Detection of object tracking is an important part of object recognition analysis. In object tracking applications, object detection is the first step of video surveillance, where accurate object detection becomes important and difficult because there are still problems that arise like the shadow of the detected object (false detection). To overcome this many object tracking applications are constantly being developed to produce accurate object detection. In this case the clustering method is one of the methods that are considered efficient and able to provide segmentation results in the image better and adaptive to changes in the environment and instantaneous changes quickly. So this research proposes the development of the object-oriented FCM method of object segmentation to obtain accurate object detection results. For the development of FCM method this research will be done by using distance approach. The distance approach used is cambera, chebychef, mahattan, minkowski, and Euclidean to get accurate results.
Hierarchical video surveillance architecture: a chassis for video big data analytics and exploration