Search

It has become a mandatory requirement for electric bike riders to wears helmet on riding. To automatically check if the electric bike rider wears helmet, a helmet and license plate detection approach based on improved YOLOv5m model is herein proposed, which can locate and recognize the license plate of the unhelmeted rider, so as to track down the violators. The model is trained with self-built dataset, uses DIOU loss function instead of GIOU loss function, and uses DIOU_NMS to replace weighted NMS so as to enhance the recognition ability for dense cycling scenes. Meanwhile, the ECA attention mechanism is added to the Backone and the Neck parts to im- prove the recognition accuracy for small and medium-sized targets. Then, the K-means algorithm is used to re- cluster the anchor frame size. Finally, the Mosaic data enhancement method is improved. The experimental results show that the mAP of the proposed approach is 92.7%, which is 2. 15,5. 7, and 6. 9 percentage points higher than the original YOLOv5m, YOLOv4 tiny, and Faster RCNN, respectively. It can be concluded that the improved YOLOv5m model can accurately recognize rider's helmet and electric bike's license plate. [ABSTRACT FROM AUTHOR]

In view of the problems of traditional Chinese license plate recognition methods, such as the requirement of scenes, poor real-time performance, and inability to deploy on edge devices, this study proposes a Chinese license plate detection and recognition method based on YOLO(You Only Look Once) in unconstrained scenes. This method is divided into two modules: license plate detection and license plate character recognition. In the license plate detection part, the improved YOLOv5 model is used to predict four groups of key points for license plate correction based on the prediction of target candidate regions, and the pre-training model trained on the COCO data set is used for training, which reduces the error detection problem caused by the complex environment and has high real-time performance. In the license plate character recognition part, the CRNN(Convolutional Recurrent Neural Network) model is improved, which greatly reduces the parameters and computation of the algorithm, so that it can be successfully deployed in various edge devices. Experimental results show that the proposed method can efficiently detect and recognize license plates in complex environments. The map value of the proposed license plate detection model is 3.0% higher than that of Retina-face in the license plate detection data set. Compared with LPR-Net, the accuracy of license plate character recognition model in license plate recognition data set is improved by 4.2%. [ABSTRACT FROM AUTHOR]

Recently, automatic license plate recognition (ALPR) has drawn much of attention from researchers due to the impressive performance of deep learning (DL) techniques. While a large number of methods for ALPR have been investigated, there are a few attempts emphasizing efficient yet accurate models for facilitating the deployment on traditional CPU boxes or low resource devices. In the present work, we propose lightweight and effective deep convolutional neuron networks to address the problems of license plate detection and recognition. Differing from traditional DL methods, the proposed models discard the use of max-pooling modules, belong to a single-phase object detector, and consist of alternating convolutional layers and Inception residual networks. Different strategies for character prediction are also studied and deeply discussed. To have more insight of convolutional features, we provide a sequence of visual snapshots or slices of feature maps learned by the network at different layers for a given input image. These data are useful to explain the model's behavior for the task of character recognition. Extensive experiments conducted on two public datasets, CCPD and AOLP, showed a promising improvement of LP detection and recognition accuracy. Interestingly, the full system can work on low-resource CPU machines with a real-time speed. [ABSTRACT FROM AUTHOR]

Automatic license plate recognition (ALPR) is a critical technology for intelligent transportation systems. Most existing ALPR methods are focused on specific application scenarios. Although there are a few methods that focus on unconstrained scenarios, they are very time-consuming. In this work, we propose an efficient ALPR (EALPR) framework, where we can handle distorted license plates (LP) caused by perspective problems with high efficiency. We design a light LPD structure based on efficient object detection methods and use anchor-free strategies for LPD to alleviate the problem of expensive costs. Benefitting from these optimizations and a united framework structure, the proposed EALPR has real-time efficiency. We evaluate our method on five datasets and the results show that our method achieves state-of-the-art accuracy: 98.15% on OpenALPR(EU), 95.61% on OpenALPR(BR), 99.51% on AOLP(RP), 88.81% on SSIG, 79.41% on CD-HARD. Additionally, our method achieves an impressive speed of 74.9 FPS (Frames Per Second), outperforming existing approaches and demonstrating its efficiency. Our source code can be accessed at https://github.com/wechao18/Efficient-alpr-unconstrained. [ABSTRACT FROM AUTHOR]

