My publications

Publications

T Wang, A Mansfield, R Hu, JP Collomosse (2009)An Evolutionary Approach to Automatic Video Editing, In: 2009 CONFERENCE FOR VISUAL MEDIA PRODUCTION: CVMP 2009pp. 127-134

In this paper, we propose an object segmentation algorithm driven by minimal user interactions. Compared to previous user-guided systems, our system can cut out the desired object in a given image with only a single finger touch minimizing user effort. The proposed model harnesses both edge and region based local information in an adaptive manner as well as geometric cues implied by the user-input to achieve fast and robust segmentation in a level set framework. We demonstrate the advantages of our method in terms of computational efficiency and accuracy comparing qualitatively and quantitatively with graph cut based techniques.

R Hu, S James, T Wang, JP Collomosse (2013)Markov Random Fields for Sketch based Video Retrievalpp. 279-286

We describe a new system for searching video databases us- ing free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with keywords that indicate the semantic category of each object. We parse space-time volumes from video to form graph rep- resentation, which we match to sketches under a Markov Random Field (MRF) optimization. The MRF energy func- tion is used to rank videos for relevance and contains unary, pairwise and higher-order potentials that reflect the colour, shape, motion and type of sketched objects. We evaluate performance over a dataset of 500 sports footage clips.

G Guo, T Wang, J Li, A Wang, Wenwu Wang (2019)Multiple Input Single Output Phase Retrieval, In: Circuits, Systems and Signal Processing Springer

In this paper, we consider the problem of recovering the phase information of multiple sources from a mixed phaseless Short-Time Fourier Transform (STFT) measurement, which is called multiple input single output (MISO) phase retrieval problem. It is an inherently ill-posed problem due to the lack of the phase and mixing information, and the existing phase retrieval algorithms are not explicitly designed for this case. To address the MISO phase retrieval problem, a least squares (LS) method coupled with an independent component analysis (ICA) algorithm is proposed for the case of sufficiently long window length. When these conditions are not met, an integrated algorithm is presented, which combines a gradient descent (GD) algorithm by minimizing a non-convex loss function with an ICA algorithm. Experimental evaluation has been conducted to show that under appropriate conditions the proposed algorithms can explicitly recover the signals, the phases of the signals and the mixing matrix. In addition, the algorithm is robust to noise

T Wang, J Collomosse, D Slatter, P Cheatle, D Greig (2010)Video Stylization for Digital Ambient Displays of Home Movies, In: Proceedings ACM 4th Intl. Symposium on Non-photorealistic Animation and Rendering (NPAR)pp. 137-146

Falling hardware costs have prompted an explosion in casual video capture by domestic users. Yet, this video is infrequently accessed post-capture and often lies dormant on users’ PCs. We present a system to breathe life into home video repositories, drawing upon artistic stylization to create a “Digital Ambient Display” that automatically selects, stylizes and transitions between videos in a semantically meaningful sequence. We present a novel algorithm based on multi-label graph cut for segmenting video into temporally coherent region maps. These maps are used to both stylize video into cartoons and paintings, and measure visual similarity between frames for smooth sequence transitions. We demonstrate coherent segmentation and stylization over a variety of home videos.

T Wang, B Han, John Collomosse (2014)TouchCut: Fast Image and Video Segmentation using Single-Touch Interaction, In: Computer Vision and Image Understanding120pp. 14-30 Elsevier

We present TouchCut; a robust and efficient algorithm for segmenting image and video sequences with minimal user interaction. Our algorithm requires only a single finger touch to identify the object of interest in the image or first frame of video. Our approach is based on a level set framework, with an appearance model fusing edge, region texture and geometric information sampled local to the touched point. We first present our image segmentation solution, then extend this framework to progressive (per-frame) video segmentation, encouraging temporal coherence by incorporating motion estimation and a shape prior learned from previous frames. This new approach to visual object cut-out provides a practical solution for image and video segmentation on compact touch screen devices, facilitating spatially localized media manipulation. We describe such a case study, enabling users to selectively stylize video objects to create a hand-painted effect. We demonstrate the advantages of TouchCut by quantitatively comparing against the state of the art both in terms of accuracy, and run-time performance.

T Wang, JP Collomosse, A Hunter, D Greig (2014)Learnable Stroke Models for Example-based Portrait Painting

We present a novel algorithm for stylizing photographs into portrait paintings comprised of curved brush strokes. Rather than drawing upon a prescribed set of heuristics to place strokes, our system learns a flexible model of artistic style by analyzing training data from a human artist. Given a training pair — a source image and painting of that image—a non-parametric model of style is learned by observing the geometry and tone of brush strokes local to image features. A Markov Random Field (MRF) enforces spatial coherence of style parameters. Style models local to facial features are learned using a semantic segmentation of the input face image, driven by a combination of an Active Shape Model and Graph-cut. We evaluate style transfer between a variety of training and test images, demonstrating a wide gamut of learned brush and shading styles.

T Wang, John Collomosse, R Hu, D Slatter, P Cheatle, D Greig (2011)Stylized Ambient Displays of Digital Media Collections, In: Computers and Graphics35(1)pp. 54-66 Elsevier

The falling cost of digital cameras and camcorders has encouraged the creation of massive collections of personal digital media. However, once captured, this media is infrequently accessed and often lies dormant on users' PCs. We present a system to breathe life into home digital media collections, drawing upon artistic stylization to create a “Digital Ambient Display” that automatically selects, stylizes and transitions between digital contents in a semantically meaningful sequence. We present a novel algorithm based on multi-label graph cut for segmenting video into temporally coherent region maps. These maps are used to both stylize video into cartoons and paintings, and measure visual similarity between frames for smooth sequence transitions. The system automatically structures the media collection into a hierarchical representation based on visual content and semantics. Graph optimization is applied to adaptively sequence content for display in a coarse-to-fine manner, driven by user attention level (detected in real-time by a webcam). Our system is deployed on embedded hardware in the form of a compact digital photo frame. We demonstrate coherent segmentation and stylization over a variety of home videos and photos. We evaluate our media sequencing algorithm via a small-scale user study, indicating that our adaptive display conveys a more compelling media consumption experience than simple linear “slide-shows”.

