Vladimir Kozitsky

Image simulation for automatic license plate recognition

Automatic license plate recognition (ALPR) is an important capability for traffic surveillance applications, including toll monitoring and detection of different types of traffic violations. ALPR is a multi-stage process comprising plate localization, character segmentation, optical character recognition (OCR), and identification of originating jurisdiction (i.e. state or province). Training of an ALPR system for a new jurisdiction typically involves gathering vast amounts of license plate images and associated ground truth data, followed by iterative tuning and optimization of the ALPR algorithms. The substantial time and effort required to train and optimize the ALPR system can result in excessive operational cost and overhead. In this paper we propose a framework to create an artificial set of license plate images for accelerated training and optimization of ALPR algorithms. The framework comprises two steps: the synthesis of license plate images according to the design and layout for a jurisdiction of interest; and the modeling of imaging transformations and distortions typically encountered in the image capture process. Distortion parameters are estimated by measurements of real plate images. The simulation methodology is successfully demonstrated for training of OCR.

Segmentation- and Annotation-Free License Plate Recognition With Deep Localization and Failure Identification

Automated license plate recognition (ALPR) is essential in several roadway imaging applications. For ALPR systems deployed in the United States, variation between jurisdictions on character width, spacing, and the existence of noise sources (e.g., heavy shadows, non-uniform illumination, various optical geometries, poor contrast, and so on) present in LP images makes it challenging for the recognition accuracy and scalability of ALPR systems. Font and plate-layout variation across jurisdictions further adds to the difficulty of proper character segmentation and increases the level of manual annotation required for training classifiers for each state, which can result in excessive operational overhead and cost. In this paper, we propose a new ALPR workflow that includes novel methods for segmentation- and annotation-free ALPR, as well as improved plate localization and automation for failure identification. Our proposed workflow begins with localizing the LP region in the captured image using a two-stage approach that first extracts a set of candidate regions using a weak sparse network of winnows classifier and then filters them using a strong convolutional neural network (CNN) classifier in the second stage. Images that fail a primary confidence test for plate localization are further classified to identify localization failures, such as LP not present, LP too bright, LP too dark, or no vehicle found. In the localized plate region, we perform segmentation and optical character recognition (OCR) jointly by using a probabilistic inference method based on hidden Markov models (HMMs) where the most likely code sequence is determined by applying the Viterbi algorithm. In order to reduce manual annotation required for training classifiers for OCR, we propose the use of either artificially generated synthetic LP images or character samples acquired by trained ALPR systems already operating in other sites. The performance gap due to differences between training and target domain distributions is minimized using an unsupervised domain adaptation. We evaluated the performance of our proposed methods on LP images captured in several US jurisdictions under realistic conditions.

Application of the SNoW machine learning paradigm to a set of transportation imaging problems

Machine learning methods have been successfully applied to image object classification problems where there is clear distinction between classes and where a comprehensive set of training samples and ground truth are readily available. The transportation domain is an area where machine learning methods are particularly applicable, since the classification problems typically have well defined class boundaries and, due to high traffic volumes in most applications, massive roadway data is available. Though these classes tend to be well defined, the particular image noises and variations can be challenging. Another challenge is the extremely high accuracy typically required in most traffic applications. Incorrect assignment of fines or tolls due to imaging mistakes is not acceptable in most applications. For the front seat vehicle occupancy detection problem, classification amounts to determining whether one face (driver only) or two faces (driver + passenger) are detected in the front seat of a vehicle on a roadway. For automatic license plate recognition, the classification problem is a type of optical character recognition problem encompassing multiple class classification. The SNoW machine learning classifier using local SMQT features is shown to be successful in these two transportation imaging applications.

Automated fault detection in violation enforcement cameras within Electronic Toll Collection systems

Electronic Toll Collection facilities offer travelers the ability to pay toll electronically, most commonly via Radio Frequency Identification (RFID) transponders placed within the vehicle. ETCs are complex systems comprising of a multitude of sensing and electronics equipment. To prevent violation, photo enforcement cameras are used to capture license plate images of the violating vehicle. To ensure adequate image quality and integrity of these cameras, it is standard maintenance practice to manually review camera images on a periodic basis. The manual review process can be expensive, error prone and may involve only a fraction of the images actually captured. To address this problem, we present algorithmic tools that can be used to automatically review images to detect any potential camera faults, thus, reduce human workload and increase maintenance efficiency. Wherever possible, we use no-reference or reduced-reference approaches for fault detection.

Vehicle speed estimation using a monocular camera

In this paper, we describe a speed estimation method for individual vehicles using a monocular camera. The system includes the following: (1) object detection, which detects an object of interest based on a combination of motion detection and object classification and initializes tracking of the object if detected, (2) object tracking, which tracks the object over time based on template matching and reports its frame-to-frame displacement in pixels, (3) speed estimation, which estimates vehicle speed by converting pixel displacements to distances traveled along the road, (4) object height estimation, which estimates the distance from tracked point(s) of the object to the road plane, and (5) speed estimation with height-correction, which adjusts previously estimated vehicle speed based on estimated object and camera heights. We demonstrate the effectiveness of our algorithm on 30/60 fps videos of 300 vehicles travelling at speeds ranging from 30 to 60 mph. The 95-percentile speed estimation error was within ±3% when compared to a lidar-based reference instrument. Key contributions of our method include (1) tracking a specific set of feature points of a vehicle to ensure a consistent measure of speed, (2) a high accuracy camera calibration/characterization method, which does not interrupt regular traffic of the site, and (3) a license plate and camera height estimation method for improving accuracy of individual vehicle speed estimation. Additionally, we examine the impact of spatial resolution on accuracy of speed estimation and utilize that knowledge to improve computation efficiency. We also improve accuracy and efficiency of tracking over standard methods via dynamic update of templates and predictive local search.