In this day and age, the programmed procurement of a tag and acknowledgment assumes a significant part in observing and coordinating vehicles in significant urban communities. It is hard to recognize a driver or proprietor of a vehicle that disregards traffic controls or plays out any incidental movement out and about. It will require a great deal of investment for a cop to review the plate of every vehicle. Subsequently, a mechanized tag acknowledgment framework can tackle these sorts of issues. This is the proposed technique; two Deep Learning calculations are utilized to distinguish the permit number and characters on the tag from the constant picture. The primary YOLOv5 model tracks down the main in the live video of a vehicle out and about. Then, at that point, cut out the area of the permit numbers in the video. The cut casing is then embedded into a second SSD (Single Shot Detection) to identify slugs on that tag. The prepared model acquires a high precision of 96.2% over a sum of 400 picture databases. [ABSTRACT FROM AUTHOR]

The automatic detection and recognition for motorcycle license plates present a very challenging task since they appear more compact and versatile than vehicle license plates. In this paper, we present an efficient detection and recognition system for motorcycle license plates based on decision tree and deep learning. It can be successfully carried out under various conditions, such as frontal, horizontally or vertically skewed, blurry, poor illumination, large viewing distances or angles, distortions, multiple license plates in an image, at night or interfered with brake lights, and headlights. Experimental results show that our system performs the best when testing with multiple license plates images under different conditions as compared against six state-of-the-art methods. Furthermore, our detection and recognition system have shown more accurate results than three commercial automatic license plate recognition systems in evaluation using accuracy, precision, recall, and F1 rates. [ABSTRACT FROM AUTHOR]

As an important core in the intelligent traffic management system, the technology and application of license plate recognition have become research focus. Detecting the accurate location of a license plate from a vehicle image is considered to be the most crucial step of license plate recognition, which greatly affects the recognition rate and speed of the whole system. Nevertheless, due to the low accuracy of license plate detection in natural scenes, further investigations are still needed in this field in order to make the detection process very efficient. In this paper, We have studied and implemented a convolutional neural network license plate detection algorithm based on transfer learning. According to the invention, new energy license plates and ordinary license plates are adopted as the research objects. The text detection model AdvancedEAST is trained on the license plate images through the transfer learning method, and experiments are carried out on the self-built license plate dataset. The experimental results show that the algorithm can better adapt to light complexity, low resolution, target interference, license plate tilt and other complex conditions. The license plate positioning algorithm has high accuracy in natural scenes, and it is superior to the traditional license plate detection methods. [ABSTRACT FROM AUTHOR]

License plate detection and recognition (LPDR) has attracted considerable attention in recent years, and many algorithms have presented the competitive performance on several datasets. However, there are still three significant issues to be addressed in this field. Firstly, most methods have poor detection performance in unconstrained scenarios with moving vehicles and highly distracting background objects. Secondly, existing systems generally focus on single image-based algorithms, yet traffic video sequences provide more effective information than individual frames for LPDR tasks. Thirdly, images and videos captured in complex environments may be adversely affected by distortions and low resolution, causing sensitive recognition performance and reduced robustness. To remedy these issues, we propose to automatically perform license plate detection, tracking, and recognition in real-world traffic videos and integrate them into a unified end-to-end framework via deep learning. The contributions of this paper are threefold: 1) A deep flow-guided spatiotemporal license plate detector is proposed to model the video contextual information by introducing optical flow and a novel spatiotemporal attention mechanism; 2) An online license plate tracker is developed to bridge video-based detection and recognition which utilizes both motion and deep appearance information, and innovatively, it can be end-to-end trained with the detector via multi-task learning; 3) The efficient quality-guided license plate recommender and recognizer are proposed to jointly perform stream recognition. The former recommends high-quality frames from video streams while the latter generates recognition results. We evaluate the proposed method on three traffic video-based license plate datasets, and ablation studies have been presented to verify the effectiveness of each component mentioned above. Moreover, extensive experiments are conducted for comparison with other approaches in different scenarios, and the results have demonstrated that our method achieves state-of-the-art performance on all datasets. [ABSTRACT FROM AUTHOR]

