This research opens a new window to novel design paradigms for the optimization of Human-Machine interfaces, i.e. in the context of driver assistance functionalities in time critical decision situations. With our methodology we gain also further insights into the cognitive mechanisms that guide human attention in real-world closed-loop dynamic situations, such as driving.
For example, a driver assistance system realizes that the driver is distracted and that a potentially hazardous situation is emerging. Where should it guide the attention of the driver? Optimally to the spot that allows the driver to make the best decision. Pedestrian detectability has been proposed recently by us as a measure of the probability that a driver perceives pedestrians in an image. Leveraging this information allows a driver assistance system to direct the attention of the driver to the spot that maximizes the probability that all pedestrians are seen.
We have shown that this concept applies to natural dynamic driving scenes. We were able to establish a complex mapping to predict the optimal focus of attention in hazardous contexts, thus demonstrating the usefulness of our method.

Engel D  and Curio C  (2012) Detectability Prediction in Dynamic Scenes for Enhanced Environment Perception IEEE Intelligent Vehicles Symposium (IV 2012), accepted.
Engel D  and Curio C  (2011) Pedestrian Detectability: Predicting Human Perception Performance with Machine Vision IEEE Intelligent Vehicles Symposium (IV 2011), 1-7. 
 

With increasingly large image databases, searching in them becomes an ever more difficult endeavor. Consequently, there is a need for advanced tools for image retrieval in a webscale context. Searching by tags becomes intractable in such scenarios as large numbers of images will correspond to queries such as “car and house and street”. We present a novel approach that allows a user to search for images based on semantic sketches that describe the desired composition of the image. Our system operates on images with labels for a few high-level object categories, allowing us to search very fast with a minimal memory footprint. We employ a structure similar to random decision forests which avails a data-driven partitioning of the image space providing a search in logarithmic time with respect to the number of images. This makes our system applicable for large scale image search problems. We performed a user study that demonstrates the validity and usability of our approach.
 
Engel D , Browatzki B , Herdtweck C  and Curio C  (2011) Image Retrieval with Semantic Sketches , 13th IFIP TC13 Conference on Human-Computer Interaction (INTERACT 2011).

Experience indicates that the sense of presence in a virtual environment is enhanced when the users is able to actively move through it. When exploring a virtual world by walking, the size of the model is usually limited by the size of the available tracking space. A promising way to overcome these limitations are motion compression techniques, which decouple the position in the real and virtual world by introducing imperceptible visual-proprioceptive conflicts. Such techniques usually precalculate the redirection factors, greatly reducing their robustness. We propose a novel way to determine the instantaneous rotational gains using a controller based on an optimization problem. We present a psychophysical study that measures the sensitivity of visual-proprioceptive conflicts during walking and use this to calibrate a real-time controller. We have demonstrated the validity of our approach by allowing users to walk through VEs vastly larger than their space they can be physically tracked within.

Engel D , Curio C , Tcheang L , Mohler B  and Bülthoff HH  (2008) A psychophysically calibrated controller for navigating through large environments in a limited free-walking space 15th ACM Symposium on Virtual Reality Software and Technology (VRST 2008), ACM Press, New York, NY, USA, 157-164.