Author
Žaklina Spalević, Miloš Ilić, Nebojša Arsić
Title
LEGAL ASPECTS OF DATA MINING ALGORITHMS FOR STREAM PROCESSING IN TRAFFIC SURVEILLANCE
Abstract
A major challenge that all law-enforcement and intelligence-gathering organizations are facing is to accurately and efficiently analyze the growing volumes of crime data. In many fields, video surveillance can be used for that purpose. Video surveillance systems are now commonly used at various places like banks, hotels, schools, supermarkets. Tese systems are applicable for real-time monitoring or post checking. Current video surveillance systems have lower intelligence and it need people to monitor them. Today, video surveillance systems are used for traffic cameras, too. Traffic cameras are an innovative and extremely functional application of video surveillance technology. Whether they are recording traffic patterns for the future study and observation or monitoring traffic and issuing tickets for moving violations, traffic cameras are an explosively popular form of video surveillance. One way to find traffic patterns or to prevent traffic accidents and provide better road security is to use data mining techniques. With data mining, stream from many traffic cameras can be processed in real time. Property like this could provide some intelligence upgrade within systems, so they could make decision on their own without the need of people to monitor them. In this paper the authors described the data mining techniques for stream processing, pattern and abnormality detection in traffic surveillance systems. Each video recording and the use of recorded video on the court must be covered by legal regulations. Te authors investigated and extracted the appropriate articles from concrete Laws of Republic Serbia, covering this kind of problems.
Glavni izazov sa kojim se suočavaju sve bezbednosne organizacije i organizacije za prikupljanje obaveštajnih podataka jeste da precizno i efikasno analiziraju sve veći obim podataka o kriminalu. U mnogim oblastima video nadzor se može koristiti za tu namenu. Sistemi video nadzora se danas uobičajeno koriste na različitim mestima poput banaka, hotela, škola, samoposluga. Ovi sistemi u primeni su za nadzor u realnom vremenu ili za naknadnu proveru. U ovom trenutku sistemi za nadzor nemaju visoku inteligenciju i potrebni su ljudi da ih prate. Danas sistemi za video nadzor koriste i kamere za nadzor saobraćaja. Bilo da snimaju saobraćajne obrasce za buduća proučavanja ili služe za posmatranje i praćenje saobraćaja i izdavanje kazni za prekršaje, saobraćajne kamere su izuzetno popularan oblik video nadzora. Jedan od načina da se utvrde saobraćajni obrasci ili da se spreče saobraćajne nezgode i osigura bolja bezbednost na putu jeste i korišćenje tehnika za analizu podataka. Uz pomoć analize podataka, neprekinuti tok podataka sa mnoštva saobraćajnih kamera može se obraditi u realnom vremenu. Ovakvo svojsto moglo bi da obezbedi da se dogradi inteligencija u okviru sistema tako da bi oni mogli sami da donose odluke bez potrebe da ih ljudi prate. U ovom radu autori opisuju tehnike analize podataka za obradu neprekidnog niza podataka, otkrivanje obrazaca i nepravilnosti u sistemima za nadzor saobraćaja. Svaki video zapis i upotreba snimljenog video zapisa na sudu mora da bude pokrivena pravnim propisima. Autori su pregledali i izvukli odgovarajuće članove iz konkretnih zakona Republike Srbije koji se bave ovom vrstom problema.
Keywords
Clustering, Data Mining, Stream Processing, Traffic Surveillance, Law Regulation, Jurisprudence
Full Text
Download (PDF)
UDK: 351.811.123(497.11)