Illumination Independent and Accurate Marker Tracking Using Cross-Ratio Invariance

Marker tracking is used in numerous applications. Depending on the context and its constraints, tracking accuracy can be a crucial component of the application. This article first explains that the tracking accuracy depends on the illumination, which is not controlled in most applications. In particular, the authors show how corner detection can shift several pixels when lighting or background context change, even if the camera and the marker are static. Based on cross-ratio invariance, the proposed method helps reestimate the corner extraction so that the marker model's cross ratio corresponds to the one computed from the extracted corners in the image. The authors show on real data that their approach improves tracking accuracy, particularly along the camera depth axis, up to several millimeters, depending on the marker depth.