Computer Science publications
Permanent URI for this collection
Browse
Browsing Computer Science publications by Title
Now showing 1 - 20 of 3132
Results Per Page
Sort Options
Item Restricted 10 years of software architecture knowledge management: practice and future(Elsevier, 2016) Capilla, R.; Jansen, A.; Tang, A.; Avgeriou, P.; Babar, M.Abstract not availableItem Metadata only 2-Space bounded online cube and hypercube packing(Tsinghua University Press, 2015) Zhao, X.; Shen, H.We consider the problem of packing d-dimensional cubes into the minimum number of 2-space bounded unit cubes. Given a sequence of items, each of which is a d-dimensional (d >= 3) hypercube with side length not greater than 1 and an infinite number of d-dimensional (d >= 3) hypercube bins with unit length on each side, we want to pack all of the items in the sequence into the minimum number of bins. The constraint is that only two bins are active at anytime during the packing process. Each item should be orthogonally packed without overlapping other items. Items are given in an online manner without the knowledge of or information about the subsequent items. We extend the technique of brick partitioning for square packing and obtain two results: a three-dimensional box and d-dimensional hyperbox partitioning schemes for cube and hypercube packing, respectively. We design 5.43-competitive and 32/21.2(d)-competitive algorithms for cube and hypercube packing, respectively. To the best of our knowledge these are the first known results on 2-space bounded cube and hypercube packing.Item Open Access 2D articulated tracking with dynamic Bayesian networks(IEEE, 2004) Shen, C.; Van Den Hengel, A.; Dick, A.; Brooks, M.; International Conference on Computer and Information Technology (4th : 2004 : Wuhan, China); Wei, D.; Wang, H.; Peng, Z.; Kara, A.; He, Y.We present a novel method for tracking the motion of an articulated structure in a video sequence. The analysis of articulated motion is challenging because of the potentially large number of degrees of freedom (DOFs) of an articulated body. For particle filter based algorithms, the number of samples required with high dimensional problems can be computationally prohibitive. To alleviate this problem, we represent the articulated object as an undirected graphical model (or Markov Random Field, MRF) in which soft constraints between adjacent subparts are captured by conditional probability distributions. The graphical model is extended across time frames to implement a tracker. The tracking algorithm can be interpreted as a belief inference procedure on a dynamic Bayesian network. The discretisation of the state vectors makes it possible to utilise the efficient belief propagation (BP) and mean field (MF) algorithms to reason in this network. Experiments on real video sequences demonstrate that the proposed method is computationally efficient and performs well in tracking the human body.Item Restricted 3-D Modeling from Concept Sketches of Human Characters with Minimal User Interaction(IEEE, 2015) Johnston, A.; Carneiro, G.; Ding, R.; Velho, L.; 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2015) (23 Nov 2015 - 25 Nov 2015 : Adelaide, AUSTRALIA)We propose a new methodology for creating 3-D models for computer graphics applications from 2-D concept sketches of human characters using minimal user interaction. This methodology will facilitate the fast production of high quality 3-D models by non-expert users involved in the development process of video games and movies. The workflow starts with an image containing the sketch of the human character from a single viewpoint, in which a 2-D body pose detector is run to infer the positions of the skeleton joints of the character. Then the 3-D body pose and camera motion are estimated from the 2-D body pose detected from above, where we take a recently proposed methodology that works with real humans and adapt it to work with concept sketches of human characters. The final step of our methodology consists of an optimization process based on a sampling importance re-sampling method that takes as input the estimated 3-D body pose and camera motion and builds a 3-D mesh of the body shape, which is then matched to the concept sketch image. Our main contributions are: 1) a novel adaptation of the 3-D from 2-D body pose estimation methods to work with sketches of humans that have non-standard body part proportions and constrained camera motion; and 2) a new optimization (that estimates a 3-D body mesh using an underlying low-dimensional linear model of human shape) guided by the quality of the matching between the 3-D mesh of the