Wyniki wyszukiwania - BazTech

1

Vehicle classification using the convolution neural network approach

Trivedi Janak, Devi Mandalapu Sarada, Dhara Dave

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2021

|

z. 112

201--209

EN

We present vehicle detection classification using the Convolution Neural Network (CNN) of the deep learning approach. The automatic vehicle classification for traffic surveillance video systems is challenging for the Intelligent Transportation System (ITS) to build a smart city. In this article, three different vehicles: bike, car and truck classification are considered for around 3,000 bikes, 6,000 cars, and 2,000 images of trucks. CNN can automatically absorb and extract different vehicle dataset’s different features without a manual selection of features. The accuracy of CNN is measured in terms of the confidence values of the detected object. The highest confidence value is about 0.99 in the case of the bike category vehicle classification. The automatic vehicle classification supports building an electronic toll collection system and identifying emergency vehicles in the traffic.

2

Utilization of portable traffic detectors as the support for the data collection process in city logistics systems

Kijewska K., Iwan S.

Archives of Transport System Telematics

|

2019

|

Vol. 12, iss. 1

29--35

EN

One of the most important problem in the analysis of city logistics systems is data collection. The solution, which could support this process is utilization of independent, easy to use devices. The paper is focused on the example of utilization the portable road traffic detectors. These devices are easy to use tools, which can help to collect traffic data including the vehicles classification. The Authors will introduce an example of practical utilization of this kind of device, Sierzega SR4, as well as the advantages related to that.

3

Detection and classification of vehicles using selected methods of image processing

Marek-Latowicki M., Konior A., Ryguła A.

Archives of Transport System Telematics

|

2019

|

Vol. 12, iss. 4

10--14

EN

Methods of vehicles detection and classification using image processing are becoming increasingly popular, especially due to their non-invasiveness in the road surface and relatively lower installation and maintenance costs. These methods are commonly used in traffic flow monitoring systems and detection of vehicles with specific parameters. Importantly, the use of video analytics methods is still characterized by sensitivity to external disturbances such as variable weather conditions. The work discusses selected data processing mechanisms that have been applied within the functioning vehicle recognition subsystem. As part of the analysis, the effectiveness of the applied solutions and sensitivity to the occurring weather conditions were assessed.

4

Classification method for vehicles with a maximum permissible weight up to 3.5 tonnes

Ryguła A., Konior T., Piwowarczyk P.

Archives of Transport System Telematics

|

2019

|

Vol. 12, iss. 4

27--30

EN

Detecting and distinguishing vehicles with a maximum permissible weight up to 3.5 tonnes, among others required in the TLS 8+1 classification, due to the similar dimensions of selected vehicle groups is often a relatively complex process that requires the use of extensive classification methods. Detection of commercials vans is particularly important. Their parameters are similar to lorry vehicles and their incorrect classification, eg in systems of weighing vehicles in motion, results in the lack of information on exceeding the permissible total weight. The article presents the selected classification method and its effectiveness.

5

Ustalanie i weryfikacja danych technicznych w procesie klasyfikacji pojazdów dla celów ewidencji, rejestracji i badań technicznych

Balke M., Balke I., Karpiński R.

Autobusy : technika, eksploatacja, systemy transportowe

|

2018

|

R. 19, nr 6

339--342, CD

PL

W artykule przybliżono temat ewidencjonowania i klasyfikacji pojazdów w Polsce. Przytoczone zostały zarówno wybrane obowiązujące przepisy, jak również podstawowe zasady stosowane w przedmiotowym zakresie. Od 2004 roku w celu ujednolicenia klasyfikacji pojazdów oraz usprawnienia ich weryfikacji, do procedur stosowanych podczas rejestracji pojazdów włączono system pomocniczy, tj. elektroniczny katalog marek i typów pojazdów homologowanych oraz dopuszczonych do ruchu na terytorium Rzeczypospolitej Polskiej opracowywany przez Instytut Transportu Samochodowego tzw. Katalog ITS.

EN

The article brings closer the topic of records and classification of vehicles in Poland. Quoted have been, both selected the applicable laws as well as fundamental principles applied in the field. Since 2004, in order to harmonize the vehicles classification and improve their verification, the procedures used during the registration of vehicles have been supplemented by the auxiliary system, i.e. the electronic catalogue of makes and type-approved vehicles admitted to the operation in the territory of the Polish Republic elaborated by the Motor Transport Institute so-called “The ITS Catalogue”.

6

Assessment of the possibility of using selected statistic tools for testing long-term stability of weigh in motion systems

Ryguła A., Konior A., Piwowarczyk P., Kornalewski L.

