Reconhecimento de faces 3D com Kinect

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Calibración de cámaras de tiempo de vuelo: ajuste adaptativo del tiempo de integración y análisis de la frecuencia de modulación

La percepción de profundidad se hace imprescindible en muchas tareas de manipulación, control visual y navegación de robots. Las cámaras de tiempo de vuelo (ToF: Time of Flight) generan imágenes de rango que proporcionan medidas de profundidad en tiempo real. No obstante, el parámetro distancia que calculan estas cámaras es fuertemente dependiente del tiempo de integración que se configura en el sensor y de la frecuencia de modulación empleada por el sistema de iluminación que integran. En este artículo, se presenta una metodología para el ajuste adaptativo del tiempo de integración y un análisis experimental del comportamiento de una cámara ToF cuando se modifica la frecuencia de modulación. Este método ha sido probado con éxito en algoritmos de control visual con arquitectura ‘eye-in-hand’ donde el sistema sensorial está compuesto por una cámara ToF. Además, la misma metodología puede ser aplicada en otros escenarios de trabajo.

Estimating 3D Body Pose Using Uncalibrated Cameras

An approach for estimating 3D body pose from multiple, uncalibrated views is proposed. First, a mapping from image features to 2D body joint locations is computed using a statistical framework that yields a set of several body pose hypotheses. The concept of a "virtual camera" is introduced that makes this mapping invariant to translation, image-plane rotation, and scaling of the input. As a consequence, the calibration matrices (intrinsics) of the virtual cameras can be considered completely known, and their poses are known up to a single angular displacement parameter. Given pose hypotheses obtained in the multiple virtual camera views, the recovery of 3D body pose and camera relative orientations is formulated as a stochastic optimization problem. An Expectation-Maximization algorithm is derived that can obtain the locally most likely (self-consistent) combination of body pose hypotheses. Performance of the approach is evaluated with synthetic sequences as well as real video sequences of human motion.

Multi-view 3D reconstruction using virtual cameras

Ce mémoire s'intéresse à la reconstruction d'un modèle 3D à partir de plusieurs images. Le modèle 3D est élaboré avec une représentation hiérarchique de voxels sous la forme d'un octree. Un cube englobant le modèle 3D est calculé à partir de la position des caméras. Ce cube contient les voxels et il définit la position de caméras virtuelles. Le modèle 3D est initialisé par une enveloppe convexe basée sur la couleur uniforme du fond des images. Cette enveloppe permet de creuser la périphérie du modèle 3D. Ensuite un coût pondéré est calculé pour évaluer la qualité de chaque voxel à faire partie de la surface de l'objet. Ce coût tient compte de la similarité des pixels provenant de chaque image associée à la caméra virtuelle. Finalement et pour chacune des caméras virtuelles, une surface est calculée basée sur le coût en utilisant la méthode de SGM. La méthode SGM tient compte du voisinage lors du calcul de profondeur et ce mémoire présente une variation de la méthode pour tenir compte des voxels précédemment exclus du modèle par l'étape d'initialisation ou de creusage par une autre surface. Par la suite, les surfaces calculées sont utilisées pour creuser et finaliser le modèle 3D. Ce mémoire présente une combinaison innovante d'étapes permettant de créer un modèle 3D basé sur un ensemble d'images existant ou encore sur une suite d'images capturées en série pouvant mener à la création d'un modèle 3D en temps réel.

Desenvolvimento de um sistema moving cameras para reconstrução 3D de movimentos submersos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Accurate depth-color scene modeling for 3D contents generation with low cost depth cameras

In this paper, we present a depth-color scene modeling strategy for indoors 3D contents generation. It combines depth and visual information provided by a low-cost active depth camera to improve the accuracy of the acquired depth maps considering the different dynamic nature of the scene elements. Accurate depth and color models of the scene background are iteratively built, and used to detect moving elements in the scene. The acquired depth data is continuously processed with an innovative joint-bilateral filter that efficiently combines depth and visual information thanks to the analysis of an edge-uncertainty map and the detected foreground regions. The main advantages of the proposed approach are: removing depth maps spatial noise and temporal random fluctuations; refining depth data at object boundaries, generating iteratively a robust depth and color background model and an accurate moving object silhouette.

μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras

Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Progressive 3D reconstruction of infrastructure with videogrammetry

A number of methods are commonly used today to collect infrastructure's spatial data (time-of-flight, visual triangulation, etc.). However, current practice lacks a solution that is accurate, automatic, and cost-efficient at the same time. This paper presents a videogrammetric framework for acquiring spatial data of infrastructure which holds the promise to address this limitation. It uses a calibrated set of low-cost high resolution video cameras that is progressively traversed around the scene and aims to produce a dense 3D point cloud which is updated in each frame. It allows for progressive reconstruction as opposed to point-and-shoot followed by point cloud stitching. The feasibility of the framework is studied in this paper. Required steps through this process are presented and the unique challenges of each step are identified. Results specific to each step are also presented.

Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

The commercial far-range (>10 m) spatial data collection methods for acquiring infrastructure’s geometric data are not completely automated because of the necessary manual pre- and/or post-processing work. The required amount of human intervention and, in some cases, the high equipment costs associated with these methods impede their adoption by the majority of infrastructure mapping activities. This paper presents an automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras. In this process SURF features are automatically detected and matched between each pair of stereo video frames. 3D coordinates of the matched feature points are then calculated via triangulation. The detected SURF features in two successive video frames are automatically matched and the RANSAC algorithm is used to discard mismatches. The quaternion motion estimation method is then used along with bundle adjustment optimization to register successive point clouds. The method was tested on a database of infrastructure stereo video streams. The validity and statistical significance of the results were evaluated by comparing the spatial distance of randomly selected feature points with their corresponding tape measurements.

Automated 3D Vision Tracking for Project Control Support

On-site tracking in open construction sites is often difficult because of the large amounts of items that are present and need to be tracked. Additionally, the amounts of occlusions/obstructions present create a highly complex tracking environment. Existing tracking methods are based mainly on Radio Frequency technologies, including Global Positioning Systems (GPS), Radio Frequency Identification (RFID), Bluetooth and Wireless Fidelity (Wi-Fi, Ultra-Wideband, etc). These methods require considerable amounts of pre-processing time since they need to manually deploy tags and keep record of the items they are placed on. In construction sites with numerous entities, tags installation, maintenance and decommissioning become an issue since it increases the cost and time needed to implement these tracking methods. This paper presents a novel method for open site tracking with construction cameras based on machine vision. According to this method, video feed is collected from on site video cameras, and the user selects the entity he wishes to track. The entity is tracked in each video using 2D vision tracking. Epipolar geometry is then used to calculate the depth of the marked area to provide the 3D location of the entity. This method addresses the limitations of radio frequency methods by being unobtrusive and using inexpensive, and easy to deploy equipment. The method has been implemented in a C++ prototype and preliminary results indicate its effectiveness

Automated 3D Structure Inference of Civil Infrastructure Using a Stereo Camera Set

The commercial far-range (>10m) infrastructure spatial data collection methods are not completely automated. They need significant amount of manual post-processing work and in some cases, the equipment costs are significant. This paper presents a method that is the first step of a stereo videogrammetric framework and holds the promise to address these issues. Under this method, video streams are initially collected from a calibrated set of two video cameras. For each pair of simultaneous video frames, visual feature points are detected and their spatial coordinates are then computed. The result, in the form of a sparse 3D point cloud, is the basis for the next steps in the framework (i.e., camera motion estimation and dense 3D reconstruction). A set of data, collected from an ongoing infrastructure project, is used to show the merits of the method. Comparison with existing tools is also shown, to indicate the performance differences of the proposed method in the level of automation and the accuracy of results.

Recovering 3D Structure of Poorly Textured Infrastructure Scenes Using Point and Line Features

Most of the existing automated machine vision-based techniques for as-built documentation of civil infrastructure utilize only point features to recover the 3D structure of a scene. However it is often the case in man-made structures that not enough point features can be reliably detected (e.g. buildings and roofs); this can potentially lead to the failure of these techniques. To address the problem, this paper utilizes the prominence of straight lines in infrastructure scenes. It presents a hybrid approach that benefits from both point and line features. A calibrated stereo set of video cameras is used to collect data. Point and line features are then detected and matched across video frames. Finally, the 3D structure of the scene is recovered by finding 3D coordinates of the matched features. The proposed approach has been tested on realistic outdoor environments and preliminary results indicate its capability to deal with a variety of scenes.

Inferring 3D Structure with a Statistical Image-Based Shape Model

We present an image-based approach to infer 3D structure parameters using a probabilistic "shape+structure'' model. The 3D shape of a class of objects may be represented by sets of contours from silhouette views simultaneously observed from multiple calibrated cameras. Bayesian reconstructions of new shapes can then be estimated using a prior density constructed with a mixture model and probabilistic principal components analysis. We augment the shape model to incorporate structural features of interest; novel examples with missing structure parameters may then be reconstructed to obtain estimates of these parameters. Model matching and parameter inference are done entirely in the image domain and require no explicit 3D construction. Our shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and works even with only a single input view. Using a dataset of thousands of pedestrian images generated from a synthetic model, we can perform accurate inference of the 3D locations of 19 joints on the body based on observed silhouette contours from real images.

Multi-scale 3D Scene Flow from Binocular Stereo Sequences

Scene flow methods estimate the three-dimensional motion field for points in the world, using multi-camera video data. Such methods combine multi-view reconstruction with motion estimation approaches. This paper describes an alternative formulation for dense scene flow estimation that provides convincing results using only two cameras by fusing stereo and optical flow estimation into a single coherent framework. To handle the aperture problems inherent in the estimation task, a multi-scale method along with a novel adaptive smoothing technique is used to gain a regularized solution. This combined approach both preserves discontinuities and prevents over-regularization-two problems commonly associated with basic multi-scale approaches. Internally, the framework generates probability distributions for optical flow and disparity. Taking into account the uncertainty in the intermediate stages allows for more reliable estimation of the 3D scene flow than standard stereo and optical flow methods allow. Experiments with synthetic and real test data demonstrate the effectiveness of the approach.