• A new problem of license plate/text detection in drone images is addressed. • The concept of Phase congruency in DCT domain is introduced for detection. • The combination of DCT and Phase congruency is new. • Deep learning is used in different way for eliminating false positives. • The combination of feature extraction and DCT-Phase is new. License plate number detection in drone images is a complex problem because the images are generally captured at oblique angles and pose several challenges like perspective distortion, non-uniform illumination effect, degradations, blur, occlusion, loss of visibility etc. Unlike, most existing methods that focus on images captured by orthogonal direction (head-on), the proposed work focuses on drone text images. Inspired by the Phase Congruency Model (PCM), which is invariant to non-uniform illuminations, contrast variations, geometric transformation and to some extent to distortion, we explore the combination of DCT and PCM (DCT-PCM) for detecting license plate number text in drone images. Motivated by the strong discriminative power of deep learning models, the proposed method exploits fully connected neural networks for eliminating false positives to achieve better detection results. Furthermore, the proposed work constructs working model that fits for real environment. To evaluate the proposed method, we use our own dataset captured by drones and benchmark license plate datasets, namely, Medialab for experimentation. We also demonstrate the effectiveness of the proposed method on benchmark natural scene text detection datasets, namely, SVT, MSRA-TD-500, ICDAR 2017 MLT and Total-Text. [ABSTRACT FROM AUTHOR]

License plate detection is the first and essential step of the license plate recognition system and is still challenging in real applications, such as on-road scenarios. In particular, small-sized and multi-oriented license plates, mainly caused by the remote and mobile camera, are challenging to detect. We propose a novel and applicable method for degraded license plate detection via vehicle-plate relation mining in this work. The proposed method can detect the license plate in a coarse-to-fine scheme. First, we propose to estimate the plate by using the relationships between the vehicle and the license plate, which can significantly reduce the search area and precisely detect small-sized license plates. Second, we present to robustly detect the multi-oriented license plate by regressing the four corners of the license plate in the local region. The whole network is constructed in an end-to-end manner, and codes are available at https://github.com/chensonglu/LPD-end-to-end. [ABSTRACT FROM AUTHOR]

The management of public security protection in forest areas has always been a problem that people lack attention to. It reveals the weakness of public security protection management in forest areas that committing crimes, illegal felling of trees and poaching animals. Our group has been committed to the application of machine vision in forest areas. In order to enhance the ability of forest area to prevent illegal cutting, this paper presents a novel algorithm of license plate detection which combines image defogging processing. This method uses the technique of contrast limited adaptive histogram equalization to remove the interference of image blurring in foggy, rainy and snowy days, and combines the features of the license plate such as color, aspect ratio, etc. to detect the license plate in fog, rain and snow weather. Compared with the ordinary license plate detection method, the result of this method has been greatly improved. The accuracy of detecting license plate in fog, rain and snow weather can reach 88. 00%, while the accuracy of ordinary license plate detection can only reach 82. 67%. This paper preliminarily proves the feasibility of the proposed algorithm in fog, rain and snow weather of forest areas. [ABSTRACT FROM AUTHOR]

Most automatic license-plate recognition (ALPR) systems use still images and ignore the temporal information in videos. Videos provide rich temporal and motion information that should be considered during training and testing. This study focuses on creating an ALPR system that uses videos. The proposed system is comprised of detection, tracking, and recognition modules. The system achieved accuracies of 81.473% and 84.237% for license-plate detection and classification, respectively. [ABSTRACT FROM AUTHOR]

