Search

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images. [ABSTRACT FROM AUTHOR]

We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their estimation using Bayesian filters, such as Kalman or particle filters. In particular, each filter estimates the state of a specific object feature, conditionally dependent on another feature estimated by a distinct filter. This dependence provides improved target representations, permitting us to segment it out from the background even in nonstationary sequences. Considering that the procedure of the Bayesian filters may be described by a "hypotheses generationhypotheses correction" strategy, the major novelty of our methodology compared to previous approaches is that the mutual dependence between filters is considered during the feature observation, that is, into the "hypotheses-correction" stage, instead of considering it when generating the hypotheses. This proves to be much more effective in terms of accuracy and reliability. The proposed method is analytically justified and applied to develop a robust tracking system that adapts online and simultaneously the color space where the image points are represented, the color distributions, the contour of the object, and its bounding box. Results with synthetic data and real video sequences demonstrate the robustness and versatility of our method. Index Terms--Bayesian tracking, multiple cue integration.

We present a novel vehicle detection and tracking system that works solely on 3D LiDAR information. Our approach segments vehicles using a dual-view representation of the 3D LiDAR point cloud on two independently trained convolutional neural networks, one for each view. A bounding box growing algorithm is applied to the fused output of the networks to properly enclose the segmented vehicles. Bounding boxes are grown using a probabilistic method that takes into account also occluded areas. The final vehicle bounding boxes act as observations for a multi-hypothesis tracking system which allows to estimate the position and velocity of the observed vehicles. We thoroughly evaluate our system on the KITTI benchmarks both for detection and tracking separately and show that our dual-branch classifier consistently outperforms previous single-branch approaches, improving or directly competing to other state of the art LiDAR-based methods. [ABSTRACT FROM AUTHOR]

In this paper we present an approach to reconstruct the 3D shape of multiple deforming objects from a collection of sparse, noisy and possibly incomplete 2D point tracks acquired by a single monocular camera. Additionally, the proposed solution estimates the camera motion and reasons about the spatial segmentation (i.e., identifies each of the deforming objects in every frame) and temporal clustering (i.e., splits the sequence into motion primitive actions). This advances competing work, which mainly tackled the problem for one single object and non-occluded tracks. In order to handle several objects at a time from partial observations, we model point trajectories as a union of spatial and temporal subspaces, and optimize the parameters of both modalities, the non-observed point tracks, the camera motion, and the time-varying 3D shape via augmented Lagrange multipliers. The algorithm is fully unsupervised and does not require any training data at all. We thoroughly validate the method on challenging scenarios with several human subjects performing different activities which involve complex motions and close interaction. We show our approach achieves state-of-the-art 3D reconstruction results, while it also provides spatial and temporal segmentation. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel interpretable shape model to encode object nonrigidity. We first use the initial frames of a monocular video to recover a rest shape, used later to compute a dissimilarity measure based on a distance matrix measurement. Spectral analysis is then applied to this matrix to obtain a reduced shape basis, that in contrast to existing approaches, can be physically interpreted. In turn, these precomputed shape bases are used to linearly span the deformation of a wide variety of objects. We introduce the low-rank basis into a sequential approach to recover both camera motion and nonrigid shape from the monocular video, by simply optimizing the weights of the linear combination using bundle adjustment. Since the number of parameters to optimize per frame is relatively small, specially when physical priors are considered, our approach is fast and can potentially run in real time. Validation is done in a wide variety of real-world objects, undergoing both inextensible and extensible deformations. Our approach achieves remarkable robustness to artifacts such as noisy and missing measurements and shows an improved performance to competing methods. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of simultaneously recovering 3D shape, pose and the elastic model of a deformable object from only 2D point tracks in a monocular video. This is a severely under-constrained problem that has been typically addressed by enforcing the shape or the point trajectories to lie on low-rank dimensional spaces. We show that formulating the problem in terms of a low-rank force space that induces the deformation and introducing the elastic model as an additional unknown, allows for a better physical interpretation of the resulting priors and a more accurate representation of the actual object’s behavior. In order to simultaneously estimate force, pose, and the elastic model of the object we use an expectation maximization strategy, where each of these parameters are successively learned by partial M-steps. Once the elastic model is learned, it can be transfered to similar objects to code its 3D deformation. Moreover, our approach can robustly deal with missing data, and encode both rigid and non-rigid points under the same formalism. We thoroughly validate the approach on Mocap and real sequences, showing more accurate 3D reconstructions than state-of-the-art, and additionally providing an estimate of the full elastic model with no a priori information. [ABSTRACT FROM AUTHOR]

Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of news articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce an adaptive CNN architecture that shares most of the structure for multiple tasks including source detection, article illustration and geolocation of articles. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and user comments). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field. [ABSTRACT FROM PUBLISHER]

In this paper we introduce the Boosted Random Ferns (BRFs) to rapidly build discriminative classifiers for learning and detecting object categories. At the core of our approach we use standard random ferns, but we introduce four main innovations that let us bring ferns from an instance to a category level, and still retain efficiency. First, we define binary features on the histogram of oriented gradients-domain (as opposed to intensity-), allowing for a better representation of intra-class variability. Second, both the positions where ferns are evaluated within the sliding window, and the location of the binary features for each fern are not chosen completely at random, but instead we use a boosting strategy to pick the most discriminative combination of them. This is further enhanced by our third contribution, that is to adapt the boosting strategy to enable sharing of binary features among different ferns, yielding high recognition rates at a low computational cost. And finally, we show that training can be performed online, for sequentially arriving images. Overall, the resulting classifier can be very efficiently trained, densely evaluated for all image locations in about 0.1 seconds, and provides detection rates similar to competing approaches that require expensive and significantly slower processing times. We demonstrate the effectiveness of our approach by thorough experimentation in publicly available datasets in which we compare against state-of-the-art, and for tasks of both 2D detection and 3D multi-view estimation. [ABSTRACT FROM PUBLISHER]

We propose a new approach to simultaneously recover camera pose and 3D shape of non-rigid and potentially extensible surfaces from a monocular image sequence. For this purpose, we make use of the Extended Kalman Filter based Simultaneous Localization And Mapping (EKF-SLAM) formulation, a Bayesian optimization framework traditionally used in mobile robotics for estimating camera pose and reconstructing rigid scenarios. In order to extend the problem to a deformable domain we represent the object's surface mechanics by means of Navier's equations, which are solved using a Finite Element Method (FEM). With these main ingredients, we can further model the material's stretching, allowing us to go a step further than most of current techniques, typically constrained to surfaces undergoing isometric deformations. We extensively validate our approach in both real and synthetic experiments, and demonstrate its advantages with respect to competing methods. More specifically, we show that besides simultaneously retrieving camera pose and non-rigid shape, our approach is adequate for both isometric and extensible surfaces, does not require neither batch processing all the frames nor tracking points over the whole sequence and runs at several frames per second. [ABSTRACT FROM PUBLISHER]

We present a novel approach for feature correspondence and multiple structure discovery in computer vision. In contrast to existing methods, we exploit the fact that point-sets on the same structure usually lie close to each other, thus forming clusters in the image. Given a pair of input images, we initially extract points of interest and extract hierarchical representations by agglomerative clustering. We use the maximum weighted clique problem to find the set of corresponding clusters with maximum number of inliers representing the multiple structures at the correct scales. Our method is parameter-free and only needs two sets of points along with their tentative correspondences, thus being extremely easy to use. We demonstrate the effectiveness of our method in multiple-structure fitting experiments in both publicly available and in-house datasets. As shown in the experiments, our approach finds a higher number of structures containing fewer outliers compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We present a new approach for matching sets of branching curvilinear structures that form graphs embedded in \mathbb R^2 or \mathbb R^3 and may be subject to deformations. Unlike earlier methods, ours does not rely on local appearance similarity nor does require a good initial alignment. Furthermore, it can cope with non-linear deformations, topological differences, and partial graphs. To handle arbitrary non-linear deformations, we use Gaussian process regressions to represent the geometrical mapping relating the two graphs. In the absence of appearance information, we iteratively establish correspondences between points, update the mapping accordingly, and use it to estimate where to find the most likely correspondences that will be used in the next step. To make the computation tractable for large graphs, the set of new potential matches considered at each iteration is not selected at random as with many RANSAC-based algorithms. Instead, we introduce a so-called Active Testing Search strategy that performs a priority search to favor the most likely matches and speed-up the process. We demonstrate the effectiveness of our approach first on synthetic cases and then on angiography data, retinal fundus images, and microscopy image stacks acquired at very different resolutions. [ABSTRACT FROM PUBLISHER]

