A robust method for TV logo tracking in video streams

Most broadcast stations rely on TV logos to claim video content own-ership or visually distinguish the broadcast from the interrupting commercial block. Detecting and tracking a TV logo is of interest to TV commercial skipping applications and logo-based broadcast-ing surveillance (abnormal signal is accompanied by logo absence). Pixel-wise difference computing within predetermined logo regions cannot address semi-transparent TV logos well for the blending ef-fects of a logo itself and inconstant background images. Edge-based template matching is weak for semi-transparent ones when incom-plete edges appear. In this paper we present a more robust approach to detect and track TV logos in video streams on the basis of mul-tispectral images gradient. Instead of single frame based detection, our approach makes use of the temporal correlation of multiple con-secutive frames. Since it is difficult to manually delineate logos of irregular shape, an adaptive threshold is applied to the gradient im-age in subpixel space to extract the logo mask. TV logo tracking is finally carried out by matching the masked region with a known tem-plate. An extensive comparison experiment has shown our proposed algorithm outperforms traditional methods such as frame difference, single frame-based edge matching. Our experimental dataset comes from part of TRECVID2005 news corpus and several Chinese TV channels with challenging TV logos. 1