body shape and the concept sketch. We show qualitative results based on seven 3-D models inferred from 2-D concept sketches, and also quantitative results, where we take seven different 3-D meshes to generate concept sketches, and use our method to infer the 3-D model from these sketches, which allows us to measure the average Euclidean distance between the original and estimated 3-D models. Both qualitative and quantitative results show that our model has potential in the fast production of 3-D models from concept sketches.Item Metadata only 3-D printed smart orthotic insoles: Monitoring a person's gait step by step(Institute of Electrical and Electronics Engineers (IEEE), 2020) Hao, Z.; Cook, K.; Canning, J.; Chen, H.T.; Martelli, C.This article reports a 3-D printing intelligent insole gait monitoring system based on an embedded fiber Bragg grating (FBG). The smart insole combines 3-D printing technology and FBG sensors providing high sensitivity and endpoint low cost. Results using pressure points measured by four FBGs are sufficient to differentiate foot loads and gait types.Item Metadata only 3-Objective Pareto Optimization for Problems with Chance Constraints(Association for Computing Machinery, 2023) Neumann, F.; Witt, C.; Genetic and Evolutionary Computation Conference (GECCO) (15 Jul 2023 - 19 Jul 2023 : Lisbon, Portugal); Paquete, L.Evolutionary multi-objective algorithms have successfully been used in the context of Pareto optimization where a given constraint is relaxed into an additional objective. In this paper, we explore the use of 3-objective formulations for problems with chance constraints. Our formulation trades off the expected cost and variance of the stochastic component as well as the given deterministic constraint. We point out benefits that this 3-objective formulation has compared to a bi-objective one recently investigated for chance constraints with Normally distributed stochastic components. Our analysis shows that the 3-objective formulation allows to compute all required trade-offs using 1-bit flips only, when dealing with a deterministic cardinality constraint. Furthermore, we carry out experimental investigations for the chance constrained dominating set problem and show the benefit for this classical NP-hard problem.Item Metadata only 3D hand tracking for human computer interaction(Elsever, 2011) Prisacariu, V.; Reid, I.Abstract not availableItem Metadata only 3D object pose inference via kernel principal component analysis with image euclidian distance (IMED).(British Machine Vision Association, 2006) Tangkuampien, T.; Suter, D.; British Machine Vision Conference (17th : 2006 : Edinburgh)Kernel Principal Component Analysis (KPCA) is a powerful non-linear unsupervised learning technique for high dimensional pattern analysis. KPCA on images, however, usually considers each image pixel as an independent dimension and does not take into account the spatial relationship of nearby pixels. In this paper, we show how the Image Euclidian Distance (IMED), which takes into account local pixel intensities, can efficiently be embedded into KPCA via the Kronecker product and Eigenvector projections, whilst still retaining desirable properties of Euclidian distance (such as kernel positive definitiveness and effective image de-noising). We demonstrate that KPCA with embedded IMED is a more intuitive and accurate technique than standard KPCA through a 3D object pose estimation application.Item Metadata only 3D R transform on spatio-temporal interest points for action recognition(IEEE, 2013) Yuan, Chunfeng; Li, Xi; Hu, Weiming; Ling, Haibin; Maybank, Steve; IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon); CVPR 2013; School of Computer ScienceSpatio-temporal interest points serve as an elementary building block in many modern action recognition algorithms, and most of them exploit the local spatio-temporal volume features using a Bag of Visual Words (BOVW) representation. Such representation, however, ignores potentially valuable information about the global spatio-temporal distribution of interest points. In this paper, we propose a new global feature to capture the detailed geometrical distribution of interest points. It is calculated by using the R transform which is defined as an extended 3D discrete Radon transform, followed by applying a two-directional two-dimensional principal component analysis. Such R feature captures the geometrical information of the interest points and keeps invariant to geometry transformation and robust to noise. In addition, we propose a new fusion strategy to combine the R feature with the BOVW representation for further improving recognition accuracy. We utilize a context-aware fusion method to capture both the pairwise similarities and higher-order contextual interactions of the videos. Experimental results on several publicly available datasets demonstrate the effectiveness of the proposed approach for action recognition.Item Metadata only 3D semantic mapping from arthroscopy using out-of-distribution pose and depth and in-distribution segmentation training(Springer International Publishing, 2021) Jonmohamadi, Y.; Ali, S.; Liu, F.; Roberts, J.; Crawford, R.; Carneiro, G.; Pandey, A.K.; 24th International Conference of Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 (27 Sep 2021 - 1 Oct 2021 : Strasbourg, France); DeBruijne, M.; Cattin, P.C.; Cotin, S.; Padoy, N.; Speidel, S.; Zheng, Y.; Essert, C.Minimally invasive surgery (MIS) has many documented advantages, but the surgeon’s limited visual contact with the scene can be problematic. Hence, systems that can help surgeons navigate, such as a method that can produce a 3D semantic map, can compensate for the limitation above. In theory, we can borrow 3D semantic mapping techniques developed for robotics, but this requires finding solutions to the following challenges in MIS: 1) semantic segmentation, 2) depth estimation, and 3) pose estimation. In this paper, we propose the first 3D semantic mapping system from knee arthroscopy that solves the three challenges above. Using out-of-distribution non-human datasets, where pose could be labeled, we jointly train depth+pose estimators using self-supervised and supervised losses. Using an in-distribution human knee dataset, we train a fully-supervised semantic segmentation system to label arthroscopic image pixels into femur, ACL, and meniscus. Taking testing images from human knees, we combine the results from these two systems to automatically create 3D semantic maps of the human knee. The result of this work opens the pathway to the generation of intra-operative 3D semantic mapping, registration with pre-operative data, and robotic-assisted arthroscopy. Source code: https://github.com/YJonmo/EndoMapNet.Item Metadata only 3D terrestrial LIDAR classifications with super-voxels and multi-scale Conditional Random Fields(Elsevier Sci Ltd, 2009) Lim, E.; Suter, D.In this paper, we propose a new method for 3D terrestrial laser range data classifications. This functions as the first step towards virtual city model reconstructions from range data and is particularly useful for scene understanding. Classification of the outdoor terrestrial range data into different data types (for example, building surface, vegetation and terrain) is challenging due to certain properties of the data: occlusions due to obstructions, density variation due to different distances of the scanned object from the laser scanner, multiple multi-structure objects and cluttered vegetation. Also, the range data acquired are massive in size and require a lot of computation and memory. Recognizing the redundancy of labeling every individual data, we propose over-segmenting the raw data into adaptive support regions: super-voxels. The super-voxels are computed using 3D scale theory and adapt to the above-mentioned range data properties. Colors and reflectance intensity acquired from the scanner system are combined with geometry features (saliency features and normals) that are extracted from the super-voxels, to form the feature descriptors for the supervised learning model. We proposed using the discriminative Conditional Random Fields for the classification problem and modified the model to incorporate multi-scales for super-voxel labeling. We validated our proposed strategy with synthetic data and real-world outdoor LIDAR (Light Detection and Ranging) data acquired from a Riegl LMS-Z420i terrestrial laser scanner. The results showed great improvement in the training and inference rate while maintaining comparable classification accuracy with previous approaches.Item Metadata only 3D tracking of multiple objects with identical appearance using RGB-D input(IEEE, 2014) Ren, C.Y.; Prisacariu, V.A.; Kähler, O.; Reid, I.D.; Murray, D.W.; International Conference on 3D Vision (3DV) (8 Dec 2014 - 11 Dec 2014 : Tokyo, Japan)Most current approaches for 3D object tracking rely on distinctive object appearances. While several such trackers can be instantiated to track multiple objects independently, this not only neglects that objects should not occupy the same space in 3D, but also fails when objects have highly similar or identical appearances. In this paper we develop a probabilistic graphical model that accounts for similarity and proximity and leads