measuring device and mobile application for drivers and the team. The system itself consists of a measuring device, applications for Android and Windows. The purpose of the device was to provide information about the car in real time. The collected data is saved and displayed on the driver’s phone. At the same time, the data is stored in a database, which allows the whole team to observe current parameters. Working of the measurement system has been described in the paper. Screenshots from individual applications, a specification of selected sensors and source code of the created applications have been presented. The summary of the project are graphs showing the smooth operation of the measurement system during races taking place on the Rockingham circuit in the UK.

Minimum Lap Time Control of Hybrid Electric Race Cars in Qualifying Scenarios

This paper presents models and control algorithms for the energy management of the Formula 1 race car in qualifying scenarios, whereby the car's performance is solely determined by the lap time achieved over a single lap. Specifically, we first extend an existing convex model of the Formula 1 car to include the waste-gate action, and analytically derive its lap-time-optimal control policy. Second, we combine nonlinear programming techniques with convex optimization to numerically compute the optimal solution for an out-lap-flying-lap sequence. Third, we devise equivalent lap time minimization strategies, whereby three PI controllers adapt the optimal control policy implemented on the car in real time, in order to track precomputed control strategies in a minimum-lap-time fashion. Finally, we benchmark the control algorithms presented against the optimal solution and validate their performance with high-fidelity simulations. The results obtained show the optimality and the robustness of the presented approach.

Development of portable automatic number plate recognition (ANPR) system on Raspberry Pi

ANPR system is used in automating access control and security such as identifying stolen cars in real time by installing it to police patrol cars, and detecting vehicles that are overspeeding on highways. However, this technology is still relatively expensive; in November 2014, the Royal Malaysian Police (PDRM) purchased and installed 20 units of ANPR systems in their patrol vehicles costing nearly RM 30 million. In this paper a cheaper alternative of a portable ANPR system running on a Raspberry Pi with OpenCV library is presented. Once the camera captures an image, image desaturation, filtering, segmentation and character recognition is all done on the Raspberry Pi before the extracted number plate is displayed on the LCD and saved to a database. The main challenges in a portable application include crucial need of an efficient code and reduced computational complexity while offering improved flexibility. The performance time is also presented, where the whole process is run with a noticeable 3 seconds delay in getting the final output.

Study on Transverse Vibration Characteristics of High-Speed Elevator under Gas-Solid Coupling

The purpose of this paper is to study the transverse vibration characteristics of highspeed elevator under the action of gas-solid coupling. A three-dimensional physical model of the high-speed elevator is established, the aerodynamic loads on the car under different transverse vibration states (translation and rotation) are numerically solved, and then the relationship between the different transverse vibration states of the car and the aerodynamic loads is obtained. The transverse vibration model of the high-speed elevator based on gas-solid coupling is established by transferring the attitude parameters and aerodynamic parameters of the car in real time combined with the guide excitation. Finally, the transverse vibration characteristics of high-speed elevators with or without gas-solid coupling are compared and analysed by solving the model with an example. The results show that the effect of gas-solid coupling on the transverse vibration acceleration peak value of high-speed elevator is greater when the running speed is greater than 4m/s, and the greater the speed, the more obvious the effect is, which provide some theoretical guidance for the analysis and control of the transverse vibration of high-speed elevator.

Initial performance evaluation of centimeter‐class augmentation system using Quasi‐Zenith Satellite System

AbstractOn September 11, 2010, the Quasi‐Zenith Satellite (QZS) “Michibiki” was launched from the Tanegashima island as the first satellite for positioning in Japan. We have attempted to fix positions using LEX data with centimeter‐class augmentation service for centimeter‐level positioning augmentation signal via Michibiki. The authors tried to fix positions by using LEX data at a stationary point and in a moving car in real time and with postprocessing. They could confirm no more than 2.22 cm as the average positioning error and discrepancy of postpositioning.

