Wyniki wyszukiwania - BazTech

1

People tracking in video surveillance systems based on artificial intelligence

Nasry Abir, Ezzahout Abderrahmane, Omary Fouzia

Journal of Automation Mobile Robotics and Intelligent Systems

|

2023

|

Vol. 17, No. 1

59--68

EN

As security is one of the basic human needs, we need security systems that can prevent crimes from happen‐ ing. In general, surveillance videos are used to observe the environment and human behavior in a given location. However, surveillance videos can only be used to record images or videos, without additional information. There‐ fore, more advanced cameras are needed to obtain other additional information such as the position and move‐ ment of people. This research extracted this information from surveillance video footage using a person tracking, detection, and identification algorithm. The framework for these is based on deep learning algorithms, a popu‐ lar branch of artificial intelligence. In the field of video surveillance, person tracking is considered a challenging task. Many computer vision, machine learning, and deep learning techniques have been developed in recent years. The majority of these techniques are based on frontal view images or video sequences. In this work, we will compare some previous work related to the same topic.

2

Moving object detection for complex scenes by merging BG modeling and deep learning method

Lin Chih-Yang, Huang Han-Yi, Lin Wei-Yang, Ng Hui-Fuang, Muchtar Kahlil, Nurdin Nadhila

Journal of Artificial Intelligence and Soft Computing Research

|

2023

|

Vol. 13. No. 3

151--163

EN

In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall F-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.

3

A novel approach of voterank-based knowledge graph for improvement of multi-attributes influence nodes on social networks

Pham Hai Van, Duong Pham Van, Tran Dinh Tuan, Lee Joo-Ho

Journal of Artificial Intelligence and Soft Computing Research

|

2023

|

Vol. 13. No. 3

165--180

EN

Recently, measuring users and community influences on social media networks play significant roles in science and engineering. To address the problems, many researchers have investigated measuring users with these influences by dealing with huge data sets. However, it is hard to enhance the performances of these studies with multiple attributes together with these influences on social networks. This paper has presented a novel model for measuring users with these influences on a social network. In this model, the suggested algorithm combines Knowledge Graph and the learning techniques based on the vote rank mechanism to reflect user interaction activities on the social network. To validate the proposed method, the proposed method has been tested through homogeneous graph with the building knowledge graph based on user interactions together with influences in realtime. Experimental results of the proposed model using six open public data show that the proposed algorithm is an effectiveness in identifying influential nodes.

4

On site processing of video stream for mapping traffic parameters

Pamuła Wiesław, Kłos Marcin Jacek

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2022

|

z. 117

175--189

EN

Traffic surveillance provides crucial data for the operation of intelligent transportation systems. The growing number of cameras in the transport system poses a problem for the efficient processing of surveillance data. Processing of video data for extracting traffic parameters is usually done using image processing methods and requires substantial processing resources. An alternative way is to transform the video stream and map the traffic parameters using the obtained transform coefficients. Spatiotemporal wavelet transform of the video stream contents, using filter banks, is proposed for mapping traffic parameters. Performed tests prove good resilience to illumination changes of road scenes. Mapping errors are smaller than in the case of the commonly used video detectors at sites on multilane roads with low to moderate traffic load.

5

6 głównych trendów na rynku monitoringu wizyjnego w 2022 roku

Szymanek Bogumił

Dozór Techniczny

|

2022

|

z. 1

21--22

PL

Nadchodzący rok na rynku monitoringu wizyjnego w dużej mierze będzie zdominowany przez jedno wyrażenie – zaufanie. Niezależnie od tego czy mówimy o rozwoju sieci 5G, rozwiązań AI czy sieci zero trust, warto postawić na technologie, które w pewny sposób odpowiedzą na nasze potrzeby. Prezentujemy 6 głównych trendów, które będą znaczącą ramą w kontekście rozwiązań technologicznych w 2022 roku.

