A Block Matching Technique for Object Tracking Based on Peripheral Increment Sign Correlation Image

Automatic detection and tracking of moving object is very important task for humancomputer interface (Black & Jepson, 1998), video communication/expression (Menser & Brunig, 2000), and security and surveillance system application (Greiffenhagen et al., 2000) and so on. Various imaging techniques for detection, tracking and identification of the moving objects have been proposed by many researchers. Based on (Collins et al., 2000; Yilmaz, 2006), the object detection can be divided at least into five conventional approaches: frame difference (Lipton et al., 1998; Collins et al., 2000), background subtraction (Heikkila & Silven, 1999; Stauffer & Grimson, 1999; McIvor, 2000; Liu et al., 2001), optical flow (Meyer et al., 1998), skin color extraction (Cho et al., 2001; Phung et al., 2003) and probability based approaches (Harwood et al., 2000; Stauffer & Grimson, 2000; Paragios et al., 2000). Based on (Wu et al., 2004), the object tracking method can be categorized into four categories: region based tracking (Wren et al., 1997; McKenna, 2000), active contour based tracking (Paragois & Deriche, 2000), feature based tracking (Schiele, 2000; Coifman et al., 1998) and model based tracking (Koller, 2000). The object identification is performed to evaluate the effectiveness of the tracking object especially when the object occlusion happens. It can be done by measuring the similarity between the object model and the tracked object. Some of the researches rely on color distribution (Cheng & Chen, 2006; Czyz et al., 2007). Regarding to our study, many of researchers have their own methods to solve the problem of object detection, object tracking and object identification. In object detection methodology, many researchers have developed their methods. (Liu et al., 2001) proposed background subtraction to detect moving regions in an image by taking the difference between current and reference background image in a pixel-by-pixel. It is extremely sensitive to change in dynamic scenes derived from lighting and extraneous events etc. In another work, (Stauffer & Grimson, 1997) proposed a Gaussian mixture model based on background model to detect the object. (Lipton et al., 1998) proposed frame difference that use of the pixel-wise differences between two frame images to extract the moving regions. This method is very adaptive to dynamic environments, but generally does a poor job of extracting all the relevant pixels, e.g., there may be holes left inside moving entities. In order to overcome disadvantage of two-frames differencing, in some cases threeframes differencing is used. For instance, (Collins et al., 2000) developed a hybrid method