Good Feature Selection for Least Squares Pose Optimization in VO/VSLAM
This work addresses accuracy improvement in VO/VSLAM systems, which is incremental as it builds on existing feature selection methods focused on efficiency.
The paper tackles the problem of selecting features that improve pose estimation accuracy in visual odometry and SLAM, introducing a Max-logDet metric and efficient algorithm that leads to accuracy gains with low overhead, as shown on a public benchmark.
This paper aims to select features that contribute most to the pose estimation in VO/VSLAM. Unlike existing feature selection works that are focused on efficiency only, our method significantly improves the accuracy of pose tracking, while introducing little overhead. By studying the impact of feature selection towards least squares pose optimization, we demonstrate the applicability of improving accuracy via good feature selection. To that end, we introduce the Max-logDet metric to guide the feature selection, which is connected to the conditioning of least squares pose optimization problem. We then describe an efficient algorithm for approximately solving the NP-hard Max-logDet problem. Integrating Max-logDet feature selection into a state-of-the-art visual SLAM system leads to accuracy improvements with low overhead, as demonstrated via evaluation on a public benchmark.