Efficient modeling of entangled details for natural scenes

Digital landscape realism often comes from the multitude of details that are hard to model such as fallen leaves, rock piles or entangled fallen branches. In this article, we present a method for augmenting natural scenes with a huge amount of details such as grass tufts, stones, leaves or twigs. Our approach takes advantage of the observation that those details can be approximated by replications of a few similar objects and therefore relies on mass‐instancing. We propose an original structure, the Ghost Tile, that stores a huge number of overlapping candidate objects in a tile, along with a pre‐computed collision graph. Details are created by traversing the scene with the Ghost Tile and generating instances according to user‐defined density fields that allow to sculpt layers and piles of entangled objects while providing control over their density and distribution.     

Maximizing the Predictivity of Smooth Deformable Image Warps through Cross-Validation

Estimating smooth image warps from landmarks is an important problem in computer vision and medical image analysis. The standard paradigm is to find the model parameters by minimizing a compound energy including a data term and a smoother, balanced by a ‘smoothing parameter’ that is usually fixed by trial and error. We point out that warp estimation is an instance of the general supervised machine learning problem of fitting a flexible model to data, and propose to learn the smoothing parameter while estimating the warp. The leading idea is to depart from the usual paradigm of minimizing the energy to the one of maximizing the predictivity of the warp, i.e. its ability to do well on the entire image, rather than only on the given landmarks. We use cross-validation to measure predictivity, and propose a complete framework to solve for the desired warp. We point out that the well-known non-iterative closed-form for the leave-one-out cross-validation score is actually a good approximation to the true score and show that it extends to the warp estimation problem by replacing the usual vector two-norm by the matrix Frobenius norm. Experimental results on real data show that the procedure selects sensible smoothing parameters, very close to user selected ones.     

Simultaneous segmentation and classification of human actions in video streams using deeply optimized Hough transform

Most researches on human activity recognition do not take into account the temporal localization of actions. In this paper, a new method is designed to model both actions and their temporal domains. This method is based on a new Hough method which outperforms previous published ones on honeybee dataset thanks to a deeper optimization of the Hough variables. Experiments are performed to select skeleton features adapted to this method and relevant to capture human actions. With these features, our pipeline improves state-of-the-art performances on TUM dataset and outperforms baselines on several public datasets.     

Activity representation with motion hierarchies

Complex activities, e.g. pole vaulting, are composed of a variable number of sub-events connected by complex spatio-temporal relations, whereas simple actions can be represented as sequences of short temporal parts. In this paper, we learn hierarchical representations of activity videos in an unsupervised manner. These hierarchies of mid-level motion components are data-driven decompositions specific to each video. We introduce a spectral divisive clustering algorithm to efficiently extract a hierarchy over a large number of tracklets (i.e. local trajectories). We use this structure to represent a video as an unordered binary tree. We model this tree using nested histograms of local motion features. We provide an efficient positive definite kernel that computes the structural and visual similarity of two hierarchical decompositions by relying on models of their parent–child relations. We present experimental results on four recent challenging benchmarks: the High Five dataset (Patron-Perez et al., High five: recognising human interactions in TV shows, 2010), the Olympics Sports dataset (Niebles et al., Modeling temporal structure of decomposable motion segments for activity classification, 2010), the Hollywood 2 dataset (Marszalek et al., Actions in context, 2009), and the HMDB dataset (Kuehne et al., HMDB: A large video database for human motion recognition, 2011). We show that per-video hierarchies provide additional information for activity recognition. Our approach improves over unstructured activity models, baselines using other motion decomposition algorithms, and the state of the art.     