Technical challenges related to implementation of a formula one real time data acquisition and analysis system in a paediatric intensive care unit

Most existing, expert monitoring systems do not provide the real time continuous analysis of the monitored physiological data that is necessary to detect transient or combined vital sign indicators nor do they provide long term storage of the data for retrospective analyses. In this paper we examine the feasibility of implementing a long term data storage system which has the ability to incorporate real-time data analytics, the system design, report the main technical issues encountered, the solutions implemented and the statistics of the data recorded. McLaren Electronic Systems expertise used to continually monitor and analyse the data from F1 racing cars in real time was utilised to implement a similar real-time data recording platform system adapted with real time analytics to suit the requirements of the intensive care environment. We encountered many technical (hardware and software) implementation challenges. However there were many advantages of the system once it was operational. They include: (1) The ability to store the data for long periods of time enabling access to historical physiological data. (2) The ability to alter the time axis to contract or expand periods of interest. (3) The ability to store and review ECG morphology retrospectively. (4) Detailed post event (cardiac/respiratory arrest or other clinically significant deteriorations in patients) data can be reviewed clinically as opposed to trend data providing valuable clinical insight. Informed mortality and morbidity reviews can be conducted. (5) Storage of waveform data capture to use for algorithm development for adaptive early warning systems. Recording data from bed-side monitors in intensive care/wards is feasible. It is possible to set up real time data recording and long term storage systems. These systems in future can be improved with additional patient specific metrics which predict the status of a patient thus paving the way for real time predictive monitoring.

Real-Time Global Localization of Robotic Cars in Lane Level via Lane Marking Detection and Shape Registration

In this paper, we propose an accurate and real-time positioning method for robotic cars in urban environments. The proposed method uses a robust lane marking detection algorithm, as well as an efficient shape registration algorithm between the detected lane markings and a GPS-based road shape prior, to improve the robustness and accuracy of the global localization of a robotic car. We show that, by formulating the positioning problem in a relative sense, we can estimate the global localization of a car in real time and bound its absolute error in the centimeter level by a cross-validation scheme. The cross-validation scheme integrates the vision-based lane marking detection with the shape registration, and it improves the accuracy and robustness of the overall localization system. The GPS localization can be refined by using lane marking detection when the GPS suffers from frequent satellite signal masking or blockage, whereas lane marking detection is validated and completed by the GPS-based road shape prior when it does not work well in adverse weather conditions or with poor lane signatures. We extensively evaluate the proposed method with a single forward-looking camera mounted on an autonomous vehicle that travels at 60 km/h through several urban street scenes.

A Telemetry-driven Approach to Simulate Data-intensive Manufacturing Processes

Telemetry enables the collection of data from remote points to support monitoring, analysis and visualization. It is largely adopted in Formula One car racing, where streams of live data collected from hundreds of sensors installed on car components are transmitted to the pitwall to be used as input of real-time car performance simulations. The aim of this paper is to evaluate the potential of a telemetry-driven approach in a manufacturing environment, where researchers are still looking for efficient methods to perform valuable simulations of the production processes on the basis of real data coming from the factory. The telemetry could contribute to the implementation of a virtual image of the real factory, which in turn could be used to simulate the factory performance, allowing to predict failures or investigate problems, and to reduce costly downtime. This study addresses in particular the efforts to combine and adapt methods and techniques borrowed from the field of Formula One car racing. Moreover, the investigation of the exploitation possibilities of the factory telemetry is paired with the design of a software application supporting this technology, starting from the elicitation and specification of the functional requirements.

Learning Discriminative Pattern for Real-Time Car Brand Recognition

In this paper, we study the problem of recognizing car brands in surveillance videos, cast it as an image classification problem, and propose a novel multiple instance learning method, named Spatially Coherent Discriminative Pattern Learning, to discover the most discriminative patterns in car images. The learned discriminative patterns can effectively distinguish cars of different brands with high accuracy and efficiency. The experimental results demonstrate that our method is significantly superior to recent image classification methods on this problem. The proposed method is able to deliver an end-to-end real-time car recognition system for video surveillance. Moreover, we construct a large and challenging car image data set, consisting of 37 195 real-world car images from 30 brands, which could serve as a standard benchmark in this field and be used in various related research communities.