Aksel Sveier

Norwegian University of Science and Technology

Papers

Total Citations

H-Index

About

Aksel Sveier is a researcher specializing in computer vision and 3D perception, with a focus on geometric modeling and state estimation for industrial applications. His work centers on developing efficient methods for processing point cloud data, particularly for pose estimation and shape detection in manufacturing and robotics contexts. Sveier’s most cited paper, “Pose Estimation with Dual Quaternions and Iterative Closest Point” (2018, 5 citations), introduces a novel approach that combines unit dual quaternions with a multiplicative extended Kalman filter (MEKF) to estimate rigid body pose from 3D camera point clouds. This work addresses the challenge of filtering noisy measurements from moving sensors, offering a mathematically elegant solution for real-time tracking. In “Primitive Shape Detection in Point Clouds” (2016, 2 citations), Sveier leverages the prevalence of geometric primitives in industrial environments to simplify computer vision tasks, demonstrating how both pose and parameters of shapes like cylinders and planes can be efficiently extracted using 3D cameras. Though his citation counts are modest, Sveier’s contributions are practically significant for automation and quality control, providing foundational techniques that bridge sensor data and actionable geometric understanding. His research is particularly valuable for students and engineers seeking robust, computationally efficient methods for 3D perception in structured environments.