Image Processing and Mixed Reality
The Image Processing and Mixed Reality group at Birmingham City University consists of research staff and academic members from the School of Computing and Digital Technology.
The group researches a range of new and exciting applications for analysing and processing still image and video data, and is linked directly to a wide variety of application domains. These include medical image analysis systems, video and image distribution systems, low-level image assessment, image feature classification, real-time video processing, mixed, augmented and virtual reality, live television studios and real-time video processing systems.
Red Alert Project (Horizon 2020)
RED-Alert brings the best of European research and innovation together to fight terrorism with a consortium of 16 organizations from 8 countries, including 6 European law enforcement agencies, supported by Europol’s counter-terrorism unit. The project starts in June 2017 and will last 3 years.
RED-Alert harnesses the power of artificial intelligence to detect terrorist content, based on a unique combination of technologies such as natural language processing, semantic media analysis, social network analysis and complex event processing
3D surface segmentation of Computed Tomography (CT) Images
This work is linked with the School of Health and Social Care at Birmingham City University and is focused on improving the segmentation of soft tissue within CT images through statistical model analysis and classification.
Problems associated with the accurate segmentation of CT data are being analysed and new methods of guided segmentation are being developed. This will aim to improve both the accuracy of medical segmentation software and procedure planning systems.
Objective performance evaluation of edge and surface detection methods
This work is looking at new methods for objectively assessing the performance of low-level edge detection algorithms. Fully quantitative measures have been developed which assess the similarity between target images alongside the accuracy of both edge and surface detection results. These methods can be applied to any edge and surface detection algorithms and provide a clear objective analysis of their accuracy.
2D and 3D edge detection using statistical features
This research is looking into the improvements offered to edge segmentation in images through the use of statistical features. New methods of 2D and 3D edge detection are in the development and the results of these techniques show improvements in textured and noisy image data where many traditional techniques fail.
Perception, Modelling and Improvement of Realism in Composites and Mixed Reality
This research is looking into measures of human perception of realism in mixed reality/composite scenes and translations of those into perceptual metrics using psychometric as well as machine learning approaches.
Onset pre-visualisation in film production
This research is looking into new methods for providing real-time on set actor pre-visualisation and feedback for the film industry. This concept of pre-visualisation can be applied to an actor in real-time attempting to interact with a virtual character. The aim of this work is to allow film crew to see instant results of any interaction and adapt their production as they desire. Currently methods are being evaluated to improve the level of real-time information presented and the accuracy of the interaction.
Real-time interaction in mixed reality
This research is looking into the methods of providing interaction between actors and virtual objects within a live virtual TV set. Automated methods of calculating depth within the virtual TV studio are being researched and new real-time occlusion systems have been developed.
The group have a testbed for assessing the interaction and have developed a framework for measuring the level of interaction accuracy.
Prof Cham Athwal - Associate Head of School (Research)
Cham is a Professor of Digital Technology and Head of the DMT Lab. His research interests cover 3D modelling, image processing, video processing, digital signal processing web technologies and simulation. Currently Cham is supervising eight PhD/MPhil projects covering a range of subjects including digital audio processing, digital image processing and virtual environments. Email: email@example.com Phone: +44 (0)121 331 5458
Dr Ian Williams
Ian is an Associate Professor and Subject leader in Image and Video technology within the DMT Lab. His research interests are in low-level image processing, feature extraction and image filtering. Ian currently supervises PhD students in both the image, video and signal processing fields. Email: firstname.lastname@example.org Phone: +44 (0)121 331 7416
Matt is a Senior Lecturer and Programme leader in Image and Video technology within the school of DMT. His current research interests are focused on providing new methods for pre-visualisation or virtual elements within film production. Email: email@example.com Phone: +44 (0)121 331 7443
Sam is currently researching for his PhD and undergoing image processing research which is looking to classify textures in soft tissue, as well as applying 2D and 3D statistical based boundary detection algorithms to biomedical computed tomography and magnetic resonance images, for the purpose of segmenting tumours in soft tissue. Email: firstname.lastname@example.org Phone: +44 (0)121 331 7416
Muadh Al Kalbani
Muadh is currently researching towards his PhD in image and video processing. His area of research involves the development of new solutions to real-time mixed reality systems and he is currently looking to improve the interaction possibilities between humans and virtual scenes using depth and video features.