6

A Big Data Platform for Real-Time Video-Surveillance

Do Thi-Thu-Trang, Ha Tai-Huy, Kim Kyungbaek, Nguyen Quang-Thinh, Huynh Quyet-Thang, Nguyen Van-Quyet

Annals of Computer Science and Information Systems

|

2022

|

Vol. 33

95--101

EN

Nowadays, smart house facilities are strongly developed with the support of multiple security cameras to protect not only a house but also a building. A large amount of video data is produced by these cameras every day. Therefore, traditional data management systems face challenges in collecting, storing, and analyzing big video data. In such systems, it is difficult to find objects and their actions from video surveillance in the building because of either the consuming time or the lack of intelligent technology support. In this paper, we propose a novel big data platform for real-time video surveillance analysis based on the combination of distributed data frameworks and intelligent video processing libraries. The proposed platform is able to collect both real-time video streams and historical video data by using Kafka and Spark Structured Streaming frameworks. Furthermore, the proposed platform provides an intelligent video processing module for object detection by using OpenCV, YOLO, and Keras libraries. To evaluate the proposal, we deploy the proposed big data platform and implement a web interface to support end-user to analyze video surveillance. Through the results of the initial video querying implementation, we show the viability of the proposed platform.

7

On-water video surveillance: data management for a ship identification system

Popik Adrian, Zaniewicz Grzegorz, Wawrzyniak Natalia

Zeszyty Naukowe Akademii Morskiej w Szczecinie

|

2019

|

nr 60 (132)

56--63

EN

Video surveillance on both marine and inland waters still only plays a mainly auxiliary role in vessel traffic observation and management. The newest technical achievements in visual systems allow camera images to be used in more sophisticated tasks, such as automatic vessel recognition and identification in observed areas. With the use of deep learning algorithms and other artificial intelligence methods, such as rough sets and fuzzy sets, new functions can be designed and implemented in monitoring systems. In this paper the challenges that were encountered and the technology that has been developed in managing video streams are presented as well as the images needed for tests and proper operation of the designed Ship Recognition and Identification System (SHREC). The current technologies, typical setups and capabilities of cameras, with regard to existing on-water video monitoring systems, are also presented. The aspects of collecting the test data in the Szczecin Water Junction area are also described. The main part of the article focuses on presenting the video data pre-processing, storing and managing procedures that have been developed for the purposes of the SHREC system.

8

Object detection in the police surveillance scenario

Wilkowski Artur, Kasprzak Włodzimierz, Stefańczyk Maciej

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

363–-372

EN

Police and various security services use video analysis when investigating criminal activity. One typical scenario is the selection of object in image sequence and search for similar objects in other images. Algorithms supporting this scenario must reconcile several seemingly contradicting factors: training and detection speed, detection reliability and learning from sparse data. In the system that we propose a combined SVM/Cascade detector is used for both speed and detection reliability. In addition, object tracking and background-foreground separation algorithm together with sample synthesis is used to collect rich training data. Experiments show that the system is effective, useful and suitable for selected tasks of police surveillance.

9

Usuwanie tła w wideo nagraniach pochodzących z monitorowania basenu pływackiego

Reiter K., Kowalczuk Z.

Pomiary Automatyka Robotyka

|

2018

|

R. 22, nr 3

15--22

PL

Automatyczna obróbka obrazu w czasie rzeczywistym jest kluczowa dla wielu rozwiązań monitoringu wykorzystywanych m.in. w celach bezpieczeństwa. Często jednym z ważniejszych etapów obróbki jest oddzielenie tła od obiektów na pierwszym planie, tak aby wykluczyć wszystkie nieistotne informacje z obrazu. Celem pracy jest podsumowanie doświadczenia zdobytego podczas śledzenia pływaków oraz pokazanie możliwości skutecznego automatycznego nadzoru wideo osób korzystających z basenu. Porównano skuteczność działania dwóch wybranych algorytmów (MOG i KNN) przy użyciu różnych odwzorowań kolorów oraz omówiono zalety i wady analizowanych metod.

EN

Automatic real-time image processing is crucial for many (video surveillance) monitoring solutions used, among others for security purposes. Often one of the most important stages of computer vision processing is separating the background from the objects in the foreground, so as to exclude all irrelevant information from the image. The aim of this work is to summarize the experience gained while tracking swimmers and to show the possibility of effective automatic video surveillance of people using a swimming pool. The effectiveness of two selected algorithms (MOG and KNN) is compared using different color mappings and the advantages and disadvantages of the analyzed methods are discussed.

