Camera pose estimation across video sequences is an important issue under several computer vision applications. In previous work, the most popular approach consists on optimization techniques applied over 2D/3D point correspondences for two consecutive frames from a video sequence. Unfortunately, these optimization techniques are iterative and depend on nonlinear optimizations applied over some geometric constraint. For real-time embedded applications, another approach, more efficient in terms of computational size and cost, could be a linear or closed-form solution for the camera pose estimation problem. In this work, we propose a new camera pose estimation approach where 2D pixel displacements are used as linear/dependent parameters for the camera pose estimation. Unlike previous work, camera poses are estimated without iterative behavior and without geometric constraints. As a results, our FPGA architecture delivers accurate/fast estimations (x50 faster than previous algorithms based on optimization techniques) for synthetic data and real world scenarios.
Fig. 1 The developed FPGA architecture