Archives of Transport System Telematics

|

2018

|

Vol. 11, iss. 4

45--50

EN

The article presents selected statistical analyses of data registered by weigh in motion systems (WIM). Particular analyses are intended to determine the distribution of selected parameters and assess the possibility of using statistical measures to test the long-term stability of WIM stations. Dataset from the WIM system was the subject of the research. Dataset is using different measurement solutions and technology.

7

System nadzoru pojazdów na parkingach autostradowych za pomocą wideo monitoringu

Stawowy M., Gałązka K., Perlicki K., Czarnecki T.

Prace Naukowe Politechniki Warszawskiej. Transport

|

2017

|

z. 116

275--285

PL

W artykule przedstawiono metodę klaryfikacji pojazdów za pomocą wirtualny detektorów. Metoda ta oparta jest na detekcji ruchu w zdefiniowanych strefach (wirtualnych detektorach). Klasyfikacja pojazdów została przeprowadzona na podstawie ich wysokości. Wykonano badania na jednym z parkingów MOP na autostradzie A2. Przedstawiono wyniki badań.

EN

This article presents a method of vehicles classification using virtual detectors. This method is based on motion detection in defined zones (virtual detectors). Classification of vehicles was carried out on the basis of their height. The study was performed on one of the parking lots of the highway A2. Shows the results of the research.

8

Method of vehicle classification using discriminant analysis

Ryguła A., Brzozowski K., Maczyński A., Konior A.

Archives of Transport System Telematics

|

2017

|

Vol. 10, iss. 4

28--31

EN

Proper characteristics of the traffic flow is a particularly important issue in the process of optimizing the efficiency of transport networks as well as in the traffic control systems. One of the elementary parameters of traffic flows is the structure of vehicles, which evaluation, in case of the automatic systems, requires the implementation of proper algorithms and methods for vehicle classification. In the paper is presented a method of vehicles classification using the discriminant analysis. Furthermore authors developed a classifier, which aggregate data according to classification 8+1 in accordance with the TLS specifications and according with the classification presented in the specification COST 323. As input dataset to the classification method were used vehicle parameters recorded by the weight in motion systems.

9

Klasyfikacja i zliczanie pojazdów na podstawie danych wideo

Czapla Z.

Autobusy : technika, eksploatacja, systemy transportowe

|

2016

|

R. 17, nr 6

562--565

PL

Artykuł przedstawia metodę klasyfikacji i zliczania pojazdów na podstawie danych wideo. Wejściowa sekwencja obrazów składa się z ramek pobranych ze strumienia wideo otrzymywanego z kamery umieszczonej nad drogą. Poszczególne obrazy wejściowej sekwencji obrazów są przetwarzane oddzielnie. Definiowane są dwa pola detekcji, początkowe pole detekcji i końcowe pole detekcji. Obrazy wejściowej sekwencji obrazów są konwertowane do reprezentacji punktowej. Obliczana jest suma punktów krawędziowych dla każdego pola detekcji. Na podstawie sum punktów krawędziowych wyznaczane są stany pól detekcji. Analiza stanów pól detekcji umożliwia klasyfikację i zliczanie pojazdów. W artykule zamieszczono wyniki pomiarów.

EN

The paper presents a method of vehicle classification and counting on the basis of video data. The input image sequence consists of consecutive frames taken from the video stream obtained from the camera placed above a road. Individual images from the input image sequence are processed separately. Two detection fields are defined, the initial detection field and the final detection field. Images from the input image sequence are converted into point representation. The sum of the edge points is calculated for each detection field. On the basis of the sums of edge points, states of the detection fields are determined. Analysis of the states of the detection fields allows vehicle classification and counting. Experimental results are provided.

10

Automatic vehicle classification in systems with single inductive loop detector

Gajda J., Mielczarek M.

Metrology and Measurement Systems

|

2014

|

Vol. 21, nr 4

619--630

EN

The work proposes a new method for vehicle classification, which allows treating vehicles uniformly at the stage of defining the vehicle classes, as well as during the classification itself and the assessment of its correctness. The sole source of information about a vehicle is its magnetic signature normalised with respect to the amplitude and duration. The proposed method allows defining a large number (even several thousand) of classes comprising vehicles whose magnetic signatures are similar according to the assumed criterion with precisely determined degree of similarity. The decision about the degree of similarity and, consequently, about the number of classes, is taken by a user depending on the classification purpose. An additional advantage of the proposed solution is the automated defining of vehicle classes for the given degree of similarity between signatures determined by a user. Thus the human factor, which plays a significant role in currently used methods, has been removed from the classification process at the stage of defining vehicle classes. The efficiency of the proposed approach to the vehicle classification problem was demonstrated on the basis of a large set of experimental data.

11

A highly selective vehicle classification utilizing dual-loop inductive detector

Gajda J., Stencel M.