10

Moving cast shadow detection using block nonnegative matrix factorization

Yang X., Liu D., Zhou D., Yang R.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 2

229--234

EN

In recent years, moving cast shadow detection has become a critical challenge in improving the accuracy of moving object detection in video surveillance. In this paper, we propose two novel moving cast shadow detection methods based on nonnegative matrix factorization (NMF) and block nonnegative matrix factorization (BNMF). First, the algorithm of moving cast shadow detection using NMF is given and the key points such as the determination of moving shadow areas and the choice of discriminant function are specified. Then BNMF are introduced so that the new training samples and new classes can be added constantly with lower computational complexity. Finally, the improved shadow detection method is detailed described according to BNMF. The effectiveness of proposed methods is evaluated in various scenes. Experimental results demonstrate that the method achieves high detection rate and outperforms several state-of-the-art methods.

11

Abnormal prediction of dense crowd videos by a purpose-driven lattice Boltzmann model

Xue Y., Liu P., Tao Y., Tang X.

International Journal of Applied Mathematics and Computer Science

|

2017

|

Vol. 27, no. 1

181--194

EN

In the field of intelligent crowd video analysis, the prediction of abnormal events in dense crowds is a well-known and challenging problem. By analysing crowd particle collisions and characteristics of individuals in a crowd to follow the general trend of motion, a purpose-driven lattice Boltzmann model (LBM) is proposed. The collision effect in the proposed method is measured according to the variation in crowd particle numbers in the image nodes; characteristics of the crowd following a general trend are incorporated by adjusting the particle directions. The model predicts dense crowd abnormal events in different intervals through iterations of simultaneous streaming and collision steps. Few initial frames of a video are needed to initialize the proposed model and no training procedure is required. Experimental results show that our purpose-driven LBM performs better than most state-of-the-art methods.

12

Wykrywanie zdarzeń w monitoringu CCTV z wykorzystaniem technologii 3D

Balcerek J., Pawłowski P., Dąbrowski A., Konieczka A.

Elektronika : konstrukcje, technologie, zastosowania

|

2017

|

Vol. 58, nr 10

31--34

PL

W referacie przebadano rozpoznawanie istotnych szczegółów w wybranych scenach z monitoringu CCTV przez niewytrenowanych i wytrenowanych operatorów wspomaganych techniką stereowizyjną. Wykazano, że stereowizyjna akwizycja i wizualizacja scen pozwala dodać istotne informacje, które nie są możliwe do pozyskania bezpośrednio z obrazów 2D. Przebadano szacowanie odległości między obiektami, w tym pomiędzy ludźmi, podczas obserwacji stereowizyjnej. W trybie 3D jest ono, w większości przypadków, o wiele lepsze niż w trybie monoskopowym. Udowodniono, że stereowizja może również pomóc w oszacowaniu trajektorii i relacji pomiędzy poruszającymi się obiektami. Zautomatyzowane obrazowanie 3D poprawia dokładność i szybkość manualnej analizy typowych sytuacji występujących w systemach CCTV. Wyniki badań wskazują, że wprowadzenie efektu stereowizyjnego pozwala na lepsze niż w przypadku obrazów 2D rozpoznawanie zagrożeń przez operatora monitoringu wizyjnego i może być oferowane jako cenna opcja w systemach monitoringu.

EN

This paper presents an analysis of recognition accuracy of typical CCTV scenes watched by untrained as well as by trained viewers (e.g. CCTV operators) supported by the stereovision technique. The 3D acquisition and visualization allows to perceive important details of the scene view, which are not seen in the case of 2D imaging. The authors experimentally checked estimation of distances between objects and people in 3D imaging. In this mode the accuracy was better than for 2D observations. Moreover it was proven that the stereovision can help in estimation of intersecting trajectories and relations between moving objects. It can also improve accuracy and speed of manual analysis of typical cases form CCTV. The proposed 3D imaging could be an important option for operators of the monitoring systems.

13

Method for pre-processing of level crossing image

Rybalka R., Honcharov K.

