Multimedia & Vision Research Group (MMV Group)

 
MMV Group
Overview
People
Projects
Publications
Events
 

Analysis of (Human) Motion

Academic contacts: Dr Ioannis Patras
Involved people:
• Weiwei Guo • Sander Koelstra • Dr Irene Kotsia
• Vijay Kumar • Antonis Oikonomopoulos (Imperial College) • Ognjen Rudinovic (Imperial College)
• Stefanos Vrochidis

Summary:

The research aims at tracking and recognition of facial expressions, body poses and gestures and human actions in image sequences. The research is driven by applications in Multimodal Human Computer Interaction, Body games and Multimedia Indexing and Retrieval.

Sub-topics:

Human Action Recognition and Localisation in Image Sequences

Academic contacts: Dr Ioannis Patras
Involved people:
• Dr Irene Kotsia • Vijay Kumar

Figure 1: Localisation examples

This work aims at developing methods for recognition and localisation of human and animal action categories in image sequences. Once trained, the methods should be able to detect and localise in an unseen image sequence, all the actions that belong to one of the known categories. The methodologies will allow training the models in image sequences in which there is significant background clutter, that is in the presence of multiple objects/actions in the scene and moving cameras. No prior knowledge of the anatomy of the human body is a-priori considered, and therefore the models will be able to identify a large class of action categories, including facial/hand/body actions, animal motion, as well as interaction between humans and objects in their environment (such as drinking a glass of water).

Publications

Journals

  • A. Oikonomopoulos, I. Patras and M. Pantic, "Sparse B-spline Polynomial Descriptors for Human Activity Recognition". Image and Vision Computing Journal, Special Issue on Spontaneous Behaviour, vol. 27, no. 12, pp. 1814-1825, Dec. 2009.
  • A. Oikonomopoulos, I. Patras and M. Pantic, "Spatiotemporal Salient Points for Visual Recognition of Human Actions". IEEE Trans. Systems, Man, and Cybernetics, Part B, Vol. 36, No. 3, pp. 710-719, Jun. 2006.

Conferences

Facial (expression) analysis

Academic contacts: Dr Ioannis Patras
Involved people:
• Sander Koelstra • Dr Irene Kotsia • Ognjen Rudinovic (Imperial College)

Figure 2: Expression classes and related models

The main field of interest of this work includes computational intelligence and image processing techniques in order to recognize facial expressions in images and video.The facial expressions under examination include the six basic facial expressions (anger, disgust, fear, happiness, sadness and surprise), as defined by psychologists. Research is conducted not only in controlled environments, but also under miscalleneous conditions, such as occlusion, diferrent lighting/pose and spontaneous expressing of emotions.

Publications

Journals

Conferences

  • I. Patras and M. Pantic, "Particle Filtering with Factorized Likelihoods for Tracking Facial Features". In IEEE International Conference on Face and Gesture Recognition, Seoul, South Korea, May 2004.
  • E. Pogalin, A. Redert, I. Patras and E.A. Hendriks, "Gaze Tracking by Using Factorized Likelihoods Particle Filtering and Stereo Vision" In Int'l Symposium on 3D Data Processing, Visualization and Transmission, North Carolina, USA, Jun. 2006.

Human pose estimation

Academic contacts: Dr Ioannis Patras
Involved people:
• Weiwei Guo

Figure 3: Extimation of human pose from acquired data

This work focuses on the recovery of the configuration of body parts from a single 2D image. The research focuses on learning direct mappings from image observations to the parameters that describe the 3D body pose.

Publications

Conferences