Metrology and Measurement Systems

|

2014

|

Vol. 21, nr 3

473--484

EN

In general, currently employed vehicle classification algorithms based on the magnetic signature can distinguish among only a few vehicle classes. The work presents a new approach to this problem. A set of characteristic parameters measurable from the magnetic signature and limits of their uncertainty intervals are determined independently for each predefined class. The source of information on the vehicle parameters is its magnetic signature measured in a system that enables independent measurement of two signals, i.e. changes in the active and reactive component of the inductive loop impedance caused by a passing vehicle. These innovations result in high selective classification system, which utilizes over a dozen vehicle classes. The evaluation of the proposed approach was carried out for good vehicles consisting of 2-axle tractor and a 3-axle semi-trailer.

12

Shape coefficient as a generic feature for vehicle classification

Czapla Z.

Logistyka

|

2014

|

nr 6

14094--14102, CD 6

EN

This article presents considerations of disturbances in logistic system of historic building's repair and reconstruction. Flows of physical, financial and information were characterized and classified. Special attention is paid to the flows of information between participants in the process of building production, where diagnosed frequent disturbances caused unavailability or lack of required expert. The main disturbances arising from construction works such as adverse weather conditions, construction failures caused bad technical condition of building which was not enough sufficiently diagnosed. Equally frequent disturbance is investment financing system, which allows to obtain funds from multiple external sources however, this system associated with a changes in work schedule and in extreme cases leads to the execution of the works with in violation of the principles of construction.

PL

W artykule podjęto tematykę zakłóceń systemu logistycznego przedsięwzięcia remontu i rekonstrukcji obiektu zabytkowego. Dokonano charakterystyki oraz klasyfikacji logistyki w zakresie przepływów informacyjno-decyzyjnych, fizycznych oraz finansowych. W publikacji zwrócono szczególną uwagę na istotę przepływów informacji pomiędzy uczestnikami procesu produkcji budowlanej, w których zdiagnozowano częste zakłócenia wynikające z niedyspozycyjności powołanych jednostek eksperckich lub ich braku. Do głównych zakłóceń wynikających z charakteru robót budowlanych należą zdarzenia losowe tj. niekorzystne warunki pogodowe a także awarie budowlane spowodowane złym stanem technicznym obiektu, który nie został dostatecznie zbadany na etapie diagnozowania konstrukcji. Równie częstym czynnikiem zakłócającym sprawne przeprowadzenie remontu lub renowacji obiektu zabytkowego stanowi system finansowania inwestycji, polegający na pozyskiwaniu środków z wielu źródeł zewnętrznych co wiąże się z zaburzeniem harmonogramu prac a w skrajnym przypadku prowadzi do realizacji robót niezgodnie ze sztuką budowlaną.

13

Wspomaganie systemu ewidencjonowania i klasyfikacji pojazdów z wykorzystaniem heurystycznych technik wnioskowania i analizy danych

Balke M., Balke I.

TTS Technika Transportu Szynowego

|

2013

|

R. 20, nr 10

3487--3495

PL

W artykule przybliżono temat ewidencjonowania i klasyfikacji pojazdów w Polsce. Przytoczone zostały zarówno wybrane obowiązujące przepisy, jak również podstawowe zasady stosowane w przedmiotowym zakresie. Podjęto temat heurystycznych technik wnioskowania i analizy danych oraz wykorzystywania ich w zakresie wspomagania systemu rejestracji i ewidencjonowania pojazdów. Od 2004 roku w celu ujednolicenia klasyfikacji pojazdów oraz usprawnienia ich weryfikacji, do procedur stosowanych podczas rejestracji pojazdów włączono system pomocniczy, tj. „Centralny Katalog ITS marek i typów pojazdów”. Katalog ITS stanowi bazę danych i wiedzy o markach i typach pojazdów homologowanych oraz dopuszczonych do ruchu na terytorium Rzeczypospolitej Polskiej.

EN

The article brings closer the topic of records and classification of vehicles in Poland. Quoted have been, both selected the applicable laws as well as fundamental principles applied in the field. The subject of heuristic reasoning techniques and data analysis, as well as their use in support of the registration and recording of vehicles, has been undertaken. Since 2004, in order to harmonize the vehicles classification and improve their verification, the procedures used during the registration of vehicles have been supplemented by the auxiliary system, i.e. the "ITS Central Catalogue of makes and types of vehicles". The ITS catalogue represents a database and knowledge on the makes and typeapproved vehicles admitted to the operation in the territory of the Polish Republic.

14

Road traffic parameters measuring system with variable structure

Burnos P., Gajda J., Marszałek Z., Piwowar P., Sroka R., Stencel M., Żegleń T.

