Visual Computing Lab

Director: Prof. Yonghuai Liu

The lab focuses on the topics in the general areas of 3D computer vision, image processing, pattern recognition, visual data analytics, computer graphics, virtual/augmented reality, human sensing and human-robot social interactions. The research is supported by the latest technologies such as  the Computer Augmented Virtual Environment (CAVE) and a range of state-of-the-art devices for data acquisition, output, visualisation, and full immersive experiences including: Tobii Eye X, Vive, Z-Space, Kinects, Hype Box, Emotive, Enobio BCI, Nao Robots, 3D Scanner and printer. It has the following goals:

(i) Connecting with stakeholders to impact society

(ii) Supporting students to test the latest visual computing techniques and acquire research-lead employability skills

(iii) Empowering researchers to solve theoretical and real-world problems in visual computing and utilising virtual and augmented reality technology

It aims to:

(i) Visualise the signal, image, shape and video data and their operations with the modern CAVE and other devices,

(ii) Enhance the visual data for high contrast and removal of unwanted factors,

(iii) Analyse and convert the visual data into semantically meaningful components, models, measurements, relevant knowledge and/or interesting responses and behaviours, and

(iv) Explore data visualisation and AR/VR simulation and applications in the real world such as medical imaging, training, computer aided instruction, CAD, systems automation, additive manufacturing, plant science, robotics, autonomous vehicles, intelligent surveillance, remote sensing, industrial quality assurance, etc.

It currently focuses on, but is not limited to, the following areas:

3D Computer Vision

  • 3D shape modelling, analysis and measurements
  • Camera calibration
  • 3D model search and query

Image Processing

  • Image noise removal, enhancement and super-resolution
  • Image analysis, decomposition, segmentation, classification and recognition

Pattern Recognition

  • Object detection, classification, recognition and tracking
  • Segmentation, clustering, consistency modelling
  • Biometrics

Computer Graphics, Virtual/Augmented Reality, Visualisation

  • Big-data visualisation
  • Reflectance modelling, rendering
  • Crowd modelling and simulation

Human Sensing and Human-Robot Social Interaction

  • Facial expression and emotion recognition
  • Human visual perception
  • Human behaviour representation, responses and prediction
  • Human activity/pose representation, estimation, classification, and recognition
  • CCTV surveillance and management

Lab Members

Dr. Ardhendu Behera, Prof. Yonghuai Liu, Dr. Peter Matthew, Dr. Peter Vangorp, Dr. Huaizhong Zhang

Last updated on Last updated on Was this page helpful? Yes No Thanks for your feedback! Please tell us more: