China
Africa
Explore chapters and articles related to this topic
Deep Learning-Based Indian Vehicle Number Plate Detection and Recognition
Published in S. Poonkuntran, Rajesh Kumar Dhanraj, Balamurugan Balusamy, Object Detection with Deep Learning Models, 2023
M. Arun Anoop, S. Poonkuntran, P. Karthikeyan
ANPR is automatic number plate recognition, consisting of two core ideas: plate detection and character extraction by the OCR method. It is helpful in the area of stolen vehicles and road safety. ANPR recognizes the number plate automatically as we know its name starts with the term “automatic” by performing OCR on images to read the license plate on vehicles. The main applications are highway monitoring, parking management, neighborhood law enforcement security and identifying over speeding based on average speed calculation criteria. The main categorization in our work is AFpMDlpd, meaning it consists of three keys. Keys are authentication, foggy image prediction, ML-based and DL-based vehicle number plate detection. The primary evaluation has been done based on these category keys (Figures 7.1–7.8).
Smart Parking System Using YOLOv3 Deep Learning Model
Published in Sam Goundar, Archana Purwar, Ajmer Singh, Applications of Artificial Intelligence, Big Data and Internet of Things in Sustainable Development, 2023
Narina Thakur, Sardar M N Islam, Zarqua Neyaz, Deepanshu Sadhwani, Rachna Jain
An enticing smart city research study is expanding knowledge and understanding about vehicle parking systems in various metropolitan areas. As a result, academics and practitioners have obtained an interconnected automobile parking dataset. Sometimes, during peak hours, parking lot operators do not register detailed information or register erroneous details into the system, creating issues for vehicle owners while leaving the parking lot and posing a massive security threat. In this paper, a robust solution to the difficulties is proposed by designing a system called automatic number plate recognition (ANPR) using the YOLOv3 deep learning model. As more cities suffer from traffic congestion and inadequate parking, the vehicle parking sector is still evolving. Predicting the site of parking has been a critical challenge in our daily lives for so many years. This is one area of smart parking systems that has received considerable attention. The authors propose the use of a neural networks (NN) [3] model to predict vehicle parking space, with a particular emphasis on smart parking systems and ANPR using deep learning models. This chapter also highlights quality concerns and areas for improvement in smart parking solutions currently being used in smart cities. Even though parking and transportation are such significant characteristics of daily life, there is a huge demand for innovative and cost-effective solutions. ANPR has numerous applications, including stolen vehicle detection, parking management, traffic flow monitoring, etc. As a result, researchers from all around the world have been studying this topic in order to improve ANPR performance in everyday situations.
Intelligent Transport Systems and Traffic Management
Published in Rajshree Srivastava, Sandeep Kautish, Rajeev Tiwari, Green Information and Communication Systems for a Sustainable Future, 2020
Pranav Arora, Deepak Kumar Sharma
Automatic number plate recognition (ANPR) is a type of specialized training model that uses computer vision-inspired optical character recognition technology to identify the number plates of automobiles after taking/creating a temporary photographic image of them. This technique is used by federal protection forces around the world to detect individual vehicles and is also used for parking entry in certain localities. These systems use infrared sensors, along with special cameras to take a photograph of the vehicle.
Speed distribution and safety effects of license plate recognition: Analysis combining crash and toll record data in Hunan Province, China
Published in Journal of Transportation Safety & Security, 2021
Zeming Yu, Hanchu Zhou, Helai Huang, Ye Li, Jia Qu
Emerging sources of data through license plate recognition (LPR) provide abundant and reliable information in estimating traffic conditions. Based on computerized video image-recognition technology, LPR system can automatically recognize the number plate of a vehicle (also known as the automatic number-plate recognition system, ANPR), which has outstanding performance for vehicle management on expressways. When the technology is applied in the expressway toll collection system, the license plate numbers of the passing vehicles are recognized by the LPR equipment at each entrance and exit of the expressway. In the process of using the system, first the image containing the vehicle license plate is captured by the shooting equipment, and then the transmission computer pre-processes the image information by using the video card. Second, the retrieval module is used to locate, search, and detect the license plate. The rectangular area of characters is segmented, and the characters are binary and divided into single characters. Finally, the corresponding recognition task is completed by license number output. The LPR data can be used to identify vehicle IDs and estimate their trajectories by matching vehicles identified by different sensors across the network, especially in estimating the speed-related characteristics of vehicles. For example, Zhan, Li, and Ukkusuri (2015) used LPR data to estimate the detailed traffic state such as travel time, the number of vehicles in the lane at the intersection level. Moreover, the LPR data is embedded in the model to estimate the vehicle speed profile, which helps support policymaking and evaluating policy implementation effects (Mo, Li, & Zhan, 2017; Rao, Wu, Xia, Ou, & Kluger, 2018). Vehicle restriction is mostly considered to be the most direct and impactful traffic demand management strategy.. For example, the odd-and-even policy allows vehicles on the road alternately based on the odd/even number of last digit on their license plates. However, the quantitative analysis of vehicle restriction policies’ effects is still considerably limited. With the help of the LPR data, the travel path of all vehicles can be controlled. The effect of vehicle restriction policies also has a more intuitive response: vehicle restrictions usually lead to more illegal travel and higher travel intensities (Liu, Li, Wang, & Shang, 2018). This reflects the extensive existence of non-ID vehicles, which includes illegal travel.