With the continuous development of waterway trade, intelligent waterway supervision is gradually becoming an important way to maintain waterway safety. In this field, ship license plate (SLP) detection is importance for intelligent waterway supervision. However, in practical surveillance scenarios, detecting ship license plates (SLPs) is challenging because of small size, and text areas in complex backgrounds can also be mistakenly identified as SLPs. To solve these problems, we propose a Target Occlusion Contrast Network (TOCNet) for SLP detection. Firstly, to mitigate the effects of complex backgrounds, a novel Target Occlusion Contrast Learning (TOCL) approach is proposed, which is used to widen the decision boundary of the model and reduce false alarms. Secondly, to solve the problem that small targets are difficult to be detected, we design a Similarity Fusion Module (SFM), which effectively improves the detection performance of the model for small targets by similarity weight. Finally, to further improve the localization accuracy, we propose the task-oriented decoupled head (TDH), which facilitates the localization accuracy through selective fusion. Experimental results on both the SLPD dataset and the UFPR-ALPR dataset show that our proposed modules effectively improve the detection performance of the model, and the proposed TOCNet model exhibits a better detection performance than the other existing state-of-the-art (SOTA) models. Our code and dataset are publicly available at https://github.com/ssyuyi/tocnet. • The proposed contrast learning reduces the false alarm rate of the detection model. • The proposed similarity fusion module facilitates the detection for small targets. • A task-oriented decoupling head is proposed to facilitate detection accuracy. • A dataset that can be used for ship license plate detection is provided. • The proposed TOCNet model exhibits the performance of SOTA. [ABSTRACT FROM AUTHOR]

• License plate detection for multi-national vehicles in a multi-lane scenario. • Ability to deal with multi-national license plates of various colors and styles. • Capability to handle illumination variance. • Performance evaluation on datasets of China, Thailand, Pakistan, USA, UAE and Netherlands. • Superior performance as compared to conventional and deep learning approaches. Only a few methods in literature are effective for multi-national license plate detection in a multi-lane scenario. These methods are prone to illumination variance, complex background and weak-edged license plates. In this paper, we propose a novel illumination invariant method to handle multi-national vehicle license plates of different colors and styles. Red corona is initially used to detect the tail-lights of vehicles to establish region-of-interest as the license plates are in a vicinity of its tail-lights. The vertical edges within each region-of-interest are obtained using a unique approach that preserve license plate edges for improved performance. Heuristic energy map is then used to distinguish the license plate area. To validate the detected regions, high-level features extracted from AlexNet Convolutional Neural Network are used. Extensive experiments on the license plates of six countries show that the proposed approach not only ensures real-time performance, but also outperforms the conventional and deep-learning methods. [ABSTRACT FROM AUTHOR]

Currently, the conventional license plate location method fails to detect the license plate under complex road environments such as severe weather conditions and viewpoint changes. Besides, it is difficult for license plate location method based on machine learning to precisely locate the area of license plate. Moreover, license plate location method may incorrectly detect similar objects such as billboards and road signs as license plates. To alleviate these problems, this article proposes a new approach to vehicle license plate location based on new model YOLO‐L and plate pre‐identification. The new model improves in two aspects to precisely locate the area of license plate. First, it uses k‐means++ clustering algorithm to select the best number and size of plate candidate boxes. Second, it modifies the structure and depth of YOLOv2 model. Plate pre‐identification algorithm can effectively distinguish license plates from similar objects. The experimental results show that authors' proposed method not only achieves a precision of 98.86% and a recall of 98.86%, which outperforms the existing methods, but also has high efficiency in real time. [ABSTRACT FROM AUTHOR]

With the development of intelligent transportation and parking, license plate detection in open environments is in great demand. However, due to the clutter of background and variation of license plates, the existing methods could not make a good balance between accuracy and efficiency. A method based on semantic region proposals is presented. By thinking from the pixel level, this method first adopts a semantic segmentation convolutional network for license plate candidate region extraction. To improve accuracy of segmentation, an enhanced loss function is designed. Afterward, a classification and regression network based on the oriented bounding box regression algorithm is used for region verification and refinement. Experiments on three public datasets show that the proposed method can be adapted to license plate images captured under different scenarios and can achieve better performance than the state-of-the-art methods. © 2019 SPIE and IS&T [DOI: 10.1117/1JEI.28.2.023017] [ABSTRACT FROM AUTHOR]

