CAR PARKING SLOT DETECTION USING YOLO ALGORITHM

Proposal and Application of Parking Area Performance Measurement Methodology

A decision support system for available parking slots on the roadsides in urban areas

Model free Reinforcement Learning to determine pricing policy for car parking lots

SCADA for the prototype M221 PLC-based multi-area car parking system is a system for managing several separate car parks on line via ethernet. The system is equipped with HMI as an interface to facilitate operators to monitor system conditions in real-time and the ability to display data on the number of vehicles entering and exiting, counting the number of vehicles parked for one day, and calculating revenue throughout the day. Loop sensor is used to detect vehicles that will enter or exit the parking door. Input from the sensor will be processed by the PLC to move the doorstop motor, indicator lights and update the display on the HMI. The results of a multi-area prototype test process for a car parking system for two parking areas have worked well. The system is able to control the opening and closing of the entrance and exit bars, controlling the indicator lights whether or not the parking area is full, showing the animation of the system process to the HMI in real time, calculating the number of vehicles and calculating the total cost of revenue in each parking area.

This Computer Vision is one of the most research fields in data science and is being applied in Autonomous vehicles, Machine Vision, Military, etc. Computer Vision is also used for license plate recognition and can be integrated with various projects such as toll points on highways, border points, exceeding the speed limit, car parking, etc. In this paper, we proposed a system for car management parking lots. The system is web-based and developed with Python programing language and Flask web framework. In this project, we have used OpenCV to receive images from the camera and OpenALPR to recognize license plates and analyze them. System running in Linux and Raspbian operating system. The experiments show that our system can be used for car parking and can recognize 85% of images captured from the camera.

This research paper introduces an intelligent parking management system aimed at optimizing parking space utilization. The system's main objective is to first keep a track of all the incoming and leaving vehicles within the parking area, while also updating the track of all the occupied and available parking slots at the same time, effectively managing the traffic. A camera installed at the entry gate will recognise the license plate and will be segmented and processed through optical character recognition achieving the recognition accuracy of 95.8% The vehicle number is then stored in a database where entry and exit times are also stored. The extracted license number will then be linked to an available parking slot that would be closest to the said vehicle, calculated through algorithms such as Dijkstra. Finally, the automatic credit system will calculate the cost through entering and leaving time, and the amount will automatically be deducted from the app's wallet. This integrated approach aims to significantly improve parking efficiency compared to manual systems. The paper will discuss the system's design, implementation, and potential performance outcomes for vehicle detection, license plate recognition, and parking slot availability. . KEYWORDS :Computer vision, Character recognition, YOLO, Vehicle detection, OpenCV

A quest of vacant parking space in the public area can indirectly lead to traffic congestion which can be troublesome for drivers in terms of time efficiency. This study is expected to assist drivers to get the available parking slots information in a real-time manner and support the parking control systems by constantly updating the information of vacant parking slots positions in public areas. A vision-based parking slots recognition method is proposed to identify occupied areas by vehicle which is divided into two main parts: setup configuration and object detection. Canny Edge and Hough Line Transform are used to achieve line detection for parallel parking slot marking; contour extraction and bounding rectangular are then applied for an initial parameter to form a reference area as a region of interest (ROI). Moreover, Structural Similarity Index Measurement (SSIM) exploits the reference image and target image to identify whether the area is empty or occupied by vehicle depending on structure comparison. Experimental result shows, from 50 sample images of parking slots attained by surveillance camera, the detection accuracy of 92% and precision of 89% are obtained using selected features with tuning SSIM threshold level of 0.4.

The current parking system still uses a manual parking system, vehicle owners still have difficulty finding an empty parking space because they have to go around the parking area so it is less efficient and takes a long time. This study aims to help car drivers save time in finding parking locations and knowing the availability of parking spaces. In this study, there are two types of input used: infrared sensors, which function to measure the capacity of the parking space, and RFID sensors, which are used to detect cards. The data processing process is carried out using Arduino Uno, while the LCD is used to display the number of available parking slots and the location of the slot. In addition, the servo motor functions to open the barrier. This system operates in a way, when a car enters and attaches a registered card, the servo motor will open, and the number of parking slots will decrease. The driver then selects a parking slot, which will be automatically marked as "full" on the LCD screen. When the infrared sensor detects a car that wants to exit, the servo motor will open again, and the number of parking slots on the LCD will increase.

Recently, due to the development of automobile industry, the number of vehicles is increasing. The traditional parking lots are unable to meet the growing demands from so many vehicles. Therefore, the current parking lots present many problems. Such as, can't find parking spaces quickly, difficult to manage too many vehicles and manual toll collection costs much time. To solve those problems above, this paper designs a new parking lot system which is based on ZigBee technology and Support Vector Machine (SVM). By the designed parking system, the parking issues can be solved more efficiently and intelligently.

Statistics from the Central Statistical Office (CSO) state that the total number of motor vehicles and mopeds in Poland in 2019 was 31,989,313 units. According to the Central Register of Vehicles (CEPiK) maintained by the Ministry of Digitalisation, the number of motor vehicles registered in Poland in 2019 was 23,878.8 thousand units. Among them, 18,302.4 thousand passenger cars were registered. The constantly increasing number of vehicles on the road has a significant impact on the deterioration of road capacity and drivers’ frustration with parking, especially during rush hours in the centres of large cities. Hence, urban logistics, including the country’s parking policy, is extremely important to a significant proportion of citizens. Unfortunately, citizens have different perspectives on parking issues. Most drivers expect to be able to leave their car as close as possible to their destination, while some residents, especially non-motorised ones, are against the conversion of free city space into car parks. In response to the presented issues, a comparative analysis of selected types of car parks was carried out. This analysis was one of the stages of the project entitled: “Analysis of the environmental impact of a vertical parking solution using life cycle assessment at the design stage” carried out at the Silesian University of Technology.

