An a contrario space-time grouping framework for the detection of coherent motions
Abstract
This paper presents a method for detecting independent temporally-persistent motion patterns in image sequences. The result is a description of the dynamic content of video sequences in terms of moving objects, their number, image postion and approximate motion. It provides for each detected motion pattern a local trajectory as well as a confidence level in the detection. The method is based on local motion measurements extracted from short video segments. These measurements are mapped in an adequate grouping space where independent trajectories correspond to distinct clusters. The automatic cluster detection is handled in an a contrario framework, which is general and involves no parameter tuning. The method was successfully applied to real video sequences featuring rigid and non-rigid moving objects, static and mobile cameras, and distracting motions. The output of this method could initialize tracking algorithms. Applications of interest are robot navigation, car-driver assistance, video surveillance and activity recognition.
Origin : Files produced by the author(s)