Design A Smart Reservation for Parking System

With the increasing population in urban areas, finding a vacant parking space has always been the biggest problem for drivers, which causes a series of issues such as energy waste and environmental pollution. Most outdoor parking lots cannot provide details of vacant parking spaces due to limited sensor technology in outdoor environments (i.e., poor resistance to external interference due to heat, light or signal noise). Although some studies are based on images captured by cameras, the existing vacancy detection methods using fixed-position surveillance cameras are not flexible and accurate enough for wide use. We propose an Inclined Bounding Box (IBB) method for detecting vacant parking spaces using aerial images. The IBB method takes advantage of the feature-description ability of deep Convolutional Neural Network (CNN) to identify the status of parking spaces and develops an inclined bounding boxes calibration algorithm on the top layer of CNN architecture. The proposed IBB method can automatically identify parking spaces, locate vacant parking spaces with any direction and detect multiple parking spaces simultaneously. The experimental results show that the proposed IBB method is more accurate than the three counterpart methods.

Finding a vacant parking space in outdoor parking lots is a daily concern of most vehicle drivers during rush hours, especially in the urban context. In this paper, an outdoor parking space vacancy detection system is proposed, using mobile devices to improve parking space searching experience for vehicle drivers by providing them with the location and occupancy information of parking spaces. The system uses state-of-the-art image recognition algorithm, namely Convolutional Neural Network with a Raspberry Pi to identify vacant parking spaces from a parking lot image retrieved in real time via an IP camera. A university parking lot has been chosen as the test bed to deploy the proposed system for real time parking space vacancy detection. An Android smartphone application called Driver App is developed to enable ubiquitous visualization of real time outdoor parking spaces occupancy information for vehicle drivers. Evaluation outcomes based on the responses to System Usability Scale (SUS) questionnaire revealed high usability of the Driver App as a tool that provides smart parking service to assist vehicle drivers in searching for a vacant parking space.

Parking occupancy detection is a critical component of modern smart city infrastructure, aimed at optimizing parking space utilization and reducing traffic congestion. This project proposes a computer vision-based solution using OpenCV to detect and monitor parking space occupancy in real-time. The system utilizes image processing techniques to analyze video feeds from surveillance cameras installed in parking lots. By employing background subtraction, contour detection, and object classification algorithms, the system identifies occupied and vacant parking spaces with high accuracy. The proposed solution is cost-effective, scalable, and capable of integrating with existing parking management systems. The results demonstrate the system's ability to provide real-time occupancy data, enabling efficient parking management and enhancing user experience. This project highlights the potential of computer vision technologies in addressing urban parking challenges and contributing to the development of smart cities. Keywords - Parking Occupancy Detection, OpenCV, Computer Vision, Image Processing, Smart Parking, Real-Time Monitoring.

The difficulty in finding parking spaces is growing into a more serious problem especially in urban areas. As the number of vehicles on the road continues to increase substantially, the difficulty in finding parking spaces increases even more. To combat this rising issue many cities have adopted a more organised and intelligent parking system which is also commonly known as smart parking system. This is to improve the efficiency of locating a parking spot, especially in an urban area. The smart parking system will often have sensors at parking spaces to determine the occupancy of the respective parking space. This occupancy value is relayed to a server by some specific communication protocol. The parking occupancy can then be displayed to the public by a Graphical User Interface (GUI) design which gets the occupancy values from a server. This project simulates the parking sensor network design in a smart campus setting by implementing the concept of the Internet of Things (IoT). This project uses ultrasonic sensors that are connected to a NodeMCU microcontroller to send the parking occupancy values to an online database implemented using Google Firebase. A mobile application with a GUI (Graphical User Interface) is also created using MIT App Inventor 2 to display the vacancy of parking by communicating with the online database. The results obtained in this project were promising. The successful implementation of this idea will allow users to save more time and money, not to mention that it can also help reduce carbon emissions from vehicles resulting in a more sustainable environment.

