In the transport and traffic management system, tracking of vehicles on road is a prime importance vehicles are identified by reading their number plate, the existing system becomes complicated when there is a large number of vehicles being traced at different locations and therefore automatic license plate recognition ALPR is used to extract the contents of the number plate. The image can be fetched by using CCTV cameras with an MATLAB image processing tool. Besides these can be used for a surveillance purpose to facilitate the operations at the toll of many gated communities the identification of vehicles are done through vehicles through motion locating the license plate and accurately identifying the numbers in the license plate. Here we are going to use Adaptive Histogram Equalization AHE, Active contour method for region separation Optical Character Recognition OCR to recognize the characters and Deep Neural Network. DNN is used for classification and extracting the text as an alphanumeric characters and comparing the text with the predefined table created in MYSQL server and changing the status accordingly.

Entry and exit monitoring using license plate recognition

The metropolis of the future demands an efficient Automatic Number Plate Recognition (ANPR) system. Since every region has a distinct number plate format and style, an unconstrained ANPR system is still not available. There is not much work done on Pakistani number plates because of the unavailability of the data and heterogeneous plate formations. Addressing this issue, we have collected a Pakistani vehicle dataset having various plate configurations and developed a novel ANPR framework using the dataset. The proposed framework localizes the number plate region using the YOLO (You Only Look Once) object detection model, applies robust preprocessing techniques on the extracted plate region, and finally recognizes the plate label using OCR (optical character recognition) Tesseract. The obtained mAP score of the YOLOv3 is 94.3% and the YOLOv4 model is 99.5% on the 0.50 threshold, whereas the average accuracy score of our framework is found to be 73%. For comparison and validation, we implemented a LeNet Convolutional Neural Network (CNN) architecture which uses the segmented image as an input. The comparative analysis shows that the proposed ANPR framework comprising the YOLOv4 and OCR Tesseract has good accuracy and inference time for a wide variation of illumination and style of Pakistani number plates and can be used to develop a real-time system. The proposed ANPR framework will be helpful for researchers developing ANPR for countries having similar challenging vehicle number plate formats and styles.

/pdf/development-of-anpr-framework-for-pakistani-vehicle-number-2usgijlcqk.pdf

Development of ANPR Framework for Pakistani Vehicle Number Plates Using Object Detection and OCR

An automatic number plate detection (ANPD) and automatic number plate recognition (ANPR) systems are robust technologies that are used for detecting and recognizing the number plates of vehicles. In this paper, a new dataset, which is called North Iraq-Vehicle Images (NI-VI) of three provinces (Duhok, Erbil, and Sulaimani) for vehicle images, is presented. There are 1500 images in this dataset. They were gathered from real-time by using handled cameras to form a realistic dataset of the vehicle images. The main contribution of this work is the creation of a new dataset for license plate of vehicles in north Iraq with Arabic fonts in different and difficult conditions. The dataset includes three categories of images: rotated, scaled and translated images. The resolutions of images are 4288 x 2848 and 5184 x 3456. Moreover, some images created for bad weather conditions, such as snowy, dusty and low lighting. Some dirty plate images also considered in the dataset. The purpose of introducing this dataset is to provide and produce a realistic dataset for ANPD and as well as for ANPR systems.

Development of New Anpr Dataset for Automatic Number Plate Detection and Recognition in North of Iraq

With ever increasing number of vehicles, vehicular management is one of the major challenges faced by urban areas. Automation in terms of detecting vehicle license plate using real time automatic license plate recognition (RT-ALPR) approach can have many use cases in automated defaulter detection, car parking and toll management. It is a computationally complex task that has been addressed in this work using a deep learning approach. As compared to previous approaches, license plates have been recognized from full camera stills as well as parking videos with noise. On a dataset of 4800 car images, the accuracy obtained is 91% on number plate extraction from images, 93% on character recognition. Proposed ALPR system has also been applied to vehicle videos shot at parking exits. Overall 85% accuracy was obtained in real-time license number recognition from these videos.