Transport Problems

|

2015

|

T. 10, z. 1

79--86

EN

Actuality of problem in the improvement of transport safety at level crossings (LC) is caused by increasing the number of vehicles and reducing discipline of vehicle drivers. One of ways for solution of this problem is associated with using the video surveillance systems for monitoring danger area of level crossing. In such systems due to the limited bandwidth of data channel usually the image compression techniques are used. In this paper the pre-processing method for compression of images is presented. Proposed method accounts unequal subjective informational content of different LC image regions (using fuzzy logic and wavelet transform). Comparison of this method with plain set partitioning in hierarchical trees (SPIHT) technique showed that proposed method allows obtaining better result at image compression in terms of reconstruction quality and compression ratio.

RU

Актуальность проблемы повышения безопасности движения на железнодорожных переездах обусловлена увеличением количества автотранспортных средств и снижением дисциплины водителей. Одно из направлений для решения данной проблемы связано с использованием систем видеонаблюдения для мониторинга опасной зоны переезда. С учетом ограниченной полосы пропускания канала передачи данных в таких системах обычно применяется сжатие изображений. В данной работе представлен метод предварительной обработки для сжатия изображений. Предложенный метод учитывает неодинаковое субъективное информационное заполнение различных участков изображения переезда (используя нечеткую логику и вейвлет преобразование). Сравнение данного метода с простым методом пространственно упорядоченных иерархических деревьев (SPIHT) показало, что предложенный метод позволяет получить лучший результат при сжатии изображения с точки зрения качества восстановления и степени сжатия.

14

System wieloprotokołowej światłowodowej sieci przemysłowej w LW Bogdanka, zrealizowanej w oparciu o urządzenia firmy Westermo – koncepcja, doświadczenia z eksploatacji, możliwości rozbudowy

Wieczorek Z.

Napędy i Sterowanie

|

2015

|

R. 17, nr 7/8

78--79

PL

W 2011 roku w kopalni Bogdanka wdrożona została sieć technologiczna oparta o komunikację Ethernet i przełączniki szwedzkiej firmy Westermo. Projekt stworzyła firma INDSoft, a jego podstawowym założeniem było bezpieczeństwo, niezawodność wymiany informacji między poszczególnymi węzłami systemu automatyki oraz połączenie kilkudziesięciu sterowników, wielu punktów wizualizacji procesów, a dodatkowo integracja ciągle bezawaryjnie działających urządzeń i sterowników instalowanych na przełomie lat 1999/2000 z nowoczesnymi sterownikami obecnie wdrażanymi przez producentów systemów automatyki.

15

Wspieranie procesu zobrazowania informacji w systemach ratownictwa z wykorzystaniem aplikacji monitoringu wideo

Łubkowski P., Laskowski D.

Logistyka

|

2015

|

nr 4

7877--7885, CD2

PL

W artykule zaprezentowano problemy implementacji i testowania mobilnej aplikacji umożliwiającej zobrazowanie informacji z systemu monitoringu w celu wsparcia operacji ratowniczych. Zaproponowane rozwiązanie umożliwia dostęp do danych wideo z systemu monitoringu i akwizycji danych dla osób funkcyjnych biorących udział w kierowaniu operacji poprzez dowiązanie do istniejącej sieci systemu monitoringu lub do sieci zorganizowanej ad-hoc. Poprzez rozdział aplikacji na część kliencką i administracyjną występuje możliwość jej właściwego skonfigurowania do typu realizowanej misji i wprowadzenia określanych uprawnień dla wszystkich członków grupy ratowniczej. Przeprowadzone testy potwierdziły poprawność realizacji założonych funkcjonalności aplikacji.

EN

The article presents problems of implementation and testing a mobile application that allows visualization of information from the monitoring system to support rescue operations. The proposed solution allows access to the video data from the monitoring and data acquisition system for those involved in managing the operations through a link to an existing or ad-hoc organized network of monitoring system. Through the separation on the part of the client and administrator application there is a possibility of proper implementation of configuration to the type of mission and the introduction of defined permissions for all members of the rescue team. The con-ducted tests confirmed the correctness of implementation of the application assumed functionality.