Accelerated urbanization and the ensuing rapid increase in urban populations led to the need for a tremendous number of parking spaces. Automated parking systems coupled with new parking lot layouts can effectively address the need. However, most automated parking systems available on the market today use ultrasonic sensors to detect vacant parking spaces. One limitation of this method is that a reference vehicle must be parked in an adjacent space, and the accuracy of distance information is highly dependent on the positioning of the reference vehicle. To overcome this limitation, an around view monitoring-based method for detecting parking spaces and algorithms analyzing the vacancy of the space are proposed in this study. The framework of the algorithm comprises two main stages: parking space detection and space occupancy classification. In addition, a highly robust analysis method is proposed to classify parking space occupancy. Two angles of view were used to detect features, classified as road or obstacle features, within the parking space. Road features were used to provide information regarding the possible vacancy of a parking space, and obstacle features were used to provide information regarding the possible occupancy of a parking space. Finally, these two types of information were integrated to determine whether a specific parking space is occupied. The experimental settings in this study consisted of three common settings: an indoor parking lot, an outdoor parking lot, and roadside parking spaces. The final tests showed that the method’s detection rate was lower in indoor settings than outdoor settings because lighting problems are severer in indoor settings than outdoor settings in around view monitoring (AVM) systems. However, the method achieved favorable detection performance overall. Furthermore, we tested and compared performance based on road features, obstacle features, and a combination of both. The results showed that integrating both types of features produced the lowest rate of classification error.

This paper proposes a novel parking spaces detection algorithm which is based on image segmentation and local binary pattern. The vehicles are usually contains a lot of compositions, while the vacant parking spaces' composition is relatively small. According to this characteristic, we segment the parking image. To judge whether each parking area has a large number of small split or not, can achieve the detection of the parking stalls. In this paper, we improve the Mean Shift algorithm and achieve the accurate segmentation result. This proposed method was tested on indoor and outdoor parking lots. The result confirmed the efficiency of the proposed method, with the detection rate being over 97%. But, this method fails to detect non-vehicle objects and when the Vehicle color and ground color is very similar. So we the introduce the texture features, use LBP (local binary pattern) to extract the parking texture feature. Using the complementary between features and ultimately to achieve accurate detection.

Proliferation in the number of vehicles is leading to problems of vehicles parking at an appropriate place especially the car parking. This indirectly leads to traffic congestion. This is because of the fact that current transportation infrastructure and car park facility are unable to cope with the arrival of large number of vehicles on the road. To alleviate the aforementioned problem, authors proposed a Smart Parking Management System that helps users to automatically find a free parking space with a smaller amount. Smart Parking involves use of Ultrasonic sensor, Arduino Uno, ESP8266-01 Wi-Fi Module, Cloud server. IOT based new parking platform enable to connect, analyze and automate data gathered from devices and execute smart parking possible. Smart parking would enable vehicle occupancy, monitoring and managing of available parking space in real-time that reducing the environmental pollution. Proposed system provides optimize usage of parking space and get considerable revenue generation.

Searching for a publicly available parking space has become a nightmare to many drivers. With the constant development of global urbanization, human population has increased drastically in the past decades. Searching for a publicly available parking space in a highly populated area can be daunting and time consuming. No matter how much time is spent to find a vacant parking space, it always causes traffic congestion in the area. To alleviate these problems, it is of utmost importance to have a system that can detect and display the vacant parking spaces in real-time. This paper has conducted a study of anticipation of parking vacancy using convolutional neural network called YOLOv3 in a university campus. Image data is gathered from the video capture of the university’s campus open space parking lot. The YOLOv3 algorithm is used to train and predict whether the space is vacant or occupied. Results showed that YOLOv3 has been able to correctly predict the vacant space. The result of the rendering video will then be transformed into an image and is sent to the students via a Telegram group.

Difficulty in finding a vacant parking space has always been a problem encountered by drivers especially in metropolitan areas. This study proposed a cost-effective vision-based outdoor parking space vacancy detection system, ConvPark to assist vehicle drivers by providing information regarding the availability of parking spaces. The system is designed based on Convolutional Neural Network (CNN) technology and is implemented through a Raspberry Pi to identify the occupancy status of parking spaces live via. an IP camera. This system has been deployed at a university car park for real-time detection of vacant parking spaces. The use of CNN classifier in the proposed system provides superiority in term of automatic image features extraction and robustness against environmental variations as compared to other computer vision-based methods. Evaluation outcomes demonstrated that our proposed system can achieve excellence performance in term of detection accuracy by precisely determining the occupancy status of parking spaces under different environmental conditions.

