Trajectons: Action recognition through the motion analysis of tracked features

The defining feature of video compared to still images is motion, and as such the selection of good motion features for action recognition is crucial, especially for bag of words techniques that rely heavily on their features. Existing motion techniques either assume that a difficult problem like background/foreground segmentation has already been solved (contour/silhouette based techniques) or are computationally expensive and prone to noise (optical flow). We present a technique for motion based on quantized trajectory snippets of tracked features. These quantized snippets, or trajectons, rely only on simple feature tracking and are computationally efficient. We demonstrate that within a bag of words framework trajectons can match state of the art results, slightly outperforming histogram of optical flow features on the Hollywood Actions dataset. Additionally, we present qualitative results in a video search task on a custom dataset of challenging YouTube videos.