We propose an algorithm for detecting the mouth events of opening and closing. Our method is translation and ro- tation invariant, works at very fast speeds, and does not re- quire segmented lips. The approach is based on a recently developed optical flow algorithm that handles the motion of linear structure in a stable and consistent way.Furthermore, we provide a semi-automatic tool for gen- erating groundtruth segmentation of video data, also based on the optical flow algorithm used for tracking keypoints at faster than 200 frames/second. We provide groundtruth for 50 sessions of speech of the XM2VTS database [16] avail- able for download, and the means to segment further ses- sions at a relatively small amount of user interaction.We use the generated groundtruth to test the proposed al- gorithm for detecting events, and show it to yield promising result. The semi-automatic tool will be a useful resource for researchers in need of groundtruth segmentation from video for the XM2VTS database and others.