16

Segmentation of Dishes for Customer Service Automation in a Self-service Canteen

Kryjak T., Krol D., Gorgon M.

Image Processing & Communications

|

2015

|

Vol. 20, no. 2

5--16

EN

The article describes research on dishes segmentation for the purposes of customer service process automation in a self-service canteen. The project assumptions and a prototype test stand are presented. The developed empty workspace detection and tray position determination algorithms are discussed. Finally, the chosen dishes segmentation algorithm is described and justified.

17

Low-Cost Scalable Home Video Surveillance System

Przybylo J, Grabska-Chrzastowska J., Korohoda P.

Image Processing & Communications

|

2014

|

Vol. 19, no. 2-3

51--58

EN

Automated and intelligent video processing and analysis systems are becoming increasingly popular in video surveillance. Such systems must meet a number of requirements, such as threat detection and real-time video recording. Furthermore, they cannot be expensive and must not consume too much energy because they have to operate continuously. The work presented here focuses on building a home video surveillance system matching the household budget and possibly making use of hardware available in the house. Also, it must provide basic functionality (such as video recording and detecting threats) all the time, and allow for a more in-depth analysis when more computing power be available.

18

Tablice informacyjne XSTD i system monitoringu wizyjnego firmy Pixel

Dyr T., Rusak Z.

Autobusy : technika, eksploatacja, systemy transportowe

|

2014

|

R. 15, nr 3

32-35

PL

Pixel sp. z o.o. od 1994 r. dostarcza zaawansowane technologicznie rozwiązania informatyczne, urządzenia elektroniczne i oprogramowanie stosowane w komunikacji publicznej. Obejmują one systemy elektronicznej informacji pasażerskiej, pobierania opłat za przejazdy, monitoringu wizyjnego oraz automatycznego zliczania pasażerów. W niniejszym artykule przedstawiono tablice informacyjne XSTD oraz system monitoringu wizyjnego oferowane przez firmę Pixel.

EN

Since 1994 Pixel Ltd. provides advanced technological solutions, electronic devices and software used in public transportation. They include the electronic passenger information systems, charging for rides, video surveillance and automatic passengers counting. This article presents XSTD information boards and video surveillance system offered by the Pixel company.

19

Segmentation of Football Video Broadcast

Maćkowiak S.

International Journal of Electronics and Telecommunications

|

2013

|

Vol. 59, No. 1

75-84

EN

In this paper a novel segmentation system for football player detection in broadcasted video is presented. Proposed detection system is a complex solution incorporating a dominant color based segmentation technique of a football playfield, a 3D playfield modeling algorithm based on Hough transform and a dedicated algorithm for player tracking, player detection system based on the combination of Histogram of Oriented Gradients (HOG) descriptors with Principal Component Analysis (PCA) and linear Support Vector Machine (SVM) classification. For the shot classification the several classification technique SVM, artificial neural network and Linear Discriminant Analysis (LDA) are used. Evaluation of the system is carried out using HD (1280×720) resolution test material. Additionally, performance of the proposed system is tested with different lighting conditions (including non-uniform pith lightning and multiple player shadows) and various camera positions. Experimental results presented in this paper show that combination of these techniques seems to be a promising solution for locating and segmenting objects in a broadcasted video.

20

Adaptive Method of Adjusting Flowgraph for Route Reconstruction in Video Surveillance Systems

Czyżewski A., Lisowski K.

Fundamenta Informaticae

|

2013

|

Vol. 127, nr 1-4

561--576

EN

Pawlak's flowgraph has been applied as a suitable data structure for description and analysis of human behaviour in the area supervised with multicamera video surveillance system. Information contained in the flowgraph can be easily used to predict consecutive movements of a particular object. Moreover, utilization of the flowgraph can support reconstructing object route from the past video images. However, such a flowgraph with its accumulative nature needs a certain period of time for adaptation to changes in behaviour of objects which can be caused, e.g. by closing a door or placing other obstacle forcing people to pass it by. In this paper a method for reduction of time needed for flowgraph adaptation is presented. Additionally, distance measure between flowgraphs is also introduced in order to determine if carrying out the adaptation process is needed.