Abstract. In this paper a novel face tracking approach is presented where optical flow information is incorporated into the Viola-Jones face detection algorithm. In the original algorithm from Viola and Jones face detection is static as information from previous frames is not considered. In contrast to the ViolaJones face detector and also to other known dynamic enhancements, the proposed face tracker preserves information about near-positives. The algorithm builds a likelihood map from the intermediate results of the Viola-Jones algorithm which is extrapolated using optical flow. The objects get extracted from the likelihood map using image segmentation techniques. All steps can be computed very efficiently in real-time. The tracker is verified on the Boston Head Tracking Database showing that the proposed algorithm outperforms the standard Viola-Jones face detector.

The authors present a novel face tracking approach where optical flow information is incorporated into a modified version of the Viola-Jones detection algorithm. In the original algorithm, detection is static, as information from previous frames is not considered; in addition, candidate windows have to pass all stages of the classification cascade, otherwise they are discarded as containing no face. In contrast, the proposed tracker preserves information about the number of classification stages passed by each window. Such information is used to build a likelihood map, which represents the probability of having a face located at that position. Tracking capabilities are provided by extrapolating the position of the likelihood map to the next frame by optical flow computation. The proposed algorithm works in real time on a standard laptop. The system is verified on the Boston Head Tracking Database, showing that the proposed algorithm outperforms the standard Viola-Jones detector in terms of detection rate and stability of the output bounding box, as well as including the capability to deal with occlusions. The authors also evaluate two recently published face detectors based on convolutional networks and deformable part models with their algorithm showing a comparable accuracy at a fraction of the computation time.