We propose a novel approach for the estimation of the pose and focal length of a camera from a set of 3D-to-2D point correspondences. Our method compares favorably to competing approaches in that it is both more accurate than existing closed form solutions, as well as faster and also more accurate than iterative ones. Our approach is inspired on the EPnP algorithm, a recent O(n) solution for the calibrated case. Yet we show that considering the focal length as an additional unknown renders the linearization and relinearization techniques of the original approach no longer valid, especially with large amounts of noise. We present new methodologies to circumvent this limitation termed exhaustive linearization and exhaustive relinearization which perform a systematic exploration of the solution space in closed form. The method is evaluated on both real and synthetic data, and our results show that besides producing precise focal length estimation, the retrieved camera pose is almost as accurate as the one computed using the EPnP, which assumes a calibrated camera. [ABSTRACT FROM AUTHOR]

Recovering the 3D shape of deformable surfaces from single images is known to be a highly ambiguous problem because many different shapes may have very similar projections. This is commonly addressed by restricting the set of possible shapes to linear combinations of deformation modes and by imposing additional geometric constraints. Unfortunately, because image measurements are noisy, such constraints do not always guarantee that the correct shape will be recovered. To overcome this limitation, we introduce a stochastic sampling approach to efficiently explore the set of solutions of an objective function based on point correspondences. This allows us to propose a small set of ambiguous candidate 3D shapes and then use additional image information to choose the best one. As a proof of concept, we use either motion or shading cues to this end and show that we can handle a complex objective function without having to solve a difficult nonlinear minimization problem. The advantages of our method are demonstrated on a variety of problems including both real and synthetic data. [ABSTRACT FROM AUTHOR]

We propose a non-iterative solution to the P nP problem—the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences—whose computational complexity grows linearly with n. This is in contrast to state-of-the-art methods that are O( n 5) or even O( n 8), without being more accurate. Our method is applicable for all n≥4 and handles properly both planar and non-planar configurations. Our central idea is to express the n 3D points as a weighted sum of four virtual control points. The problem then reduces to estimating the coordinates of these control points in the camera referential, which can be done in O( n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12×12 matrix and solving a small constant number of quadratic equations to pick the right weights. Furthermore, if maximal precision is required, the output of the closed-form solution can be used to initialize a Gauss-Newton scheme, which improves accuracy with negligible amount of additional time. The advantages of our method are demonstrated by thorough testing on both synthetic and real-data. [ABSTRACT FROM AUTHOR]

We present a system for refocusing images and videos of dynamic scenes using a novel, single-view depth estimation method. Our method for obtaining depth is based on the defocus of a sparse set of dots projected onto the scene. In contrast to other active illu- mination techniques, the projected pattern of dots can be removed from each captured image and its brightness easily controlled in or- der to avoid under- or over-exposure. The depths corresponding to the projected dots and a color segmentation of the image are used to compute an approximate depth map of the scene with clean region boundaries. The depth map is used to refocus the acquired image after the dots are removed, simulating realistic depth of field effects. Experiments on a wide variety of scenes, including close-ups and live action, demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a new technique to perform figure-ground segmentation in image sequences of moving objects under varying illumination conditions. Unlike most of the algorithms that adapt color, there is not the assumption of smooth change of the viewing conditions. To cope with this, we propose the use of a new colorspace that maximizes the foreground/background class separability based on the ‘Linear Discriminant Analysis’ method. Moreover, we introduce a technique that formulates multiple hypotheses about the next state of the color distribution (some of these hypotheses take into account small and gradual changes in the color model and others consider more abrupt and unexpected variations) and the hypothesis that generates the best object segmentation is used to remove noisy edges from the image. This simplifies considerably the final step of fitting a deformable contour to the object boundary, thus allowing a standard snake formulation to successfully track non-rigid contours. In the same manner, the contour estimate is used to correct the color model. The integration of color and shape is done in a stage called ‘sample concentration’, introduced as a final step to the well-known CONDENSATION algorithm [Copyright &y& Elsevier]

