Ahmet Alp Kindiroglu

Learn More
This paper presents a framework for spotting and recognizing continuous human gestures. Skeleton based features are extracted from normalized human body coordinates to represent gestures. These features are then used to construct spatio-temporal template based Random Decision Forest models. Finally, predictions from different models are fused at score level(More)
In-vehicle information systems (IVIS) should minimize the cognitive load on the drivers to reduce any risk of accidents. For that purpose we built an experiment in which two alternatives for information display are compared. One alternative is the traditional information display method of showing a map with the target route highlighted in red. This is(More)
  • 1