PROJECT TITLE :

MotionFlow: Visual Abstraction and Aggregation of Sequential Patterns in Human Motion Tracking Data

ABSTRACT:

Pattern analysis of human motions, that is useful in several analysis areas, needs understanding and comparison of different designs of motion patterns. However, working with human motion tracking information to support such analysis poses nice challenges. In this paper, we propose MotionFlow, a visual analytics system that gives an efficient overview of varied motion patterns primarily based on an interactive flow visualization. This visualization formulates a motion sequence as transitions between static poses, and aggregates these sequences into a tree diagram to construct a set of motion patterns. The system conjointly permits the users to directly replicate the context of information and their perception of create similarities in generating representative cause states. We have a tendency to give local and global controls over the partition-based mostly clustering method. To support the users in organizing unstructured motion information into pattern teams, we have a tendency to designed a set of interactions that enables searching for similar motion sequences from the information, detailed exploration of knowledge subsets, and making and modifying the cluster of motion patterns. To guage the usability of MotionFlow, we have a tendency to conducted a user study with six researchers with expertise in gesture-based mostly interaction design. They used MotionFlow to explore and organize unstructured motion tracking information. Results show that the researchers were ready to simply learn how to use MotionFlow, and therefore the system effectively supported their pattern analysis activities, including leveraging their perception and domain information.