Metrology and Measurement Systems

|

2011

|

Vol. 18, nr 4

659-666

EN

Systems of road traffic parameters measurement play a key role in the process of road traffic control, its supervision as well as in gathering and processing information for statistical purposes. Expectations of users of such systems mainly concern automation and provision of measurement continuity, possibility of selection of the measured road traffic parameters and high accuracy along with reliability of obtained results. In order to meet the requirements set for such systems, at the Department of Instrumentation and Measurement of the AGH University of Science and Technology in Cracow a new prototype system of road traffic parameters measurement - Traffic-1 - has been constructed. The innovativeness of the solution is manifested in the structure of the system that can be modified by the user adequately to current measurement needs and in the used algorithms of signals processing. The work contains a brief description of the constructed system with particular focus on the used innovations that are the result of many years of research work of the designers.

15

System pomiaru parametrów ruchu drogowego o zmiennej strukturze Traffic-1

Burnos P., Gajda J., Marszałek Z., Piwowar P., Sroka R., Stencel M.

Drogownictwo

|

2011

|

nr 9

283-285

PL

Systemy pomiaru parametrów ruchu drogowego (pprd) odgrywają kluczową rolę w procesie optymalnego sterowania ruchem drogowym, nadzorowania tego ruchu oraz zbierania i przetwarzania informacji do celów statystycznych. W artykule opisano system pprd Traffic-1. Innowacyjność rozwiązania przejawia się w strukturze systemu, która może być modyfikowana przez użytkownika odpowiednio do aktualnych potrzeb pomiarowych oraz w zastosowanych algorytmach przetwarzania sygnałów.

EN

Systems of road traffic parameters measurement play a key role in the process of road traffic control, its supervision as well as gathering and processing information for statistical purposes. The work contains a brief description of constructed system of road traffic parameters measurement Traffic-1. Innovativeness of the solution is manifested in the structure of the system that can be modified by the user adequately to current measurement needs and in the used algorithms of signals processing.

16

A simple vehicle classification framework for wireless audio-sensor networks

Malhotra B., Nikolaidis I., Harms J.

Journal of Telecommunications and Information Technology

|

2008

|

nr 1

43-50

EN

Vehicle tracking is one of the important applications of wireless sensor networks. We consider an aspect of tracking: the classification of targets based on the acoustic signals produced by vehicles. In this paper, we present a naive classifier and simple distributed schemes for vehicle classification based on the features extracted from the acoustic signals. We demonstrate a novel way of using Aura matrices to create a new feature derived from the power spectral density (PSD) of a signal, which performs at par with other existing features. To benefit from the distributed environment of the sensor networks we also propose efficient dynamic acoustic features that are low on dimension, yet effective for classification. An experimental study has been conducted using real acoustic signals of different vehicles in an urban setting. Our proposed schemes using a na¨ive classifier achieved highly accurate results in classifying different vehicles into two classes. Communication and computational costs were also computed to capture their trade-off with the classification quality.

17

Measurements of road traffic parameters using inductive loops and piezoelectric sensors

Burnos P., Gajda J., Piwowar P., Sroka R., Stencel M., Żegleń T.

Metrology and Measurement Systems

|

2007

|

Vol. 14, nr 2

187-203

EN

The basic problems corresponding to traffic measurements have been presented in the paper. The Authors gave a general overview of the parameters and characteristics describing the vehicles and traffic flow. The current sensor technologies used in measuring systems have been presented. Moreover the measuring systems used in traffic measurements have been described. Special at tention has been paid to the more sophisticated problems like a vehicle's classification based on the analysis of its magnetic signature and to vehicle's weigh-in-motion technique. The presented results base on the Authors' experience in designing and exploitation of the measuring systems equipped with inductive loops and piezoelectric sensors.

18

Data fusion applications in the traffic parameters measurement

Gajda J., Sroka R., Stencel M., Zeglen T.

Metrology and Measurement Systems

|

2005

|

Vol. 12, nr 3

249-262

EN

In the paper the problem of measuring road traffic parameters using systems with complex algorithms for measurement data processing is discussed. A characteristic feature of these systems is utilising there data fusion methods. This way a possibility has been created of linking the knowledge of measuring with an initial knowledge on the measurement object. The authors have shown that these methods allow to decrease measurement uncertainty, increase measurement reliability or limit the influence of the disturbing factors.

PL

Praca dotyczy zagadnienia pomiaru parametrów ruchu drogowego przy użyciu systemów realizujących złożone algorytmy przetwarzania danych pomiarowych. Cechą charakterystyczną omawianych systemów i algorytmów jest wykorzystanie w nich metod fuzji danych. W ten sposób stworzona została możliwość łączenia wiedzy pomiarowej z wiedzą wstępną posiadaną na temat obiektu pomiarowego. Autorzy wykazali, że metody te pozwalają zmniejszyć niepewność wyniku pomiaru, zwiększyć jego rozdzielczość lub ograniczyć wpływ czynników zakłócających. W pracy przedstawiono problemy związane z klasyfikacją pojazdów, ważeniem pojazdów w ruchu oraz kalibracją systemów ważących.