Real Time License Plate Recognition from Video Streams using Deep Learning

Real-time Jordanian license plate recognition using deep learning

Automatic License Plate Recognition (ALPR) systems are employed for detection and recognition of license plate/number plate of vehicles. The performance of existing systems is well below the desired level. In this perspective, there is a definite need to propose a system to overcome the limitations of currently available systems. A new approach is being introduced in this paper for fast and efficient implementation of ALPR system. In this approach, the vertical edge detection algorithm is applied and removes unwanted edges by image normalization technique. The LP region is extracted by incorporating statistical and morphological image processing techniques. For character recognition, the template matching is employed for optical character recognition (OCR). The algorithm is tested on 500 real time images, which are acquired under different illumination conditions and from different scenes. Overall efficiency of the proposed method is 84.8% and the execution time is less than 0.5sec.

Automatic license plate recognition using extracted features

This paper presents a comparative analysis of different Motion Planning (MP) techniques currently popular for Autonomous Mobile Robot (AMR) applications. The discussion separates the techniques into two major categories: Classic and Heuristic. The techniques are assessed on the basis of their efficiency and effectiveness under varying constraints such as static, dynamically changing environments and environments with different complexities etc. At the end, results of the performances of the methods in a standard environment have been shown, the execution time and path lengths for each method have also been presented in the form of a table.

Comparative analysis of motion planning techniques for autonomous mobile robots

A novel control approach based on Linear Parameter Varying (LPV) is designed for Electric Vehicles (EVs) to address the crucial challenge of torque derating. A high fidelity Interior Permanent Magnet Synchronous Motor (IPMSM) based EV is modelled by taking into account the influence of temperature. A closed loop torque compensation control architecture with LPV based Field Oriented Control (FOC) has been designed to mitigate the thermal effects. In order to curtail deteriorating of FOC due to parameter variation, a robust LPV observer has been proposed to estimate the degraded Permanent Magnet (PM) flux linkage and instantaneous torque production caused by uncertainties in stator resistance arises due to thermal effects. A LPV gain scheduling robust current controller for inner control loop of FOC has also been designed which ensures internal stability. The LPV observer-controller gains are computed by solving Linear Matrix Inequalities (LMIs) using convex optimization and singular value decomposition. The experiments simulations have been performed for EV operation against the Worldwide Harmonized Light Vehicles Test Procedure (WLTP) class 3, New European Driving Cycle (NEDC) and Federal Test Procedure (FTP) driving cycles considering thermal effects in Matlab/Simulink. The efficacy of proposed control architecture for managing the derating torque of IPMSM based EV is demonstrated through the validity of results and detailed data analysis. The LPV based FOC is compared with conventional FOC control counterpart. The comparative experiments simulation results show that the overall Mean Square Error (MSE) value is exponentially reduced which establish superiority of the proposed control scheme.

Compensating Thermal Derated Torque of IPMSM Centric Electric Vehicles

Design and analysis of linear parameter varying control for IPMSM using new European driving cycle

Electric traction motors are the most integral part of Electric Vehicles (EV). A high fidelity Interior Permanent Magnet Synchronous Motor (IPMSM) commonly adopted in electrified powertrain is modelled. A closed loop control architecture of Field Oriented Control (FOC) is designed. The IPMSM operations against the real time environment using the Worldwide Harmonized Light Vehicles Test Procedure (WLTP) class 3 and New European Driving Cycle (NEDC) is experimented. The effectiveness and accuracy of the proposed scheme for nonlinear mathematical IPMSM model with complex dynamics are validated thorough extensive simulation experiments using MATLAB/Simulink.

Hassam Muazzam

Papers

Automatic license plate recognition using extracted features

Comparative analysis of motion planning techniques for autonomous mobile robots

Compensating Thermal Derated Torque of IPMSM Centric Electric Vehicles

Design and analysis of linear parameter varying control for IPMSM using new European driving cycle

Vector Control of IPMSM used in Electric Vehicles