Helene Schulerud
Papers
2
Total Citations
13
H-Index
2
About
Helene Schulerud is a leading researcher in industrial machine vision and automated inspection, with a career dedicated to bridging the gap between simulation and real-world manufacturing. Her primary research areas include 3D imaging, robotic bin picking, and in-line quality control, where she has pioneered methods that replace manual, error-prone processes with robust, automated systems. Schulerud’s most impactful work, "Bin Picking of Reflective Steel Parts Using a Dual-Resolution Convolutional Neural Network Trained in a Simulated Environment" (2018, 9 citations), introduces a novel deep learning approach that overcomes the challenge of handling highly reflective industrial components. By training a dual-resolution CNN entirely in simulation, she demonstrated that synthetic data can effectively transfer to real-world bin picking tasks, significantly reducing the need for costly physical datasets. Her earlier foundational work, "In-line geometric fault detection in car parts based on structured light projection and image processing" (2003, 4 citations), developed a high-speed inspection system using Gray code and phase shifting to detect geometric defects in automotive parts. This system replaced manual inspection, achieving robust height measurement with standard CCD cameras and projectors. Schulerud’s contributions have advanced the practical deployment of computer vision in harsh industrial environments, making automated quality control more reliable and accessible.
Research Focus
Key Achievements
Top Papers
- 1
- 2