Andrzej Glowacz

The efficient real- and non-real-time make and model recognition of cars

Make and Model recognition of cars (MMR) has become an important element of automatic vision based systems. Nowadays, MMR utility is commonly added to traffic monitoring (e.g. Licence Plate Recognition) or law enforcement surveillance systems. Facing the growing significance of Make and Model Recognition of cars we have designed and implemented two different MMR approaches. According to their disparate assumption data of these implementations one is obligated to estimate different car models in milliseconds (with a bit less emphasis placed on its accuracy) while the other is aimed first of all to reach higher classification accuracy. Both the implemented MMR approaches, called Real-Time and Visual Content Classification, respectively, are described in this paper in detail and with reference to other MMR methods presented in the literature. Analyses of their performance with respect to classification accuracy and, in case of the Real-Time approach, to its response time are also presented, discussed and finally concluded.

Quality assessment for a visual and automatic license plate recognition

Video transmission and analysis is often utilized in applications outside of the entertainment sector, and generally speaking this class of video is used to perform specific tasks. Examples of these applications include security and public safety. The Quality of Experience (QoE) concept for video content used for entertainment differs significantly from the QoE of surveillance video used for recognition tasks. This is because, in the latter case, the subjective satisfaction of the user depends on achieving a given functionality. Recognizing the growing importance of video in delivering a range of public safety services, we focused on developing critical quality thresholds in license plate recognition tasks based on videos streamed in constrained networking conditions. Since the number of surveillance cameras is still growing it is obvious that automatic systems will be used to do the tasks. Therefore, the presented research includes also analysis of automatic recognition algorithms.

Recognition of Thermal Images of Direct Current Motor with Application of Area Perimeter Vector and Bayes Classifier

Abstract Infrared thermography can measure the temperature of a surface remotely. In this article authors present a diagnostic method of incipient fault detection. The proposed approach is based on pattern recognition. It uses monochrome thermal images of the rotor with the application of an area perimeter vector and a Bayes classifier. The investigations have been carried out for direct current motor without faults and motor with shorted rotor coils. The measurements were performed in the laboratory. The efficiency of recognition using the area perimeter vector and the Bayes classifier was 100 %. The investigations show that the method based on recognition of thermal images can be profitable for engineers. The proposed method can be applied in mining, metallurgy, fuel industry and in factories where electrical motors are used.

Quality Assessment for a Licence Plate Recognition Task Based on a Video Streamed in Limited Networking Conditions

Video transmission and analysis is often utilised in applications outside of the entertainment sector, and generally speaking this class of video is used to perform a specific task. Examples of these applications are security and public safety. The Quality of Experience (QoE) concept for video content used for entertainment differs significantly from the QoE of surveillance video used for recognition tasks. This is because, in the latter case, the subjective satisfaction of the user depends on achieving a given functionality. Moreover, such sequences have to be compressed significantly because the monitored place has to be seen on-line and it can be connected by an error prone wireless connection. Recognising the growing importance of video in delivering a range of public safety services, we focused on developing critical quality thresholds in licence plate recognition tasks based on videos streamed in constrained networking conditions.

Video Detection Algorithm Using an Optical Flow Calculation Method

The article presents the concept and implementation of an algorithm for detecting and counting vehicles based on optical flow analysis. The effectiveness and calculation time of three optical flow algorithms (Lucas-Kanade, Horn-Schunck and Brox) were compared. Taking into account the effectiveness and calculation time the Horn-Schunck algorithm was selected and applied to separating moving objects. The authors found that the algorithm is effective at detecting objects when they are subject to binarisation using a fixed threshold. Thanks to the specialized software the results obtained by the algorithm were compared with the manual ones: the total vehicle detection and counting rate achieved by the algorithm was 95,4%. The algorithm is capable to analyse about 8 frames per second (Intel Core i7 920, 2.66 GHz processor, Win7x64).

IOEM - ontology engineering methodology for large systems

The paper presents IOEM, a methodology for ontology development elaborated for the INSIGMA project. Although prepared for a particular use, the methodology is quite general and can be used in a large variety of IT projects requiring ontology components. It is particularly suitable for large and geographically distributed software projects. The methodology is oriented towards applications of ontologies in various phases of a software lifecycle: development and run-time.

Visual detection of knives in security applications using Active Appearance Models

In this paper, a novel application of Active Appearance Models to detecting knives in images is presented. In contrast to its popular applications in face segmentation and medical image analysis, we not only use this computer vision algorithm to locate an object that is known to exist in an analysed image, but–using an interest point typical of knives–also try to identify whether or not a knife exists in the image in question. We propose an entire detection scheme and examine its performance on a sample test set. The work presented in this paper aims to create a robust visual knife-detector to be used in security applications.

Automated qualitative assessment of multi-modal distortions in digital images based on GLZ

This paper introduces a novel approach to a qualitative assessment of images affected by multi-modal distortions. The idea is to assess the image quality perceived by an end user in an automatic way in order to avoid the usual time-consuming, costly and non-repeatable method of collecting subjective scores during a psycho-physical experiment. This is achieved by computing quantitative image distortions and mapping results on qualitative scores. Useful mapping models have been proposed and constructed using the generalised linear model (GLZ), which is a generalisation of the least squares regression in statistics for ordinal data. Overall qualitative image distortion is computed based on partial quantitative distortions from component algorithms operating on specified image features. Seven such algorithms are applied to successfully analyse the seven image distortions in relation to the original image. A survey of over 12,000 subjective quality scores has been carried out in order to determine the influence of these features on the perceived image quality. The results of quantitative assessments are mapped on the surveyed scores to obtain an overall quality score of the image. The proposed models have been validated in order to prove that the above technique can be applied to automatic image quality assessment.

Towards Robust Visual Knife Detection in Images: Active Appearance Models Initialised with Shape-Specific Interest Points

In this paper a novel application of Active Appearance Models to detecting knives in images is presented. Contrary to popular applications of this computer vision algorithm such as face segmentation or medical image analysis, we use it not only to locate an instance of an object that is known to exist in the analysed image. Using an interest point typical to knives we try to answer the question, whether a knife is or is non-existent in the image in question. We propose an entire detection scheme and examine its performance on a sample test set. The work presented in this paper aims at creating a robust visual knife detector that will find application in computerised monitoring of the public using CCTV.

Object detection in security applications using dominant edge directions

Abstract This paper presents a novel approach to object detection in images. We build on the existing work on detecting knives in images, which has previously attempted to solve the problem by using the well-established histogram of oriented gradients (HOG) features. We introduce a new feature set that allows for rapid initial object location in images, and can then be followed by the use of an object specific detector. This approach allows for speeding up the overall detection process, which has been demonstrated on the example of knives, and is in the position of bringing many object detectors closer to real-time execution speeds.