VILAB | Research | Publications | Projects | AISENSE

Hulya Yalcin: AISENSE
Marie Curie Career Integration Grants (CIG)
Grant Agreement No. PCIG9-GA-2011-294053

As average human life expectancy has risen dramatically over the last century, many countries in Europe are experiencing an ageing of their populations, a trend that is projected to continue until at least the middle of the twenty-first century. With an increasing number of people reaching increasingly higher ages, the ageing society is imposing many problems on society and the economy. Increasing retirement age, financial problems in pensions, health insurance and social security systems, rising medical costs, shortage in nursing personnel are aspects that are commonly attributed to the ageing society.

Considered to be the best preventive medicine for elderly people, increasing physical activity could potentially reduce the risk factor for developing chronic diseases. There is evidence from geriatric studies that physical activity may prevent or postpone the problems that come along with aging. Physically inactive people are twice as likely to develop cardiovascular diseases compared to those who are physically active. Moderate physical activity on three-to-five occasions per week reduces blood pressure. Physical activity contributes to increased bone density and can thus counteract osteoporosis. Moreover, it elevates physical function to levels which can guarantee more years of independent living. Finally, physically inactive people are at greater risk of developing depression than those who are physically active, while physically active persons may have reduced risk of developing Alzheimer’s disease. Physical activity plays an important role in maintaining health and effective function in older people and its significance emerges in public health issues such as disease prevention, maintenance of an healthy independent lifestyle in later life stages.

Since physical rehabilitation is a complex and long-term process that requires clinician experts and appropriate tools, technology that can successfully support the rehabilitation of individuals is of great interest to all the parties in sports and health industry. Technology is expected to play an increasingly active role in providing care to ageing populations. At a basic level, it can be applied to support medical professionals by relieving them of routine, mundane tasks. There is a new trend in the way physical exercise can be incorporated into a fitness training program, namely “exergaming”. Exergaming is a form of exercise through the use of video games and vitual environments whose main focus is the improvement and promotion of physical health of individuals. Exergames combined with activity monitoring technologies have been promising as a form of game that may make people involved in these video games more actively and physically.

AISENSE project aims to build an exergaming system and proposes a computer vision system for physical activity assessment. The overall objective of AISENSE is to build an exergaming system that allows elderly people to naturally interact with a virtual environment through their body movements and assess their physical performance. The game scenario is devised to engage elderly people in mild exercising that wouldn’t extremely physically challenge them and entertain them while assessing their physical performance.
Usually, exergames are games full of exercises which would have a positive effect on balance ability of the players. However, most games are not developed for the elderly. Sometimes, games could be boring, or too fast and difficult to operate for them. Game scenarios composed of very simple set of instructions asking elderly to stand upright or sit down in a rehabilitation game might lead elderly people get bored very quickly and quit exercising. Since the exer-gaming system in this project aims to engage elderly people in mild exercising that wouldn’t extremely physically challenge them and entertain them while assessing their physical performance, Dr. Yalcin collaborated with professionals in the areas of Neurology and Physical Training areas in order to develop an exer-gaming scenario that will be engaging, entertaining, increasing physical activity levels and has the capability of sustaining the attention of the subject.
Dr. Yalcin and her collaborators developed an exergaming scenario that involves recognizing certain objects in a room equipped with depth sensors and cameras. The exergaming scenario is built around the idea of driving the player to move around the room searching for some objects and performing certain tasks with those objects. The player is rewarded/penalized depending on whether he successfully accomplishes the subtasks of the game. The physical performance of the player is assessed both by evaluating his body pose throughout the exergaming duration as well as evaluating the measurements taken from a smartphone fastened securely on the body of the subject acting as a biosensor.
The overall objective of AISENSE is to build an exergaming system that allows elderly people to naturally interact with a virtual environment through their body movements and assess their physical performance. An exergaming scenario is devised to engage elderly people in mild exercising that wouldn’t extremely physically challenge them and entertain them while assessing their physical performance.
In this exergaming scenario, instructions to find certain objects in the room are spelt out by the exergaming software system. The elderly person first finds the particular object of interest in the room and then carries it to the other location again spelt out by the exergaming software system. There are toys randomly scattered in the room and the exergaming software system is already trained to recognize those toy objects. Each time two of those objects are randomly selected by the system. Elderly person is first asked to advance towards the first object and carry it next to the other randomly selected toy object by the system. He leaves first toy object next to second toy object. He then waits for the gaming system to assign the next task to him. The gaming system randomly selects a third object in the environment. The next task of the elderly person becomes grabbing the second toy object, searching for the third object in the room and carrying the second toy object towards the third toy object. The exergaming system verifies if the elderly person correctly locates the position of the third toy object, as well as if he was able to carry the second toy object successfully next to third toy object. While accomplishing these tasks, the elderly person interacts with the exergaming software system that he achieved the task by a predetermined gesture, which is already defined in the gesture vocabulary of the gaming system. The exergaming system rewards the player if the task is successfully accomplished. In case the player fails to find the object of interest, he makes another gesture to let the gaming system to know that he failed to achieve the task. This self-confessed failure of the player is also expressed to the gaming system by another predetermined gesture which is also defined in the gesture vocabulary of the gaming system. In that case, the player is penalized by decreasing his earned points. The gaming system then randomly selects another toy object and spells it out to the player and the game continues on up until the player makes a gesture that he wishes to quit the game.
The human-computer interaction is achieved through recognition of the body movements of the subject using multiple numbers of vision sensor platforms which have conventional cameras and depth sensors on them. The objects of interest in the exergaming environment are detected state-of-art 3-D object recognition algorithms. The research is focused on the developing of algorithms that allow different types of sensors to detect various aspects of the activity in the environment collectively. One of the major challenges of the AISENSE project has been ensuring that spatial and temporal features obtained from multiple set of sensors to be processed simultaneously and developing fusion algorithms to combine the results obtained from different modalities and to improve the recognition rate by strengthening performance of each sensor by the results of the other sensors. At the end of AISENSE project, it is expected to have an exergaming environment where different components of the exergaming system are working seamlessly together.

Publications based on the research carried out through AISENSE project can be found in Publications link.

VILAB | Research | Publications | Projects | AISENSE
Electronics and Communication Engineering
Istanbul Technical University
34469, Maslak/Istanbul

hulyayalcin@itu.edu.tr









































Begonvil ve Bisikletim