We describe a novel framework for segmenting a time- and view-coherent foreground matte sequence from synchronised multiple view video. We construct a Markov Random Field (MRF) comprising links between superpixels corresponded across views, and links between superpixels and their constituent pixels. Texture, colour and disparity cues are incorporated to model foreground appearance. We solve using a multi-resolution iterative approach enabling an eight view high definition (HD) frame to be processed in less than a minute. Furthermore we incorporate a temporal diffusion process introducing a prior on the MRF using information propagated from previous frames, and a facility for optional user correction. The result is a set of temporally coherent mattes that are solved for simultaneously across views for each frame, exploiting similarities across views and time.

JE Kyprianidis, JP Collomosse, T Isenberg, T Wang (2012)State of the Art: A Taxonomy of Artistic Stylization Techniques for Images and Video, In: IEEE Transactions on Visualization and Computer Graphicsvolume IEEE

This paper surveys the field of non-photorealistic rendering (NPR), focusing on techniques for transforming 2D input (images and video) into artistically stylized renderings. We first present a taxonomy of the 2D NPR algorithms developed over the past two decades, structured according to the design characteristics and behavior of each technique. We then describe a chronology of development from the semi-automatic paint systems of the early nineties, through to the automated painterly rendering systems of the late nineties driven by image gradient analysis. Two complementary trends in the NPR literature are then addressed, with reference to our taxonomy. First, the fusion of higher level computer vision and NPR, illustrating the trends toward scene analysis to drive artistic abstraction and diversity of style. Second, the evolution of local processing approaches toward edge-aware filtering for real-time stylization of images and video. The survey then concludes with a discussion of open challenges for 2D NPR identified in recent NPR symposia, including topics such as user and aesthetic evaluation.

T Wang, Y Wang, Chong Han (2017)An improved clustering routing mechanism for wireless Ad hoc network, In: Journal of Intelligent & Fuzzy Systems32(5)pp. 3401-3412 IOS Press

In Wireless Ad hoc Networks (WANET), to organize sensor nodes for data collection is an important research issue. Clustering is an effective technique for prolonging the network lifetime. However, the Cluster Header (CH) in a cluster always involves a lot of data forwarding tasks, rather than its Cluster Members (CMs). This energy consumption overloading inevitably leads to the “hot spot” problem. With these in mind, an Energy-Balanced and Unequally-Layered Routing Protocol (EBULRP) is proposed in this article. The main emphasis is on balancing the energy consumption among CHs. In our design, the network is decoupled into multiple layers with different width, where the radius of clusters is differentiated at each layer. The core is to organize those CHs closer to the sink node, with more energy for inter-cluster data forwarding. Simulation results show that the proposed EBULRP effectively balances the energy consumption among CHs, and further prolongs the network lifetime.

T wang, JP Collomosse (2012)Probabilistic Motion Diffusion of Labeling Priors for Coherent Video Segmentation, In: IEEE Transactions on Multimedia14(2)pp. 389-400 IEEE

We present a robust algorithm for temporally coherent video segmentation. Our approach is driven by multi-label graph cut applied to successive frames, fusing information from the current frame with an appearance model and labeling priors propagated forwarded from past frames. We propagate using a novel motion diffusion model, producing a per-pixel motion distribution that mitigates against cumulative estimation errors inherent in systems adopting “hard” decisions on pixel motion at each frame. Further, we encourage spatial coherence by imposing label consistency constraints within image regions (super-pixels) obtained via a bank of unsupervised frame segmentations, such as mean-shift. We demonstrate quantitative improvements in accuracy over state-of-the-art methods on a variety of sequences exhibiting clutter and agile motion, adopting the Berkeley methodology for our comparative evaluation.

R Hu, T Wang, J Collomosse (2011)A Bag-of-Regions approach to Sketch-based Image Retrieval, In: International Conference on Image Processing (ICIP)pp. 3661-3664

This paper presents a sketch-based image retrieval system using a bag-of-region representation of images. Regions from the nodes of a hierarchical region tree range in various scales of details. They have appealing properties for object level inference such as the naturally encoded shape and scale information of objects and the specified domains on which to compute features without being affected by clutter from outside the region. The proposed approach builds shape descriptor on the salient shape among the clutters and thus yields significant performance improvements over the previous results on three leading descriptors in Bag-of-Words framework for sketch based image retrieval. Matched region also facilitates the localization of sketched object within the retrieved image.

T Wang, J Guillemaut, J Collomosse (2010)Multi-label Propagation for Coherent Video Segmentation and Artistic Stylization, In: Proceedings of Intl. Conf. on Image Proc. (ICIP)pp. 3005-3008

We present a new algorithm for segmenting video frames into temporally stable colored regions, applying our technique to create artistic stylizations (e.g. cartoons and paintings) from real video sequences. Our approach is based on a multilabel graph cut applied to successive frames, in which the color data term and label priors are incrementally updated and propagated over time. We demonstrate coherent segmentation and stylization over a variety of home videos.