Author Archives: Xianghua Xie

About Xianghua Xie

19th BMVA Computer Vision Summer School

bmva2014.jpegBMVA Computer Vision Summer School 2014 was successfully hosted at Swansea from 30 June to 4 July 2014. A total of 67 delegates from 14 different countries ( 21 from outside UK) were attending the 19th edition of this summer school. 17 speakers from both academia and industry delivered 19 lectures and 2 lab sessions.

Click here to visit the summer school website.

Subject specific 3D human pose interaction classification

Screen Shot 2014-05-09 at 10.16.44In this work, we investigate whether it is possible to distinguish conversational interac- tions from observing human motion alone, in particular subject specific gestures in 3D. We adopt Kinect sensors to obtain 3D displacement and velocity measurements, followed by wavelet decomposition to extract low level temporal features. These features are then generalized to form a visual vocabulary that can be further generalized to a set of topics from temporal distributions of visual vocabulary. A subject specific supervised learning approach based on Random Forests is used to classify the testing sequences to seven dif- ferent conversational scenarios. These conversational scenarios concerned in this work have rather subtle differences among them. Unlike typical action or event recognition, each interaction in our case contain many instances of primitive motions and actions, many of which are shared among different conversation scenarios. That is the interactions we are concerned with are not micro or instant events, such as hugging and high-five, but rather interactions over a period of time that consists rather similar individual motions, micro actions and interactions. We believe this is among one of the first work that is devoted to subject specific conversational interaction classification using 3D pose features and to show this task is indeed possible.

pdficon_largeJ. Deng, X. Xie, and B. Daubney, A bag of words approach to subject specific 3D human pose interaction classification with random decision forests, Graphical Models, Volume 76, Issue 3, Pages 162–171, May 2014.

More details can be found at the Swansea Vision website.

Arron Lacey successfully defends MSc by Research viva

Congratulations to Arron Lacey who successfully defended his MSc by Research thesis, titled “Supervised Machine Learning Techniques in Bioinformatics: Protein Classification“.

Xianghua Xie was the supervisor, the two external examiners were Reyer Zwiggelaar (Aberystwyth) and Yulia Hicks (Cardiff), and Parisa Eslambolchilar was the viva chair.

Segmentation of biomedical images using shape prior

Screen Shot 2014-05-09 at 10.26.02In this article, a new level set model is proposed for the segmentation of biomedical images. The image energy of the proposed model is derived from a robust image gradient feature which gives the active contour a global representation of the geometric configuration, making it more robust in dealing with image noise, weak edges, and initial configurations. Statistical shape information is incorporated using nonparametric shape density distribution, which allows the shape model to handle relatively large shape variations. The segmentation of various shapes from both synthetic and real images depict the robustness and efficiency of the proposed method.

pdficon_largeS. Y. Yeo, X. Xie, I. Sazonov, and P. Nithiarasu, Segmentation of biomedical images using active contour model with robust image feature and shape prior, International Journal for Numerical Methods in Biomedical Engineering, Volume 30, Issue 2, pages 232–248, February 2014.

More details can be found at the Swansea Vision website.

Integrated Segmentation and Interpolation of Sparse Data

Screen Shot 2014-05-09 at 09.51.59We address the two inherently related problems of segmentation and interpolation of 3D and 4D sparse data and propose a new method to integrate these stages in a level set framework.
The interpolation process uses segmentation information rather than pixel intensities for increased robustness and accuracy. The method supports any spatial configurations of sets of 2D slices having arbitrary positions and orientations. We achieve this by introducing a new level set scheme based on the interpolation of the level set function by radial basis functions. The proposed method is validated quantitatively and/or subjec- tively on artificial data and MRI and CT scans and is compared against the traditional sequential approach, which interpolates the images first, using a state-of-the-art image interpolation method, and then segments the interpolated volume in 3D or 4D. In our experiments, the proposed framework yielded similar segmentation results to the sequential approach but provided a more robust and accurate interpolation. In particular, the interpolation was more satisfactory in cases of large gaps, due to the method taking into account the global shape of the object, and it recovered better topologies at the extremities of the shapes where the objects disappear from the image slices. As a result, the complete integrated framework provided more satisfactory shape reconstructions than the sequential approach.

pdficon_largeA. Paiement, M. Mirmehdi, X. Xie, and M. Hamilton, Integrated Segmentation and Interpolation of Sparse Data, IEEE Transactions on Image Processing (T-IP), volume 23, issue 1, pages 110-125, January 2014.

More details can be found at the Swansea Vision website.

Shape and Appearance Priors for Level Set-based LV Segmentation

We propose a novel spatiotemporal constraint based on shape and appearance and combine it with a level-set deformable model for left ventricle (LV) segmentation in four-dimensional gated cardiac SPECT, particularly in the presence of perfusion defects. The model incorporates appearance and shape information into a ‘soft-to-hard’ probabilistic constraint, and utilises spatiotemporal regularisation via a maximum a posteriori framework. This constraint force allows more flexibility than the rigid forces of shape constraint-only schemes, as well as other state of the art joint shape and appearance constraints. The combined model can hypothesise defective LV borders based on prior knowledge. The authors present comparative results to illustrate the improvement gain. A brief defect detection example is finally presented as an application of the proposed method.

IET Journal of Computer Vision, vol. 7, no.3, pp. 170-183, 2013.

Follow this link to see more publications on Computer Vision and Medical Image Analysis.

Jingjing Deng passes MSc by Research

Congratulations to Jingjing Deng who successfully defended his MSc by Research viva. He became the first MSc by Research graduate from the department since the very recent introduction of this one year research only degree scheme. His thesis is titled “Towards Human Interaction Modelling”.

Jingjing Deng was under the supervision of Dr. Xianghua Xie. The external examiner was Prof. Reyer Zwiggelaar (Aber) and the internal examiner was Dr. Gary Tam.