Traffic surveillance is an important issue in intelligent transportation systems. Efficient and accurate vehicle detection is one challenging problem for complex urban traffic surveillance. As such, this paper proposes a new vehicle detection method using spatial relationship GMM for daytime and nighttime based on a high-resolution camera. First, the vehicle is treated as an object composed of multiple components, including the license plate, rear lamps and headlights. These components are localized using their distinctive color, texture, and region feature. Deriving plate color converting model, plate hypothesis score calculation and cascade plate refining were accomplished for license plate localization. Multi-threshold segmentation and connected component analysis are accomplished for rear lamps localization. Frame difference and geometric features similarity analysis are accomplished for headlights localization. After that, the detected components are taken to construct the spatial relationship using GMM. Finally, similar probability measures of the model and the GMM, including GMM of plate and rear lamp, GMM of both rear lamps and GMM of both headlights are adopted to localize vehicle. Experiments in practical urban scenarios are carried out under daytime and nighttime. It can be shown that our method can adapt to the partial occlusion and various lighting conditions well, meanwhile it has a fast detection speed. [ABSTRACT FROM AUTHOR]

Fully convolutional networks (FCNs) have shown outstanding performance in image semantic segmentation, which is the key work in license plate detection (LPD). An FCN architecture for LPD is presented. First, a multiscale hierarchical network structure is used to combine multiscale and multilevel features produced by FCN. Then, an enhanced loss structure that contains three loss layers is defined to emphasize the license plates in images. Finally, the FCN generates prediction maps that directly show the location of license plates. Experiments show that our approach is more accurate than many state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Many methods for multinational License Plate Detection (LPD) have been proposed in recent times but most of them are not sophisticated enough to handle complex backgrounds. Moreover, their ability to handle various environmental and illumination conditions has been limited and still needs improvement. In this paper, we propose a novel technique to detect license plates of vehicles regardless of their color, size, and content. As the rear vehicle lights are an essential part of any vehicle, we reduce the image processing area to eliminate the complex background by detecting the rear-lights as the license plates are in a certain range of these lights. Heuristic Energy Map (HEM) of the vertical edge information in the Region of Interest (ROI) is calculated and area with the dense edges is selected using a unique histogram approach which is considered to be the license plate. The proposed algorithm is tested on 855 images from various countries including China, Pakistan, Serbia, Italy and various states of America. Experimental results show that the proposed method is able to detect license plates 90.4% of times despite of complex backgrounds in 0.25 s on average that can achieve real time performance. [ABSTRACT FROM AUTHOR]

Due to the variation of background, illumination, and view point, license plate detection in an open environment is challenging. We propose a detection method by boundary clustering. To start with, a boundary map is obtained through Canny edge detector and removal of unwanted horizontal background edges. Second, boundaries are classified into different clusters by a density-based approach. In the approach, the density of each boundary is defined by the total gradient intensity of its neighboring and reachable boundaries. Also, the cluster centers and the number of them are determined automatically according to a minimum-distance principle. At last, a set of horizontal candidate regions with accurately located borders are extracted for classification. The classifier is trained on the histogram of oriented gradient feature by a linear support vector machine model. Experiments on three public datasets including images captured under different scenarios demonstrate that the proposed method outperforms several state-of-the-art methods in detection accuracy and its performance in efficiency is also comparable. [ABSTRACT FROM AUTHOR]

The presented framework uses the localization concept of multiwavelet transform and empirical mode decomposition (EMD) to locate number plate from vehicle. Multiwavelet transform is similar to wavelet transform but unlike wavelet, it simultaneously provides orthogonality, symmetry, short-support and vanishing moment. Multiwavelet is used to decompose the image and EMD helps to find the actual wave crest from the projected information provided by multiwavelet transform. The effectiveness of the proposed algorithm is improvised using pre- and post-processing steps which include image enhancement and skew correction respectively. Proposed algorithm has also been tested on single and double line number plate. The performance of the proposed algorithm has been tested on various countries’ number plates like Croatia, Austria, France, India and Greece, and in various conditions like shadow, dirt and blurry. Proposed algorithm has detected number plate with high accuracy and in relatively less time. [ABSTRACT FROM AUTHOR]

