Metin Soycan

Papers

Total Citations

H-Index

About

Metin Soycan is a leading researcher in the fields of geomatics engineering, sensor fusion, and autonomous navigation systems. His work focuses on integrating visual and inertial data to enhance the accuracy and robustness of positioning technologies, particularly in challenging environments where GPS signals are unreliable. Soycan’s most notable contribution is the development of the YTU dataset, a benchmark resource for visual-inertial odometry (VIO), which he paired with a recurrent neural network (RNN)-based approach to improve trajectory estimation. This work, published in 2021 and cited 20 times, has become a foundational reference for researchers exploring deep learning in VIO systems. Beyond this, Soycan has made significant strides in calibration techniques for multi-sensor platforms and the application of artificial intelligence to geospatial data analysis. His research has been instrumental in advancing autonomous vehicle navigation, robotics, and augmented reality technologies. With a career marked by rigorous experimentation and open-access datasets, Soycan continues to shape the future of intelligent positioning systems, inspiring students and engineers to push the boundaries of sensor-driven autonomy.