A genetic algorithm has been coupled with CFD simulations of a 600 MW boiler. The genetic algorit... more A genetic algorithm has been coupled with CFD simulations of a 600 MW boiler. The genetic algorithm was able to automatically generate innovative boiler settings. Correlations between operating parameters and boiler output data were obtained. A target function helped to achieve low-NO x configurations with low corrosion risk. The predicted NO x emissions are consistent with levels measured in the boiler.
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical ... more Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by Edmonds, Karp, and Dinic [7, 6] in 1972, capacity scaling is well known in the combinatorial optimization community. Surprisingly, this major performance improving technique is overlooked in computer vision where graph cut methods typically solve energy minimization problems on huge N-D grids and algorithms' efficiency is a widely studied issue [3, 12, 16, 10]. Unlike some earlier hierarchical methods addressing efficiency of graph cuts in imaging, e.g. [16], capacity scaling preserves global optimality of the solution. This is the main motivation for our work studying capacity scaling in the context of vision. We show that capacity scaling significantly reduces non-polynomial theoretical time complexity of the max-flow algorithm in [3] to weakly polynomial O(m 2 n 2 log(U)) where U is the largest edge weight. While [3] is the fastest method for many applications in vision, capacity scaling gives several folds speed-ups for problems with large number of local minima. The effect is particularly strong in 3D applications with denser neighborhoods.
Mixed integer linear programs are commonly solved by Branch and Bound algorithms. A key factor of... more Mixed integer linear programs are commonly solved by Branch and Bound algorithms. A key factor of the efficiency of the most successful commercial solvers is their fine-tuned heuristics. In this paper, we leverage patterns in real-world instances to learn from scratch a new branching strategy optimised for a given problem and compare it with a commercial solver. We propose FMSTS, a novel Reinforcement Learning approach specifically designed for this task. The strength of our method lies in the consistency between a local value function and a global metric of interest. In addition, we provide insights for adapting known RL techniques to the Branch and Bound setting, and present a new neural network architecture inspired from the literature. To our knowledge, it is the first time Reinforcement Learning has been used to fully optimise the branching strategy. Computational experiments show that our method is appropriate and able to generalise well to new instances.
Image processing techniques are now widely spread out over a large quantity of domains: like medi... more Image processing techniques are now widely spread out over a large quantity of domains: like medical imaging, movies post-production, games... Automatic detection and extraction of regions of interest inside an image, a volume or a video is challenging problem since it is a starting point for many applications in image processing. However many techniques were developed during the last years and the state of the art methods suffer from some drawbacks: The Level Sets method only provides a local minimum while the Graph Cuts method comes from Combinatorial Community and could take advantage of the specificity of image processing problems. In this thesis, we propose two extensions of the previously cited methods in order to soften or remove these drawbacks. We first discuss the existing methods and show how they are related to the segmentation problem through an energy formulation. Then we introduce stochastic perturbations to the Level Sets method and we build a more generic framework: the Stochastic Level Sets (SLS). Later we provide a direct application of the SLS to image segmentation that provides a better minimization of energies. Basically, it allows the contours to escape from local minimum. Then we propose a new formulation of an existing algorithm of Graph Cuts in order to introduce some interesting concept for image processing community: like initialization of the algorithm for speed improvement. We also provide a new approach for layer extraction from video sequence that retrieves both visible and hidden layers in it. 7.1 Dynamic segmentation of a video sequence. The Active cuts algorithm (yellow) runs 2-6 times faster than the state-of-theart max-flow algorithm in [18] (red). In each new frame initial cut for our algorithm is set to an optimal cut/segmentation from the previous frame. The speed of our algorithm almost linearly proportional to the magnitude of motion shown by the plot of the Hausdorff distance between the segments in consecutive frames (blue). Note that active cuts can be further accelerated in dynamic applications by "recycling" flow computed in the previous frame [
Image processing techniques are now widely spread out over a large quan-tity of domains: like med... more Image processing techniques are now widely spread out over a large quan-tity of domains: like medical imaging, movies post-production, games... Au-tomatic detection and extraction of regions of interest inside an image, a volume or a video is challenging problem since it is a starting point for many applications in image processing. However many techniques were developed during the last years and the state of the art methods suffer from some drawbacks: The Level Sets method only provides a local minimum while the Graph Cuts method comes from Combinatorial Community and could take advantage of the specificity of image processing problems. In this thesis, we propose two extensions of the previously cited methods in order to soften or remove these drawbacks. We first discuss the existing methods and show how they are related to the segmentation problem through an energy formulation. Then we intro-duce stochastic perturbations to the Level Sets method and we build a more
2007 IEEE 11th International Conference on Computer Vision, 2007
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical ... more Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by Edmonds, Karp, and Dinic [7, 6] in 1972, capacity scaling is well known in the combinatorial optimization community. Surprisingly, this major performance improving technique is overlooked in computer vision where graph cut methods typically solve energy minimization problems on huge N-D grids and algorithms' efficiency is a widely studied issue [3, 12, 16, 10]. Unlike some earlier hierarchical methods addressing efficiency of graph cuts in imaging, e.g. [16], capacity scaling preserves global optimality of the solution. This is the main motivation for our work studying capacity scaling in the context of vision. We show that capacity scaling significantly reduces non-polynomial theoretical time complexity of the max-flow algorithm in [3] to weakly polynomial O(m 2 n 2 log(U)) where U is the largest edge weight. While [3] is the fastest method for many applications in vision, capacity scaling gives several folds speed-ups for problems with large number of local minima. The effect is particularly strong in 3D applications with denser neighborhoods.