to robust real-time tracking of multiple objects from RGB-D data, without recourse to bolton collision detection.Item Metadata only 6-DOF multi-session visual SLAM using anchor nodes(ECMR, 2011) McDonald, J.; Kaess, M.; Cadena Lerma, C.; Neira, J.; Leonard, J.; European Conference on Mobile Robots (ECMR) (7 Sep 2011 - 9 Sep 2011 : Orebro, Sweden)This paper describes a system for performing multisession visual mapping in large-scale environments. Multi-session mapping considers the problem of combining the results of multiple Simultaneous Localisation and Mapping (SLAM) missions performed repeatedly over time in the same environment. The goal is to robustly combine multiple maps in a common metrical coordinate system, with consistent estimates of uncertainty. Our work employs incremental Smoothing and Mapping (iSAM) as the underlying SLAM state estimator and uses an improved appearance-based method for detecting loop closures within single mapping sessions and across multiple sessions. To stitch together pose graph maps from multiple visual mapping sessions, we employ spatial separator variables, called anchor nodes, to link together multiple relative pose graphs. We provide experimental results for multi-session visual mapping in the MIT Stata Center, demonstrating key capabilities that will serve as a foundation for future work in large-scale persistent visual mapping.Item Metadata only 9.6 million links in source code comments: purpose, evolution, and decay(IEEE, 2019) Hata, H.; Treude, C.; Kula, R.G.; Ishio, T.; IEEE/ACM International Conference on Software Engineering (ICSE) (25 May 2019 - 31 May 2019 : Montreal, Canada)Links are an essential feature of the World Wide Web, and source code repositories are no exception. However, despite their many undisputed benefits, links can suffer from decay, insufficient versioning, and lack of bidirectional traceability. In this paper, we investigate the role of links contained in source code comments from these perspectives. We conducted a large-scale study of around 9.6 million links to establish their prevalence, and we used a mixed-methods approach to identify the links' targets, purposes, decay, and evolutionary aspects. We found that links are prevalent in source code repositories, that licenses, software homepages, and specifications are common types of link targets, and that links are often included to provide metadata or attribution. Links are rarely updated, but many link targets evolve. Almost 10% of the links included in source code comments are dead. We then submitted a batch of link-fixing pull requests to open source software repositories, resulting in most of our fixes being merged successfully. Our findings indicate that links in source code comments can indeed be fragile, and our work opens up avenues for future work to address these problems.Item Metadata only A 2-step deep learning method with domain adaptation for Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Magnetic Resonance Segmentation(Springer International Publishing, 2021) Corral Acero, J.; Sundaresan, V.; Dinsdale, N.; Grau, V.; Jenkinson, M.; 11th International Workshop on Statistical Atlases and Computational Models of the Heart (STACOM) (4 Oct 2020 - 4 Oct 2020 : virtual online)Segmentation of anatomical structures from Cardiac Magnetic Resonance (CMR) is central to the non-invasive quantitative assessment of cardiac function and structure. Anatomical variability, imaging heterogeneity and cardiac dynamics challenge the automation of this task. Deep learning (DL) approaches have taken over the field of automatic segmentation in recent years, however they are limited by data availability and the additional variability introduced by differences in scanners and protocols. In this work, we propose a 2-step fully automated pipeline to segment CMR images, based on DL encoder-decoder frameworks, and we explore two domain adaptation techniques, domain adversarial training and iterative domain unlearning, to overcome the imaging heterogeneity limitations. We evaluate our methods on the MICCAI 2020 Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge training and validation datasets. The results show the improvement in performance produced by domain adaptation models, especially among the seen vendors. Finally, we build an ensemble of baseline and domain adapted networks, that reported state-of-art mean Dice scores of 0.912, 0.857 and 0.861 for left ventricle (LV) cavity, LV myocardium and right ventricle cavity, respectively, on the externally validated Challenge dataset, including several unseen vendors, centers and cardiac pathologies.Item Metadata only A BasisEvolution framework for network traffic anomaly detection(Elsevier, 2018) Xia, H.; Fang, B.; Roughan, M.; Cho, K.; Tune, P.Abstract not availableItem Metadata only A Bayesian data augmentation approach for learning deep models(Neural Information Processing Systems Foundation, 2018) Tran, T.; Pham, T.; Carneiro, G.; Palmer, L.; Reid, I.; NIPS Foundation Inc (4 Dec 2017 - 9 Dec 2017 : Long Beach, CA); Guyon, I.; Luxburg, U.V.; Bengio, S.; Wallach, H.; Fergus, R.; Vishwanathan, S.; Garnett, R.Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as data augmentation. The dominant data augmentation approach in the field assumes that new training samples can be obtained via random geometric or appearance transformations applied to annotated training samples, but this is a strong assumption because it is unclear if this is a reliable generative model for producing new training samples. In this paper, we provide a novel Bayesian formulation to data augmentation, where new annotated training points are treated as missing variables and generated based on the distribution learned from the training set. For learning, we introduce a theoretically sound algorithm --- generalised Monte Carlo expectation maximisation, and demonstrate one possible implementation via an extension of the Generative Adversarial Network (GAN). Classification results on MNIST, CIFAR-10 and CIFAR-100 show the better performance of our proposed method compared to the current dominant data augmentation approach mentioned above --- the results also show that our approach produces better classification results than similar GAN models.Item Metadata only A Bayesian Estimation of Building Shape Using MCMC(Springer-Verlag, 2002) Dick, A.; Dyer, F.; Cipolla, R.; European Conference on Computer Vision (7th : 2002 : Copehagen, Denmark); Heyden, A.; Sparr, G.; Nielsen, M.; Johansen, P.This Paper investigates the use of an implicit Prior in Bayesian model-based 3D reconstruction of architecture from image sequences. In our previous work architecture is represented as a combination of basic primitives such as windows and doors etc, each with their own Prior. The contribution of this work is to provide a global Prior for the spatial organization of the basic primitives. However, it is difficult to explicitly formulate the Prior on spatial organization. Instead we define an implicit representation that favours global regularities prevalent in architecture (e.g. windows lie in rows etc.). Specifying exact Parameter values for this Prior is problematic at best, however it is demonstrated that for a broad range of values the Prior provides reasonable results. The validity of the Prior is tested visually by generating synthetic buildings as draws from the Prior simulated using MCMC. The result is a fully Bayesian method for structure from motion in the domain of architectureItem Metadata only A bilinear approach to the parameter estimation of a general heteroscedastic linear system, with application to conic fitting(Kluwer Academic Publ, 2007) Chen, P.; Suter, D.In this paper, we employ low-rank matrix approximation to solve a general parameter estimation problem: where a non-linear system is linearized by treating the carrier terms as separate variables, thereby introducing heteroscedastic noise. We extend the bilinear approach to handle cases with heteroscedastic noise, in the framework of low-rank approximation. The ellipse fitting problem is investigated as a specific example of the general theory. Despite the impression given in the literature, the ellipse fitting problem is still unsolved when the data comes from a small section of the ellipse. Although there are already some good approaches to the problem of ellipse fitting, such as FNS and HEIV, convergence in these iterative approaches is not ensured, as pointed out in the literature. Another limitation of these approaches is that they cannot model the correlations among different rows of the “general measurement matrix”. Our method, of employing the bilinear approach to solve the general heteroscedastic parameter estimation problem, overcomes these limitations: it is convergent, at least to a local optimum, and can cope with a general heteroscedastic problem. Experiments show that the proposed bilinear approach performs better than other competing approaches: although it is still far short of a solution when the data comes from a very small arc of the ellipse.Item Metadata only A block-aware hybrid data dissemination with hotspot elimination in wireless sensor network(Academic Press, 2014) Niu, W.; Li, G.; Tong, E.; Sheng, Q.; Li, Q.; Hu, Y.; Vasilakos, A.; Guo, L.Abstract not available