Mobility by using private vehicles has created a need of appropriate parking spaces. Usually, vacant parking spaces could be found by exploring through the entire parking area or by reservation through an Internet application. Searching a vacant parking lot by exploring would cost a driver some considerable time, while obtaining one by reservation in advance would reduce the parking lots utilization. Hence, we propose a dynamic allocation method to reserve parking space using Internet application. The proposed method would reduce the need of the driver to explore the entire parking spot by finding the vacant parking lot and do the reservation for the driver. We use event-driven scheme allocation at the event of a vehicle (car) arrived at the parking lots gate to maintain parking lot utilization level. Simulation results show that our system could reduce drivers required time to find a vacant parking lot to zero. A parking lot which implemented our system would also has parking lot utilization level as high as conventional parking system, and better than conventional Internet-based reservation parking system.

The increasing vehicle density in urban areas has made parking space availability a significant challenge. With technological advancements, efficient smart parking systems based on object detection have become essential. This study evaluates the performance of YOLO versions 3 to 11 in detecting vacant parking spaces in urban environments, focusing on real-time processing, high accuracy with limited datasets, and adaptability to varying conditions. Using 4,215 annotated images and two test videos, YOLOv7 achieved the highest overall accuracy of 99.57% with an average FPS of 30.79, making it the most effective model for smart parking applications. YOLOv8 and YOLOv11 followed closely, with accuracies of 98.51% and 98.72%, respectively, and average FPS rates of 32.31 and 31.99, balancing precision and speed, which are ideal for real-time applications. Meanwhile, YOLOv5 stood out for its exceptional processing speed of 33.92 FPS. These results highlight YOLO's potential to revolutionize smart parking systems by significantly enhancing both detection precision and operational efficiency.

Parking Spaces Detection Based on Fingerprint Algorithm

Finding a parking space is usually challenging in urban areas. The literature shows that 30% of traffic congestion is caused by searching for parking spaces, which results in unnecessary energy consumption and environmental pollution. With the development of sensor technologies, smart parking guidance systems provide users with a variety of real-time parking space information. However, users cannot know whether the target parking space remains available upon arrival. Moreover, parking resources may be under competition when multiple users target the same open parking space. In this research, we develop a new framework named prediction-based parking allocation (PPA) that provides smart parking services to users. In PPA, we first construct a prediction model of parking occupancy and predict the subsequent parking availabilities. Then, we design a matching-based allocation strategy to assign users to selected parking spaces. To the best of our knowledge, this is the first study that combines occupancy prediction and space allocation simultaneously to address smart parking issues. Finally, we collect a real dataset from the SFPark on-street parking system for performance evaluation. According to experimental results, PPA can effectively increase the parking success rate and reduce costs, fuel consumption, and carbon emissions.

In smart parking environments, how to choose suitable parking facilities with various attributes to satisfy certain criteria is an important decision issue. Based on the multiple attributes decision making (MADM) theory, this study proposed a smart parking guidance algorithm by considering three representative decision factors (i.e., walk duration, parking fee, and the number of vacant parking spaces) and various preferences of drivers. In this paper, the expected number of vacant parking spaces is regarded as an important attribute to reflect the difficulty degree of finding available parking spaces, and a queueing theory-based theoretical method was proposed to estimate this expected number for candidate parking facilities with different capacities, arrival rates, and service rates. The effectiveness of the MADM-based parking guidance algorithm was investigated and compared with a blind search-based approach in comprehensive scenarios with various distributions of parking facilities, traffic intensities, and user preferences. Experimental results show that the proposed MADM-based algorithm is effective to choose suitable parking resources to satisfy users’ preferences. Furthermore, it has also been observed that this newly proposed Markov Chain-based availability attribute is more effective to represent the availability of parking spaces than the arrival rate-based availability attribute proposed in existing research.

Finding on-street parking in congested urban areas is a challenging chore that most drivers worldwide dislike. Previous vehicle traffic studies have estimated that around thirty percent of vehicles travelling in inner city areas are made up of drivers searching for a vacant parking space. While there are hardware sensor based solutions to monitor on-street parking occupancy in real-time, instrumenting and maintaining such a city wide system is a substantial investment. In this paper, a novel vehicle parking activity detection method, called ParkUs, is introduced and tested with the aim to eventually reduce vacant car parking space search times. The system utilises accelerometer and magnetometer sensors found in all smartphones in order to detect parking activity within a city environment. Moreover, it uses a novel sensor fusion feature called the Orthogonality Error Estimate (OEE). We show that the OEE is an excellent indicator as it’s capable of detecting parking activities with high accuracy and low energy consumption. One of the envisioned applications of the ParkUs system will be to provide all drivers with guidelines on where they are most likely to find vacant parking spaces within a city. Therefore, reducing the time required to find a vacant parking space and subsequently vehicle congestion and emissions within the city.