A genetic algorithm has been coupled with CFD simulations of a 600 MW boiler. The genetic algorit... more A genetic algorithm has been coupled with CFD simulations of a 600 MW boiler. The genetic algorithm was able to automatically generate innovative boiler settings. Correlations between operating parameters and boiler output data were obtained. A target function helped to achieve low-NO x configurations with low corrosion risk. The predicted NO x emissions are consistent with levels measured in the boiler.
Classic mosaic is one of the oldest and most durable art forms. There has been a growing interest... more Classic mosaic is one of the oldest and most durable art forms. There has been a growing interest in simulating classic mosaics from digital images recently. To be visually pleasing, a mosaic should satisfy the following constraints: tiles should be non-overlapping, tiles should align to the perceptually important edges in the underlying digital image, and orientation of the neighbouring tiles should vary smoothly across the mosaic. Most of the existing approaches operate in two steps: first they generate tile orientation field and then pack the tiles according to this field. However, previous methods perform these two steps based on heuristics or local optimisation which, in some cases, is not guaranteed to converge. Some other major disadvantages of previous approaches are: (i) either substantial user interaction or hard decision making such as edge detection is required before mosaicing starts (ii) the number of tiles per mosaic must be fixed beforehand, which may cause either undesired overlap or gap space between the tiles. In this work, we propose a novel approach by formulating the mosaic simulating problem in a global energy optimisation framework. Our algorithm also follows the two-step approach, but each step is performed with global optimisation. For the first step, we observe that the tile orientation constraints can be naturally formulated in an energy function that can be optimised with the α-expansion algorithm. For the second step of tightly packing the tiles, we develop a novel graph cuts based algorithm. Our approach does not require user interaction, explicit edge detection, or fixing the number of tiles, while producing results that are visually pleasing.
Classic mosaic is an old and durable art form. Generating artificial classic mosaics from digital... more Classic mosaic is an old and durable art form. Generating artificial classic mosaics from digital images is an interesting problem that has attracted attention in recent years. Previous approaches to mosaic generation are largely based on heuristics, and therefore it is harder to analyse, predict and improve their performance. In addition, previous methods have a number of disadvantages, such as requiring that the number of tiles in a mosaic is known a priori, or relying on extensive user interaction, or using heuristics for tile placement that lead to visible artefacts. We propose a classic mosaic generation algorithm that is based on a principled global optimization. Our approach is fully automatic. We design and optimize an objective function that incorporates the desired mosaic properties, such as tile alignment to significant image edges, prohibiting tile overlap, etc. Our optimization method is based on graph cuts, which proved to be a powerful optimization tool in graphics and computer vision. Experimental comparison to previous work demonstrate the advantages of our approach.
Based on recent work on Stochastic Partial Differential Equations (SPDEs), this paper presents a ... more Based on recent work on Stochastic Partial Differential Equations (SPDEs), this paper presents a simple and well-founded method to implement the stochastic evolution of a curve. First, we explain why great care should be taken when considering such an evolution in a Level Set framework. To guarantee the well-posedness of the evolution and to make it independent of the implicit representation of the initial curve, a Stratonovich differential has to be introduced. To implement this differential, a standard Ito plus drift approximation is proposed to turn an implicit scheme into an explicit one. Subsequently, we consider shape optimization techniques, which are a common framework to address various applications in Computer Vision, like segmentation, tracking, stereo vision etc. The objective of our approach is to improve these methods through the introduction of stochastic motion principles. The extension we propose can deal with local minima and with complex cases where the gradient o...
Digital matting consists in extracting a foreground element from a background image. Besides the ... more Digital matting consists in extracting a foreground element from a background image. Besides the image, usual matting methods need to be initialized with two disjoint regions : the set of foreground only pixels and the set of background only pixels. Pixels belonging to none of these two regions are considered as an undetermined blending between the foreground and the background. Here, one has to estimate the opacity (alpha channel) and the original foreground and background colors that have been blended. Initialization is a crucial step for these methods, and usually one has to specify accurate initial regions, leaving undetermined as few pixels as possible. This is especially true for recent methods that use local models. This paper proposes an unsupervised segmentation scheme that initializes any matting method by extracting the foreground and background regions from just a small subset of them. Standard statistical models are used for the foreground and background regions, while ...
Stochastic mean curvature motion in computer vision: Stochastic active contours
This paper presents a novel framework for image segmentation based on stochastic optimization. Du... more This paper presents a novel framework for image segmentation based on stochastic optimization. Dur-ing the last few years, several segmentation methods have been proposed to integrate different information in a varia-tional framework, where an objective function depending on both boundary information and region information is minimized using a gradient-descent method. Some recent methods are even able to extract the region model during the segmentation process itself. Yet, in complex cases, the objective function does not have any computable gradient. In other cases, the minimization process gets stuck in some local minimum, while no multi-resolution approach can be invoked. To deal with those two frequent problems, we pro-pose a stochastic optimization approach and show that even a simple Simulated Annealing method is powerful enough in many cases. Based on recent work on Stochastic Partial Differential Equations (SPDEs), we propose a simple and well-founded method to implement the...
Uploads
Papers by Olivier Juan