Homography Decomposition Networks for Planar Object Tracking
This addresses a critical problem in robotics, visual servoing, and visual SLAM by improving tracking accuracy under difficult conditions, representing a strong specific gain rather than a foundational advancement.
The paper tackles the challenge of planar object tracking under rapid motion and large transformations by proposing Homography Decomposition Networks (HDN), which decomposes homography into two groups to stabilize the condition number, resulting in outperforming state-of-the-art methods on POT, UCSB, and POIC datasets.
Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM. Although the previous planar trackers work well in most scenarios, it is still a challenging task due to the rapid motion and large transformation between two consecutive frames. The essential reason behind this problem is that the condition number of such a non-linear system changes unstably when the searching range of the homography parameter space becomes larger. To this end, we propose a novel Homography Decomposition Networks(HDN) approach that drastically reduces and stabilizes the condition number by decomposing the homography transformation into two groups. Specifically, a similarity transformation estimator is designed to predict the first group robustly by a deep convolution equivariant network. By taking advantage of the scale and rotation estimation with high confidence, a residual transformation is estimated by a simple regression model. Furthermore, the proposed end-to-end network is trained in a semi-supervised fashion. Extensive experiments show that our proposed approach outperforms the state-of-the-art planar tracking methods at a large margin on the challenging POT, UCSB and POIC datasets.