My main interests are focused on 3D motion analysis and classification, motion synthesis, human animation, and involve motion capture, inverse kinematics, and applications of conformal geometric algebra in graphics.
The project «DEMONSTRATION: DEep MOtioN SynThesis foR character AnimaTION» covers a wide range of multidisciplinary topics that are in line with the recent tendencies in computer graphics, character animation, and virtual reality. It aims at investigating modern trends in machine (deep, convolutional, adversarial, and reinforcement) learning, with ultimate target to provide ingenious solutions for overcoming the current limitations in character animation, and essentials for future improvements in a wide range of ambitious and challenging projects.
Motion capture is a technology used for turning the observations of a moving subject into 3D position and orientation information, stimulating our ability to define and virtually portray complex movements. The ALADDIN project aims at the development of such a technology that goes beyond conventional methods, is cost-effective, and minimizes the risks associated with capturing in dynamic situations. The proposed system is easily scalable and intrinsic, in the sense that measurements are not taken by external devices, enabling efficient capturing in outdoor environments, with state-of-the-art acquisition accuracy. More information can be found at the Cyprus Seeds Leaflet.
SCHEDAR aims to contribute in the safeguarding of our Intangible Cultural Heritage (ICH), and more specifically folk dancing, by providing novel solutions to the three key challenges of archiving, reusing & repurposing, and ultimately disseminating ICH creations. A comprehensive set of new guidelines will be devised, and a framework and software tools for leveraging existing ICH motion databases. Data acquisition will be undertaken holistically; encompassing data related to the performance, the performer, the kind of the dance, the hidden/untold story, etc. Innovative use of state-of-the-art multisensory Augmented Reality technology will be used to enable direct interaction with the dance, providing new experiences and training in traditional dance.
ReTrack aims to tackle the problem of animal monitoring and habitat utilization, specifically designed for small-sized reptiles. It will advance the scientific knowledge in the fields of (a) reptile locomotion, (b) behavioral analysis, and (c) conservation, through the development of innovative monitoring techniques and approaches. Utilizing state-of-the-art technology in remote sensing, advanced photogrammetry and image pattern recognition, ReTrack aims to create fine-scale micro-habitat utilization maps for two common Cypriot species, a lizard (Stellagama stellio) and a snake (Dolichophis jugularis), thus advancing site level management through the designing of more targeted, species based management and conservation actions.
Visit our 3D reptiles museum .
More details about my involvement in the project can be found at the behavioral analysis section of the project.
ITN-DCH aims -for the first time worldwide- to analyze, design, research, develop and validate an innovative multi-disciplinary and inter-sectorial research training framework that covers the entire lifecycle of digital CH research for a cost–effective preservation, documentation, protection and presentation of cultural heritage. CH is an integral element of Europe and vital for the creation of a common European identity and one of the greatest assets for steering Europe’s social, economic development and job creation. However, the current research training activities in CH are fragmented and mostly design to be of a single-discipline, failing to cover the whole lifecycle of Digital Cultural Heritage (DCH) research, which is by nature a multi-disciplinary and inter-sectorial research agenda.
This project aims at generating a virtual animated character that interacts, in real-time, with a real dancing performer to compose a contemporary dancing show. The proposed research will explore innovative topics with special interest in the area of computer animation, including methods which smoothly combine optical motion capture (mocap) data with kinematic techniques, human figure modelling, a novel methodology for motion classification and partial-body motion synthesis. The system will be adjusted dynamically according to the performers' actions and responses, offering the maximum possible interaction between the natural and virtual performer. Similar techniques can be adapted to the game industry, possibly for military or local law enforcement training simulators or other virtual character animations.
This project aims at creating a publicly accessible digital archive of dances using 3D motion capture data (with metadata); more emphasis will be given to Cypriot and Greek folk dancing.
This is an evolving project and data will be added to our database as we capture them over time.
Cyprus has a long and rich history of dance tradition which unfortunately, year after year, tends to be forgotten; thus, it is our duty to help documenting and disseminating our dance heritage to the younger generations. In this work, we aim to preserve the Cypriot folk dance heritage, creating a state-of-the-art publicly accessible digital archive of folk dances. Our dance library, apart from the rare video materials that are commonly used to document dance performances, utilises three dimensional motion capture technologies to record and archive high quality motion data of expert dancers. Apart from the goal of preserving this intangible cultural heritage by digitizing it, the project is interested in increasing the awareness of the local community to its dance heritage. To achieve this a 3D video game for children is developed to teach these folk dances to the younger generations.
SimPol VR (Synthesis of Dynamic Characters with motion capture data for human figure animation: Educating the police force) is a research project funded by the Cyprus Research Promotion Foundation in the area of Computer Graphics and more specifically in the sub-area of Human Body Animation. The project focuses in investigating the usability and applicability of Virtual Reality in training special forces. It proposes the development of a platform using Computer Graphics techniques (as oppossed to the existing video-based system that is restrictive), for the creation of a 3D Visualisation Tool enriched with tools suitable for the formation and customisation of dynamic scenarios. The proposed platform will be used as a simulator for training purposes by the Cyprus Police Emergency Response Unit. The user of the platform will be able to fully participate, act and interact with the environment. To achieve the above, research will be carried out in the area of Computer Animation for realistic avatar movement as well as the realistic and dynamic change of facial expressions. Smoothing of the surfaces on the avatar models used is another area that will be targeted by this project work. Researchers from Frederick University, the University of Cyprus, P.A. College, the University of Nicosia and abroad will be involved as well as acting trainers from the Cyprus Police Emergency Response Unit.
Inverse Kinematics is defined as the problem of determining a set of appropriate joint configurations for which the end effectors move to desired positions as smoothly, rapidly, and as accurately as possible. However, many of the currently available methods suffer from high computational cost and production of unrealistic poses. In this work, a novel heuristic method, called Forward And Backward Reaching Inverse Kinematics (FABRIK), is described and compared with some of the most popular existing methods regarding reliability, computational cost and conversion criteria. FABRIK avoids the use of rotational angles or matrices, and instead finds each joint position via locating a point on a line. Thus, it converges in fewer iterations, has low computational cost and produces visually realistic poses. Constraints can easily be incorporated within FABRIK and multiple chains with multiple end effectors are also easily supported.
© 2017 Andreas Aristidou