Efficient Object Tracking Using Optimized K-Means Segmentation and Radial Basis Function Neural Networks

Abstract—in this paper, an improved method for object tracking is proposed using radial basis function neuralnetworks. optimized k-means color segmentation is employed for detecting an object in first frame. next the pixelbasedcolor features (r, g, b) from object is used for representing object color and color features from surroundingbackground is extracted and extended to develop an extended background model. the object and extendedbackground color features are used to train radial basis function neural network. the trained rbfnn is employedto detect object in subsequent frames while mean-shift procedure is used to track object location. the performance ofthe proposed tracker is tested with many video sequences. the proposed tracker is illustrated to be able to trackobject and successfully resolve the problems caused by the camera movement, rotation, shape deformation and 3dtransformation of the target object. the proposed tracker is suitable for real-time object tracking due to its lowcomputational complexity.