Email: Muadh.AlKalbani@mail.bcu.ac.uk Phone: +44 (0)121 331 7416
We have many emerging areas of research in both image and video technology which are available for postgraduate study towards MPhil and PhD awards. In conjunction with projects listed above the following opportunities are always available. For more information on any of these topics please contact Prof Cham Athwal or Dr Ian Williams.
- Medical image processing
- Image segmentation, filtering, analysis and classification of soft tissue.
- Guided segmentation between MRI and CT images.
- Real-time CT processing for virtual model replication.
- Mixed Reality
- Actor interaction with virtual elements of video.
- Real-time analysis of scene conditions.
- Automated object compositing in broadcast video.
- Guided 3D reconstruction.
- Dynamic 3D model creation from CT images.
- Improving segmentation for 3D model creation.
There are a range of resources, code files and applications available upon request. For any access to these files or programmes please contact Dr Ian Williams.
- Microsoft Hololens
- Oculus Rift DK2 × 2
- Microsoft Kinect V2 × 2
- Google Glass
- Eye Tracker
3D Surface Detection Models: A model for offering improved 3D surface detection in slice CT and MRI data.
Statistical edge detection techniques: A series of algorithms are the product of the thesis titled “Edge Detection of Textured Images Using Multiple Scales and Statistics”. They apply several two-sample tests to 2D image data to locate edge information.
Multiple Scale Edge Detectors using ANNs: The algorithms presented in these files extend the 2D edge detectors with the use of Artificial Neural Networks (ANN). The ANN application allows both the training and classification of edges of varying scales within an image, using a variety of statistical tests. These algorithms can be trained around a specific application and therefore tailored to a given type of data.
Edge and Surface Performance Measures: A series of both 2D and 3D performance measures for assessing the quality of edge and surface detection methods.
For more information on these resources, contact Dr Ian Williams.
Hough, G., Williams, I., Athwal, C. Measurements of Live Actor Motion in Mixed Reality Interaction. IEEE International Symposium on Mixed and Augmented Reality. Munich, Germany. 2014.
Hough, G., Williams, I., Athwal, C. Measurement of Perceptual Tolerance for Inconsistencies within Mixed Reality Scenes. IEEE International Symposium on Mixed and Augmented Reality. Munich, Germany. 2014.
Williams I, Bowring N, Svoboda D, A Performance Evaluation of Statistical Tests for Edge Detection in Textured Images, Computer Vision and Image Understanding.
Barbosa, I.B. , Theoharis, T. , Schellewald, C. , Athwal, C., ‘Transient biometrics using finger nails’, IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), 2013, Arlington, VA.
Hough G, Athwal C and Williams I. Advanced Occlusion Handling for Virtual Studios. Lecture Notes in Computer Science, Springer 2012.
Hough G, Athwal C and Williams I. 'ScaMP: A Head Guided Projection System' ACM Designing Interactive Systems'12. Newcastle, UK. 2012
Williams I, Athwal C and Foss J. Developing Real-time Virtual Environments from Video Data.IET Seminar on Video Data Analysis, IET, London 2011
Williams I, Shirvani B and Mourier JM. Measurement of Cold Rolled Steel Sections Using Digital Image Processing. Journal of Key Engineering Materials, vol 473. Trans Tech Publications, 2011
I. Williams, D. Svoboda and N. Bowring, “A Novel Performance Metric for Grey-Scale Edge Detection” – International Conference on Computer Vision Theory and Applications 2010
J. D. Foss, B. Malheiro, “Media Component Brokerage”; Proceedings of the Fourth European Conference on the Use of Modern Information and Communication Technologies – ECUMICT 2010, Gent, Belgium, March 2010
Elson, B., Athwal C., Reynolds P., “Creating the World of Augmented Dental Training”, E-Learn 2009, World Conference on E-Learning in Corporate, Government and Healthcare, AACE Vancouver, 2009
Hough, G., Athwal, C., Williams, I., 2015. Fidelity and Plausibility of bimanual Interaction in Mixed Reality, IEEE Transactions on Visualisation and Computer Graphics, 2015
Smith, Samuel; Williams, Ian. A Statistical Method for Surface Detection. In proceeding of Eurographics Workshop on Visual Computing for Biology and Medicine, 2015.
S. Smith and I. Williams, "A Statistical Method for Improved 3D Surface Detection," in IEEE Signal Processing Letters, vol. 22, no. 8, pp. 1045-1049, Aug. 2015.