Object detection and localization is a crucial step for inspection and manipulation tasks in robotic and industrial applications. We present an object detection and localization scheme for 3D objects that combines intensity and depth data. A novel multimodal, scale- and rotation-invariant feature is used to simultaneously describe the object's silhouette and surface appearance. The object's position is determined by matching scene and model features via a Hough-like local voting scheme. The proposed method is quantitatively and qualitatively evaluated on a large number of real sequences, proving that it is generic and highly robust to occlusions and clutter. Comparisons with state of the art methods demonstrate comparable results and higher robustness with respect to occlusions.
I'm working towards my Ph.D. on the subject of rigid and non-rigid 3D object detection for industrial applications under the supervision of Dr. Slobodan Ilic. My work is funded by MVTec Software GmbH in Munich.
My research interests include
Rigid and non-rigid 3D object detection in point clouds
Advanced methods for Hough Transform
Object detection in multimodal data
Real-Time computer and machine vision algorithms
This video shows an application of our CVPR 2010 approach for rigid 3D object detection. The robot uses a stereo system to acquire a 3D scan of the scene and detects the object of interest within this scene.