We present an algorithm which can track the 3D pose of a hand held camera in real-time using predefined models of objects in the scene. The technique utilises and extends recently developed techniques for 3D tracking with a particle filter. The novelty is in the use of edge information for 3D tracking which has not been achieved before within a real-time Bayesian sampling framework. We develop a robust tracker by carefully designing the particle filter observation model: grouping line segments from a known model into 3D junctions and performing fast inlier/outlier counts on projected junction branches. Results demonstrate the ability to track full 3D pose in dense clutter whilst using a minimal number of junctions.