Infinitesimal Plane-Based Pose Estimation

Estimating the pose of a plane given a set of point correspondences is a core problem in computer vision with many applications including Augmented Reality (AR), camera calibration and 3D scene reconstruction and interpretation. Despite much progress over recent years there is still the need for a more efficient and more accurate solution, particularly in mobile applications where the run-time budget is critical. We present a new analytic solution to the problem which is far faster than current methods based on solving Pose from \(n\) Points (PnP) and is in most cases more accurate. Our approach involves a new way to exploit redundancy in the homography coefficients. This uses the fact that when the homography is noisy it will estimate the true transform between the model plane and the image better at some regions on the plane than at others. Our method is based on locating a point where the transform is best estimated, and using only the local transformation at that point to constrain pose. This involves solving pose with a local non-redundant 1st-order PDE. We call this framework Infinitesimal Plane-based Pose Estimation (IPPE), because one can think of it as solving pose using the transform about an infinitesimally small region on the surface. We show experimentally that IPPE leads to very accurate pose estimates. Because IPPE is analytic it is both extremely fast and allows us to fully characterise the method in terms of degeneracies, number of returned solutions, and the geometric relationship of these solutions. This characterisation is not possible with state-of-the-art PnP methods.     

Identification of distinctive protein expression patterns in colorectal adenoma

Purpose: As a pre‐malignant precursor, adenoma provides an ideal tissue for proteome profiling to investigate early colorectal cancer development and provide possible targets for preventive interventions. The aim of this study was to identify patterns of differential protein expression that distinguish colorectal adenoma from normal tissue. Experimental design: Twenty paired samples of adenoma and normal mucosa were analysed by 2‐DE and MALDI‐TOF/TOF MS to detect proteins with ≥2‐fold differential expression. Results: Four proteins were up‐regulated in adenoma (Annexin A3, S100A11, S100P and eIF5A‐1) and three were down‐regulated (Galectin‐1, S100A9 and FABPL). S100P, galectin‐1, S100A9 and FABPL expression was localised by immunohistochemistry. Conclusions and clinical relevance: Distinctive patterns of in vivo protein expression in colorectal adenoma were identified for the first time. These proteins have important functions in cell differentiation, proliferation and metabolism, and may play a crucial role in early colorectal carcinogenesis. The ability to recognise premalignant lesions may have important applications in cancer prevention.     

Spatiotemporal filtering of sequences of ultrasound images to estimate a dense field of velocities

Blood velocity estimation is required in many clinical applications. Ultrasonic imaging is often used to reach this goal. This article presents a velocity vector estimation method from ultrasonic imaging. It complements Doppler imaging, which has several limitations. New techniques such as block-matching (BM) and decorrelation-based methods have already been developed to overcome these limitations. Our method is based on spatiotemporal filtering to estimate the apparent velocity vector for each pixel of the sequence of ultrasound images. A moving object is represented by a group of pixels travelling from image to image in the sequence, leaving a trace in the spatiotemporal volume. A bank of filters was designed to estimate a local texture orientation related to the velocity of the object. The method was first developed in 2D then extended in 3D to estimate the two components in the imaging plane. The method was applied to sequences of ultrasound images of calibrated flow in a vessel (mean velocity ). The velocity estimates obtained in 2D and 3D showed mean errors less than 5% and 12%, respectively. The results are presented as dynamic cartography and dense fields of velocity vectors. The associated velocity profiles show good agreement with the theoretical parabolic profile of laminar flow. Our approach has been compared with three other velocity estimation methods and showed good performance in comparison with them.     

Solving an integrated employee timetabling and job-shop scheduling problem via hybrid branch-and-bound

We propose exact hybrid methods based on integer linear programming (ILP) and constraint programming (CP) for an integrated employee timetabling and job-shop scheduling problem. Each method we investigate uses a CP formulation associated with an LP relaxation. Under a CP framework, the LP relaxation is integrated into a global constraint using in addition reduced cost-based filtering techniques. We propose two CP formulations of the problem yielding two different LP relaxations. The first formulation is based on a direct representation of the problem. The second formulation is based on a decomposition in intervals of the possible operation starting times. We show the theoretical interest of the decomposition-based representation compared to the direct representation through the analysis of dominant schedules. Computational experiments on a set of randomly generated instances confirm the superiority of the decomposition-based representation. In both cases, the hybrid methods outperform pure CP for employee cost minimization while it is not the case for makespan minimization. The experiments also investigate the interest of the proposed integrated method compared to a sequential approach and show its potential for multiobjective optimization.     

The Isowarp: The Template-Based Visual Geometry of Isometric Surfaces

International Journal of Computer Vision - Registration maps or warps form a key element in Shape-from-Template (SfT). They relate the template with the input image, which contains the projection...