Measuring the nearshore bathymetry is critical in coastal management and morphodynamic studies. The recent advent of Unmanned Aerial Vehicles (UAVs), in combination with coastal video monitoring techniques, allows for an alternative and low cost evaluation of the nearshore bathymetry. Camera calibration and stabilization is a critical issue in bathymetry estimation from video systems. This work introduces a new methodology in order to obtain such bathymetries, and it compares the results to echo-sounder ground truth data. The goal is to gain a better understanding on the influence of the camera calibration and stabilization on the inferred bathymetry. The results show how the proposed methodology allows for accurate evaluations of the bathymetry, with overall root mean square errors in the order of 40 cm. It is shown that the intrinsic calibration of the camera, related to the lens distortion, is the most critical aspect. Here, the intrinsic calibration that was obtained directly during the flight yields the best results. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel error measure to compare a computer-generated segmentation of images or volumes against ground truth. This measure, which we call Tolerant Edit Distance (TED), is motivated by two observations that we usually encounter in biomedical image processing: (1) Some errors, like small boundary shifts, are tolerable in practice. Which errors are tolerable is application dependent and should be explicitly expressible in the measure. (2) Non-tolerable errors have to be corrected manually. The effort needed to do so should be reflected by the error measure. Our measure is the minimal weighted sum of split and merge operations to apply to one segmentation such that it resembles another segmentation within specified tolerance bounds. This is in contrast to other commonly used measures like Rand index or variation of information, which integrate small, but tolerable, differences. Additionally, the TED provides intuitive numbers and allows the localization and classification of errors in images or volumes. We demonstrate the applicability of the TED on 3D segmentations of neurons in electron microscopy images where topological correctness is arguable more important than exact boundary locations. Furthermore, we show that the TED is not just limited to evaluation tasks. We use it as the loss function in a max-margin learning framework to find parameters of an automatic neuron segmentation algorithm. We show that training to minimize the TED, i.e., to minimize crucial errors, leads to higher segmentation accuracy compared to other learning methods. [ABSTRACT FROM AUTHOR]

Robotic handling of textile objects in household environments is an emerging application that has recently received considerable attention thanks to the development of domestic robots. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields a desired configuration. In this work we propose a vision-based method, built on the Bag of Visual Words approach, that combines appearance and 3D information to detect parts suitable for grasping in clothes, even when they are highly wrinkled. We also contribute a new, annotated, garment part dataset that can be used for benchmarking classification, part detection, and segmentation algorithms. The dataset is used to evaluate our approach and several state-of-the-art 3D descriptors for the task of garment part detection. Results indicate that appearance is a reliable source of information, but that augmenting it with 3D information can help the method perform better with new clothing items. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we show that the performance of binary classifiers based on Boosted Random Ferns can be significantly improved by appropriately bootstrapping the training step. This results in a classifier which is both highly discriminative and computationally efficient and is particularly suitable when only small sets of training images are available. During the learning process, a small set of labeled images is used to train the boosting binary classifier. The classifier is then evaluated over the training set and warped versions of the classified and misclassified patches are progressively added into the positive and negative sample sets for a new re-training step. In this paper we thoroughly study the conditions under which this bootstrapping scheme improves the detection rates. In particular we assess the quality of detection both as a function of the number of bootstrapping iterations and the size of the training set. We compare our algorithm against state-of-the-art approaches for several databases including faces, cars, motorbikes and horses, and show remarkable improvements in detection rates with just a few bootstrapping steps. [Copyright &y& Elsevier]