Spectral Filter Tracking

Visual object tracking is a challenging computer vision task with numerous real-world applications. Here we propose a simple but efficient Spectral Filter Tracking (SFT) method. To characterize rotational and translation invariance of tracking targets, the candidate image region is models as a pixelwise grid graph. Instead of the conventional graph matching, we convert the tracking into a plain least square regression problem to estimate the best center coordinate of the target. But different from the holistic regression of correlation filter based methods, SFT can operate on localized surrounding regions of each pixel (i.e., vertex) by using spectral graph filters, which thus is more robust to resist local variations and cluttered background. To bypass the eigenvalue decomposition problem of the graph Laplacian matrix L, we parameterize spectral graph filters as the polynomial of L by spectral graph theory, in which L exactly encodes a k-hop local neighborhood of each vertex. Finally, the filter parameters (i.e., polynomial coefficients) as well as feature projecting functions are jointly integrated into the regression model. SFT can simply boil down to only a few line codes, but surprisingly it beats the correlation filter based model with the same feature input, and achieves the current best performance on the dataset [36] under the same feature extraction strategy (i.e., the existing VGG-Net model [32]). The code will be fully released in our website soon.