Ahmet Burak Can

About

Ahmet Burak Can’s research centers on 3D computer vision, particularly object recognition and simultaneous localization and mapping (SLAM) using RGB-D sensors. His most cited work, “Volumetric Object Recognition Using 3-D CNNs on Depth Data” (2018, 27 citations), pioneered the use of 3D convolutional neural networks to directly process volumetric depth data, enabling robust recognition for applications in autonomous robotics and self-driving vehicles. This approach leveraged low-cost RGB-D sensors to achieve rapid progress in 3D understanding. In his earlier study, “A Comparison of Feature Detectors and Descriptors in RGB-D SLAM Methods” (2015, 11 citations), Can systematically evaluated visual features for SLAM systems, providing critical guidance for researchers building real-time mapping and localization pipelines. His work bridges deep learning and geometric computer vision, offering practical solutions for machines to perceive and navigate 3D environments. Can’s contributions are particularly valuable for students and engineers developing autonomous systems, as they demonstrate how to effectively combine depth data with neural architectures for reliable real-world performance.

Research Focus

Key Achievements

Top Papers

1. 1
   Volumetric Object Recognition Using 3-D CNNs on Depth Data

   27 citations · 2018
2. 2
   A Comparison of Feature Detectors and Descriptors in RGB-D SLAM Methods

   11 citations · 2015

Key Collaborators

Contact & Links