202 VEHICLE DETECTION BASED LANEMASKING AND BACKGROUND ELIMINATION USING K – MEANS CLUSTERING Ariyono Setiawan, Mochamad Hariadi Intelligence Neural Of Multimedia, Faculty Technology Of Industry Institute Technology Of Sepuluh Nopember Surabaya e-Mail : rmaryo4u@yahoo.com Abstract At this time, traffic congestion has been often found in big cities in Indonesia, especially at rush hour. One indicator of traffic congestion is the speed of travel or time travel on segments of the city road network. By looking at the correlation of traffic volume road network. In this thesis proposed an estimation method of detection of vehicles using masking and Land Background Elimination using K-Means Clustering. Among the various methods of motion estimation, algorithm K-Means Clustering is the most widely used and popular because of its simplicity in application. Of this thesis is expected measurement measures the speed of travel time and average travel roads can be understood so that the correlation relationship between the speed of traffic can be controlled by the Intelligence Traffic System. Keywords : Intelligence Traffic system, land masking, Background Elimination, K- Means Clustering, 1. Introduction At this time, traffic congestion has been often found in big cities in Indonesia, especially at rush hour. One indicator of traffic congestion is the speed of travel or time travel on segments of the city road network. By looking at the correlation of traffic volume road network. In this study proposed a method of detecting land vehicles using masking and Background Elimination using K-Means Clustering. Among the various methods of movement, the algorithm K-Means Clustering is the most widely used and popular because of its simplicity in application. Of this thesis is expected measurement measures the speed of travel time and average travel roads can be understood so that the correlation relationship between the speed f traffic can be controlled by the Intelligence Traffic System. movement is a process to determine the movement of an object in video sequences. Generally the movement is realized by motion vectors at selected points within the frame is now linked to another frame, called a frame of reference. Motion vector is a representation of the displacement of a point between he frame with the frame now. 1.1. Problem Definition In this study discussed the detection of vehicles using the method of land masking and Background Elimination using K-Means Clustering. System called the Intelligent Transport System (ITS) that can be used to monitor traffic Furthermore this system can be used for other purposes such as the function of providing information and enforcement of traffic discipline.