Abstract 1 1 HSI: hue-saturation-intensity; 2D: two-dimensional; 3D: three-dimensional; REG: special register. This paper presents a new algorithm for detecting and extracting license plates from a complex image by using a fuzzy two-dimensional Gabor filter. The filter parameters are fuzzified to optimize the Gabor filter. In particular, the orientation and wavelengths of the Gabor filter are fuzzified. Fuzzification of the wavelength results in greater selectivity. These parameters dominate the filtering results. Bell’s function and triangular membership function were proven to be the most efficient method for selecting the filter parameters in our experiments and were used for fuzzification. The use of these filters provided satisfactory results; the components of interest were efficiently extracted, and the procedure was found to be very noise-resistant. [ABSTRACT FROM AUTHOR]

An algorithm that projects image intensity along a radial line oriented at a specific angle enables the recognition of vehicular license plates at odd angles. The algorithm determines orientation angle, rotates the image to a horizontal perspective, and removes image noise from rotation to achieve recognition accuracy as high as 98 percent. [ABSTRACT FROM AUTHOR]

Abstract: Adaboost detector has been successfully used in object detection. In this paper, we propose a new License Plate (LP) detection technique based on multistage information fusion, which is adopted to reduce high false alarm rate in the conventional Adaboost detector. The proposed multistage information fusion system is composed of an enhanced Adaboost detector, a color checking module and an SVM detector, where the latter two stages further check whether the image patch that gets through the Adaboost detector is an LP. Test results of the dataset that consists of 950 real-world images show that the fusion reduces the false alarm rate. The proposed Fusion detector outperforms the conventional Adaboost detector throughout the ROC (Receiver Operating Characteristic) curve. The AUC (Area Under the Curve) of the best Fusion detector reaches 0.9081; however, the AUC of the best Adaboost detector is only 0.8441, which shows that the modification on feature extraction and the multistage information fusion significantly improve the LP detection performance. [Copyright &y& Elsevier]

Abstract: In this paper, we present a novel method to detect license plates in video sequences automatically. The framework mainly integrates the cascade detectors method and the Tracking Learning Detection (TLD) algorithm. The cascade detectors are used to detect license plates, and the TLD algorithm is adopted to track the license plate regions. The license plates in the first frame image are detected by the cascade detectors to build the original tracking list, the tracking results and the detection results in following frames will be compared, and the newly appearing license plate information will be added to the tracking list. Meanwhile, the tracking results existing in the current tracking list would be replaced by the corresponding detection results with higher degree of confidence. We demonstrate the effectiveness of our algorithm for license plate detection task on a road intersection dataset, and the experimental evaluation shows the detection performance has been greatly improved by synthetically using the detection and tracking strategy. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a license plate detection method based on the gradient information and a cascade detection framework. The proposed method consists of three main modules: image preprocessing, license plate detection and license plate confirmation. Considering the diversities of Chinese license plate, we first get the gradient images to unify plate forms through image preprocessing. The license plate will be detected roughly by using the cascade AdaBoost classifier in the next step. Finally, several heuristic judgment strategies and a voting-based method are used to verify the candidate license plates. The effectiveness of our method is validated with an experimental study in license plate detection. [Copyright &y& Elsevier]

Abstract: This paper presents an algorithm for extraction (detection) and recognition of license plates in traffic video datasets. For license plate detection, we introduce a method that applies both global edge features and local Haar-like features to construct a cascaded classifier consisting of 6 layers with 160 features. The characters on a license plate image are extracted by a method based on an improved blob detection algorithm for removal of unwanted areas. For license plate recognition (i.e., character recognition), an open source OCR is modified and used. Our proposed system is robust under poor illumination conditions and for moving vehicles. Our overall system is efficient and can be applied in real-time applications. Experimental results are demonstrated using a traffic video. [Copyright &y& Elsevier]

In this paper a license plate detection and recognition system for Iranian private cars is implemented. The proposed license plate localization algorithm is based on region elements analysis which works properly independent of distance (how far a vehicle is), rotation (angle between camera and vehicle), and contrast (being dirty, reflected, or deformed). In addition, more than one car may exist in the image. The proposed method extracts edges and then determines the candidate regions by applying window movement. The region elements analysis includes binarization, character analysis, character continuity analysis and character parallelism analysis. After detecting license plates, we estimate the rotation angle and try to compensate it. In order to identify a detected plate, every character should be recognized. For this purpose, we present 25 features and use them as the input to an artificial neural network classifier. The experimental results show that our proposed method achieves appropriate performance for both detection and recognition of the Iranian license plates. [ABSTRACT FROM AUTHOR]

