My main research area is visual recognition including object tracking, detection and action recognition using Boosting algorithms, Random Forest and Deep Learning. This field is especially interesting, because it is mostly about solving high-demanding learning problems like pedestrian detection, traffic sign recognition and therefore often requires new ideas both from Computer Vision as well as from the Machine Learning community. Additional scientific interests are Machine Learning using different sensors like inertial sensors, kinect cameras, time-of-flight cameras, thermal imaging cameras and the fusion of them. Others interests are embedded Computer Vision in the field of mobile app development on ARM platforms.
Projects are structured into the following categories:
- Action Recognition
- Object Recognition
- Object Detection
Please use the dropdown menu for detailed insights.