Search

Augmented Reality (AR) technologies have recently been explored for application in dementia care, including cognitive training and screening, navigational assistance to find their way around, assistance to identify friends and family members, and assistance with activities of daily living. The presented work proposes the use of mobile and playful assessment of executive functions in the home environment by AR technology. We implemented a gamified version of the neuropsychological test ‘Tower of London’ (Shallice, 1982 [1]). It is played with poles of various size and colored balls, starting each exercise with a certain start and desired goal configuration of balls on poles. The novel AR-based technology enables hand-based interaction with artificial objects in the field of view and monitoring of the user’s gaze behavior via eye tracking towards the artificial objects of interest. A pilot study was performed with 12 healthy people that played the game with various degrees of difficulty concerning its planning depth. The results of the study demonstrate statistically significant correlation between the eye tracking features and the planning ability as well as cognitive flexibility measured by standardized psychological tests. This study provides first indication that executive functions can be estimated from playful AR-based interaction. Future work will focus on adjusting the game for persons with dementia, such as, by decreasing the difficulty level appropriately.

Insufficient tailoring of individual needs of nursing home residents can lead to standardized (leisure) activities. Virtual Reality (VR) provides the potential to offer a multimodal experience of individualized activities to residents. The aim of the VR4Care study is to explore attitudes, knowledge, and expectations regarding the use of VR glasses for (leisure) activities in female residents living in rural nursing homes. A mixed method approach in two phases (phase 1: interviews with a complementary standardized questionnaire; phase 2: measurement of affective states) was used. In total, 20 participants were interviewed regarding nine categories. The results show that the most described VR-scenarios for (leisure) activities include arts and crafts (e.g., sewing and knitting), followed by gardening (e.g., farmhouse garden), washing and ironing clothes and dancing (e.g., Austrian folk dances). This study serves as an important basis for scenario development and for testing the use of biosensor measurements in phase 2.

Optimization of log breakdown is still an open and active research topic. Even though it is proven that substantial economic gains (by quality improvement) could be achieved by acquiring knowledge about the internal structure of logs, industrial optimization applications taking into account internal defects have not yet been realized. X-ray computed tomography (CT) is the most used technique for imaging internal wood defects. Contrary to medical CT scanners where this technique is now perfectly mastered, industrial CT scanners should satisfy more extreme constraints to be used in a sawmill environment. Airport security scanners give an operational solution to this problem. A test of such a scanner in a sawmill demonstrates the operational validity of this assumption. Furthermore, a simple and non-automated optimization based on the data provided by this scanner clearly proved that value gains could be realized thus giving great hopes for a fully automated system.

Computer vision and image understanding processes are not very robust; small changes in exposure parameters or in internal parameters of algorithms can lead to significantly different results. A combination (fusion) of these results is profitable. The authors introduce an extended fusion concept dealing with different sources of information at external (world, scene, image) and internal (image description, scene description) levels and define the process of fusion. Each level requires its own procedure of quality measure and information fusion in order to yield a combination of components from several sources. Related work in the field is reviewed. Examples from the authors' own work cover remote sensing (improvement of classification results by fusion at the image level), medical image processing of ocular fundus images (automatic control point selection by fusion at the image description level) and the interpretation of Billard scenes (object identification by fusion at the scene description level). >