Keeping a safe distance from the car in front of you is important in car accident prevention. This paper presents the use of a single CCD camera to measure the distance to the car in front at night. The distance from the car in front is estimated using the taillight, the license plate (LP), and distance measurement. The two taillights of a car are detected and extracted to be the salient features in estimation. Based on the proportionality of similar triangles, the distance between the CCD camera and the car in front is calculated. Since the width of the two taillights of a car depends on its type and shape, LPs are detected for accuracy enhancement. From the results, less processing time and high accuracy rates have been achieved using the proposed approach. [ABSTRACT FROM AUTHOR]

Automatic License Plate Detection (ALPD) is an integral component of using computer vision approaches in Intelligent Transportation Systems (ITS). An accurate detection of vehicles' license plates in images is a critical step that has a substantial impact on any ALPD system's recognition rate. In this paper, we develop an efficient license plate detecting technique through the intelligent combination of Faster R-CNN along with digital image processing techniques. The proposed algorithm initially detects vehicle(s) in the input image through Faster R-CNN. Later, the located vehicle is analyzed by a robust License Plate Localization Module (LPLM). The LPLM module primarily uses color segmentation and processes the HSV image to detect the license plate in the input image. Moreover, the LPLM module employs morphological filtering and dimension analysis to find the license plate. Detailed trials on challenging PKU datasets demonstrate that the proposed method outperforms few recently developed methods by producing high license plates detection accuracy in much less execution time. The proposed work demonstrates a great feasibility for security and target detection applications. [ABSTRACT FROM AUTHOR]

In smart surveillance and urban mobility applications, camera-equipped embedded platforms with deep learning technology have demonstrated applicability and effectiveness in identifying various targets. These use cases can be found in a variety of contexts and locations. It is critical to collect relevant data from the location where the application will be deployed. In this paper, we propose an integrated vehicle type and license plate recognition system using YOLOv4, which consists of vehicle type detection, license plate detection, and license plate character detection to better support the context of Korean vehicles in multilane highway and urban environments. Using our dataset of one to four multilane images, our system detected six vehicle classes and license plates with mAP of 98.0%, 94.0%, 97.1%, and 84.6%, respectively. On our dataset and a publicly available open dataset, our system demonstrated mAP of 99.3% and 99.4% for the detected license plates, respectively. From 4K high-resolution images, our system was able to detect minuscule license plates as small as 100 pixels wide. We believe that our system can be used in densely populated regions to address the high demands for enhanced visual sensitivity in smart cities and Internet-of-Things. [ABSTRACT FROM AUTHOR]

A reliable estimation of the traffic state in a network is essential, as it is the input of any traffic management strategy. The idea of using the same type of sensors along large networks is not feasible; as a result, data fusion from different sources for the same location should be performed. However, the problem of estimating the traffic state alongside combining input data from multiple sensors is complex for several reasons, such as variable specifications per sensor type, different noise levels, and heterogeneous data inputs. To assess sensor accuracy and propose a fusion methodology, we organized a video measurement campaign in an urban test area in Zurich, Switzerland. The work focuses on capturing traffic conditions regarding traffic flows and travel times. The video measurements are processed (a) manually for ground truth and (b) with an algorithm for license plate recognition. Additional processing of data from established thermal imaging cameras and the Google Distance Matrix allows for evaluating the various sensors' accuracy and robustness. Finally, we propose an estimation baseline MLR (multiple linear regression) model (5% of ground truth) that is compared to a final MLR model that fuses the 5% sample with conventional loop detector and traffic signal data. The comparison results with the ground truth demonstrate the efficiency and robustness of the proposed assessment and estimation methodology. [ABSTRACT FROM AUTHOR]

