Login Form

Editors

Activity recognition results on UCF Sports and Holywood2

Table above shows the results, obtained on UCF Sports dataset (http://crcv.ucf.edu/data/UCF_Sports_Action.php). We report recognition rate with respect to the number...


Read More...

Computational efficiency and parallel implementation

The developed algorithms are computationally effective and the compositional processing pipeline is well-suited for implementation on massively parallel architectures. Many...


Read More...

Motion hierarchy structure

Our model is comprised of three processing stages, as shown in the Figure. The task of the lowest stage (layers...


Read More...

Server crash

After experiencing a total server failure, we are back online. We apologize for the inconvenience - we are still in...


Read More...

L1: motion features

Layer L1 provides an input to the compositional hierarchy. Motion, obtained in L0 is encoded using a small dictionary.


Read More...
01234

Relevance to the development of science or a scientific field

Successful realization of the research project objectives in scientific terms is directly relevant to the primary scientific field, the field of computer vision, as well as the development of the motion analysis. Learning and motion recognition is one of the central topics of computer, as well as artificial cognitive vision. The reason is the significant scientific challenge and the usability of the solutions for various automated systems based on efficient motion sensing and activity recognition. The planned research is therefore an important step forward in these areas, as it proposes a new paradigm of creating algorithms and systems to detect and interpret motion. The central contribution is a new approach based on learning of hierarchical compositional motion models, which provides a link to a similar concept of perception of the shape category. This leads to a more consistent approach of treating the shape and motion.

In addition to theoretical models we will develop their fast parallel implementations. Our results and methodology will therefore have a potential of being applied in other fields of science, such as the cognitive robotics. In the field of cognitive robotics, the project results will enable faster and more robust detection and interpretation of motion. This will extend the possibility of achieving complex tasks and interactions with the environment and users. Recently, much research in the field of cognitive robotics has focused on the integration of various sources of information into multimodal systems. One of our objectives in the project is to address the shape and motion information within a common theoretical framework. We can therefore expect that our findings can also be used in the subfield of artificial cognitive systems.

This website uses cookies to manage authentication, navigation, and other functions. By using our website, you agree that we can place these types of cookies on your device.

View e-Privacy Directive Documents

You have declined cookies. This decision can be reversed.

You have allowed cookies to be placed on your computer. This decision can be reversed.