In recent years, with the rapid development of China’s automobile industry, the number of vehicles in China has been increasing steadily. Vehicles represent a convenient mode of travel, but the growth rate of the number of urban motor vehicles far exceeds the construction rate of parking facilities. The continuous improvement of parking allocation methods has always been key for ensuring sustainable city management. Thus, developing an efficient and dynamic parking distribution algorithm will be an important breakthrough to alleviate the urban parking shortage problem. However, the existing parking distribution models do not adequately consider the influence of real-time changes in parking demand and supply on parking space assignment. Therefore, this study proposed a method for dynamic parking allocation using parking demand predictions and a predictive control method. A neural-network-based dynamic parking distribution model was developed considering seven influencing factors: driving duration, walking distance, parking fee, traffic congestion, possibility of finding a parking space in the target parking lot and adjacent parking lot, and parking satisfaction degree. Considering whether the parking spaces in the targeted parking lots are shared or not, two allocation modes—sharing mode and non-sharing mode—were proposed and embedded into the model. At the experimental stage, a simulation case and a real-time case were performed to evaluate the developed models. The experimental results show that the dynamic parking distribution model based on neural networks can not only allocate parking spaces in real time but also improve the utilisation rate of different types of parking spaces. The performance score of the dynamic parking distribution model for a time interval of 2–20 min was maintained above 80%. In addition, the distribution performance of the sharing mode was better than that of the non-sharing mode and contributed to a better overall effectiveness. This model can effectively improve the utilisation rate of resources and the uniformity of distribution and can reduce the failure rate of parking; thus, it significantly contributes to more smart and sustainable urban parking management.

A huge growth of big cities, the number of vehicles are increased significantly and large buildings and parking lots have been built. Smarter parking systems need to be developed to assist drivers in finding nearby parking spaces available. Various research efforts have been shown in developed countries in such system implementation. There are four main types of systems of parking management: wired sensor based, image based, counter based, and based on wireless sensors. This paper combines computer vision and LoRa wireless technology and worked on image-based system to find empty slot in the parking lot. Following the first edge detection category, includes front/rear pixel rate, closed contour density, and edge density. For all car parks to determine if the vehicle exists or not and to update this information to the user using wireless technology in a way that saves power and performance offline while minimizing system maintenance costs.

The upcoming technological era 5G has increased the interest towards IOT significantly, the ability of IOT (Internet of Things) which is able to render and connect multiple IOT devices and its services from any location through various applications makes the use of this technology more efficient towards its future enterprise. The introduction of smart IOT technologies which is the present stream of automation in cars has allowed the devices to connect and communicate from any location. In an overpopulated nation like India finding a parking space for a car is a major concern especially in a metropolitan city, searching for a car parking space may sometimes result in traffic or wrong parkings might lead to penalties and traffic. Here an online booking system of networking devices based on IOT-cloud platform from where the user can get the information of parking slots empty or full in the area of choice and the user can get the information of the number of empty slots in that particular place and can book a parking slot in advance. The system of the model is presented in such a way that car parking update can be done offline without any booking and the update of the car parked at the slot is shown on the website in real time. The proposed project is implemented using 2G GSM SIM800A module with ESP8266 Wi-Fi module, we have used ThingSpeak open -source software for the IOT platform cloud database service through which an end user can use it to check the availability of the parking slot and book it accordingly.Here a systematic car parking sytem model is presented

When it comes to edge applications that require object detection based on computer vision, there are several models that can be used. However there is not an easy way to identify what is the best model for each application. In this paper we present a com prehensive comparison of several YOLO-based models for object detection targeting edge applications using single board computers (Raspberry pi). We compare several versions of YOLO (YOLOv5, v8 and v10) in terms of accuracy, inference time and training time. For the specific comparison we evaluate the performance for an edge application where the system has to identify the empty parking spots in a parking lot. The comparison allows developers to select the best model based on the application requirements.

Energy trading with electric vehicles provides opportunities to eliminate the high peak demand for electric vehicle charging while providing cost saving and profits for all participants. This work aims to design a framework for local energy trading with electric vehicles in smart parking lots where electric vehicles are able to exchange energy through buying and selling prices. The proposed architecture consists of four layers: the parking energy layer, data acquisition layer, communication network layer, and market layer. Electric vehicles are classified into three different types: seller electric vehicles (SEVs) with an excess of energy in the battery, buyer electric vehicles (BEVs) with lack of energy in the battery, and idle electric vehicles (IEVs). The parking lot control center (PLCC) plays a major role in collecting all available offer/demand information among parked electric vehicles. We propose a market mechanism based on the Knapsack Algorithm (KPA) to maximize the PLCC profit. Two cases are considered: electric vehicles as energy sellers and the PLCC as an energy buyer, and electric vehicles as energy buyers and the PLCC as an energy seller. A realistic parking pattern of a parking lot on a university campus is considered as a case study. Different scenarios are investigated with respect to the number of electric vehicles and amount of energy trading. The proposed market mechanism outperforms the conventional scheme in view of costs and profits.