In this paper the authors describe a license plate (LP) detection method that can eliminate the restrictions on LP position, three-dimensional rotation and size. In the method, LP reference images, which replaced characters on the plate image by rectangles, are prepared beforehand. Using a frontal LP image, they are calculated by perspective projection at regular direction intervals and are calculated by a process of expanding and shrinking at regular size intervals. Using an input image of a vehicle passing through a scene and one reference image, a correlation map as a distribution of matching degree is obtained by a matched filter. By using the matched filter with every reference image, the correlation maps corresponding to the reference images are obtained. Detecting the highest value in all correlation maps, the matched reference image and the coordinates as LP position are decided. Furthermore, the shape of the LP in the input image is detected by fitting the LP frame, which is calculated using the matched reference image. In the paper, the proposed method is explained and an example of the experimental results is given. © 2009 Wiley Periodicals, Inc. Electron Comm Jpn, 91(9): 20–27, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10004 [ABSTRACT FROM AUTHOR]

As the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs small-sized vehicle plate detection with high precision in a coarse-to-fine scheme using vehicle–plate relationships. The direct detection branch detects the license plate directly in the input image, reducing false negatives in the indirect detection branch due to the miss of vehicles' detection. We propose a universal multidirectional license plate refinement method by localizing the four corners of the license plate. Finally, we construct an end-to-end trainable network for license plate detection by combining these two branches via post-processing operations. The network can effectively detect the small-sized license plate and localize the multidirectional license plate in real applications. To our knowledge, the proposed method is the first one that combines indirect and direct methods into an end-to-end network for license plate detection. Extensive experiments verify that our method outperforms the indirect methods and direct methods significantly. [ABSTRACT FROM AUTHOR]

License plate recognition is an emerging topic for real-time applications in smart city development because of automatic systems for toll fee-paying, traffic controlling, and vehicle detection. Speed of vehicles, unpredictable weather conditions such as night/low light/limited light images, and capturing images at different angles make recognition harder. This paper presents a new Fractal Series Expansion (FSE) model for license plate image enhancement. The proposed FSE model is justified because it estimates the high probability for the pixels which represent the license plate compared to the pixels which represent background irrespective of the above challenges, resulting in enhanced image. Besides, since the FSE model considers local information for estimating probability, the model has the ability to tackle non-uniform degradations as well as distortion affected multiple adverse factors. In addition to qualitative results, to validate the effectiveness of the proposed enhancement, quantitatively, recognition rates of the different methods before and after enhancement are computed. For this purpose, we have considered different datasets like dataset of Night License Plate Images (NLPI), which consists of images captured in the night and low lights environment, the UCSD benchmark dataset which provides poor and high quality day license plate images, etc. It is noted that recognition results after enhancement is higher than that of before enhancement, and hence our enhancement is useful and effective. • A new Fractal Series Expansion model for license plate image enhancement. • It tackles non-uniform degradations and distortions. • Different datasets including night license images are validated. [ABSTRACT FROM AUTHOR]

License plate detection (LPD) is the first and key step in license plate recognition. State-of-the-art object-detection algorithms based on deep learning provide a promising form of LPD. However, there still exist two main challenges. First, existing methods often enclose objects with horizontal rectangles. However, horizontal rectangles are not always suitable since license plates in images are multi-oriented, reflected by rotation and perspective distortion. Second, the scale of license plates often varies, leading to the difficulty of multi-scale detection. To address the aforementioned problems, we propose a novel method of multi-oriented and scale-invariant license plate detection (MOSI-LPD) based on convolutional neural networks. Our MOSI-LPD tightly encloses the multi-oriented license plates with bounding parallelograms, regardless of the license plate scales. To obtain bounding parallelograms, we first parameterize the edge points of license plates by relative positions. Next, we design mapping functions between oriented regions and horizontal proposals. Then, we enforce the symmetry constraints in the loss function and train the model with a multi-task loss. Finally, we map region proposals to three edge points of a nearby license plate, and infer the fourth point to form bounding parallelograms. To achieve scale invariance, we first design anchor boxes based on inherent shapes of license plates. Next, we search different layers to generate region proposals with multiple scales. Finally, we up-sample the last layer and combine proposal features extracted from different layers to recognize true license plates. Experimental results have demonstrated that the proposed method outperforms existing approaches in terms of detecting license plates with different orientations and multiple scales. [ABSTRACT FROM AUTHOR]