Daniel Berjón

Moving object detection for real-time augmented reality applications in a GPGPU

The last generation of consumer electronic devices is endowed with Augmented Reality (AR) tools. These tools require moving object detection strategies, which should be fast and efficient, to carry out higher level object analysis tasks. We propose a lightweight spatio-temporal-based non-parametric background-foreground modeling strategy in a General Purpose Graphics Processing Unit (GPGPU), which provides real-time high-quality results in a great variety of scenarios and is suitable for AR applications.

GPU-based implementation of an optimized nonparametric background modeling for real-time moving object detection

Answering to the growing demand of computer vision tools for the last generations of consumer electronic devices equipped with smart cameras, several nonparametric moving detection algorithms have been developed. These algorithms, by modeling both background and foreground from spatio-temporal reference data, provide satisfactory results in many complex scenarios. However, to be computationally efficient, they apply some simplifications that decrease the quality of the detections. This paper presents a novel real-time implementation of an optimized spatio-temporal nonparametric moving object detection strategy. To improve the quality of previous algorithms, the bandwidths of the kernels required to model the background are dynamically estimated, and the background model is also selectively updated. The proposed implementation features smart cooperation between a computer/devices Central and Graphics Processing Units (CPU/GPU) and extensive usage of the texture mapping and filtering units of the latter, including a novel method for fast evaluation of Gaussian functions. Thanks to these features, high quality detection rates are achieved while respecting the realtime restrictions imposed by computer vision tools running on current consumer electronic devices.

Seamless, Static Multi-Texturing of 3D Meshes

In the context of 3D reconstruction, we present a static multi‐texturing system yielding a seamless texture atlas calculated by combining the colour information from several photos from the same subject covering most of its surface. These pictures can be provided by shooting just one camera several times when reconstructing a static object, or a set of synchronized cameras, when dealing with a human or any other moving object. We suppress the colour seams due to image misalignments and irregular lighting conditions that multi‐texturing approaches typically suffer from, while minimizing the blurring effect introduced by colour blending techniques. Our system is robust enough to compensate for the almost inevitable inaccuracies of 3D meshes obtained with visual hull–based techniques: errors in silhouette segmentation, inherently bad handling of concavities, etc.

Optimal Piecewise Linear Function Approximation for GPU-Based Applications

Many computer vision and human-computer interaction applications developed in recent years need evaluating complex and continuous mathematical functions as an essential step toward proper operation. However, rigorous evaluation of these kind of functions often implies a very high computational cost, unacceptable in real-time applications. To alleviate this problem, functions are commonly approximated by simpler piecewise-polynomial representations. Following this idea, we propose a novel, efficient, and practical technique to evaluate complex and continuous functions using a nearly optimal design of two types of piecewise linear approximations in the case of a large budget of evaluation subintervals. To this end, we develop a thorough error analysis that yields asymptotically tight bounds to accurately quantify the approximation performance of both representations. It provides an improvement upon previous error estimates and allows the user to control the tradeoff between the approximation error and the number of evaluation subintervals. To guarantee real-time operation, the method is suitable for, but not limited to, an efficient implementation in modern graphics processing units, where it outperforms previous alternative approaches by exploiting the fixed-function interpolation routines present in their texture units. The proposed technique is a perfect match for any application requiring the evaluation of continuous functions; we have measured in detail its quality and efficiency on several functions, and, in particular, the Gaussian function because it is extensively used in many areas of computer vision and cybernetics, and it is expensive to evaluate.

Region-based moving object detection using spatially conditioned nonparametric models in a GPU

A novel GPU-based nonparametric moving object detection strategy for computer vision tools requiring real-time processing is proposed. An alternative and efficient Bayesian classifier to combine nonparametric background and foreground models allows increasing correct detections while avoiding false detections. Additionally, an efficient region of interest analysis significantly reduces the computational cost of the detections.

Automatic system for virtual human reconstruction with 3D mesh multi-texturing and facial enhancement

The present paper presents a fully automatic low-cost system for generating animatable and statically multi-textured avatars of real people captured with several standard cameras. Our system features a novel technique for generating view-independent texture atlases computed from the original images, and two proposals for improving the quality of the facial region of the 3D mesh: a purely passive one implying no additional cost, and another based on active techniques such as structured light projection.

Optimal Polygonal

The analysis of complex nonlinear systems is often carried out using simpler piecewise linear representations of them. A principled and practical technique is proposed to linearize and evaluate arbitrary continuous nonlinear functions using polygonal (continuous piecewise linear) models under the L1 norm. A thorough error analysis is developed to guide an optimal design of two kinds of polygonal approximations in the asymptotic case of a large budget of evaluation subintervals N. The method allows the user to obtain the level of linearization (N) for a target approximation error and vice versa. It is suitable for, but not limited to, an efficient implementation in modern Graphics Processing Units (GPUs), allowing real-time performance of computationally demanding applications. The quality and efficiency of the technique has been measured in detail on two nonlinear functions that are widely used in many areas of scientific computing and are expensive to evaluate.

L_{1}

3D mesh compression is essential in the context of network-based virtual worlds, but so are objective and subjective fidelity of the reconstructed mesh to the original one. Unfortunately, it is difficult to establish a fair way to compare objectively two textured, triangular 3D meshes meant to approximate the surface of the same 3D object. We explain why by elaborating on how the geometric distance between two meshes can be estimated, after introducing some basic concepts related to mesh shape and a brief taxonomy of static 3D mesh coding techniques. We review a selection of such coding techniques, almost all of which deal only with the shape of the surface, and then focus on surface appearance, usually described separately with a texture to be mapped onto the 3D mesh at rendering time, and we also review existing techniques specifically devised to compress textures meant for 3D models. Finally, we discuss the even larger complexity of establishing any reasonable way to compare the subjective quality of the experience produced by two versions of the same 3D object, especially if different rendering methods may be used.

Linearization and Fast Interpolation of Nonlinear Systems

In this paper, we explore the challenges posed by wide baseline camera configurations for depth-image-based rendering, which should provide greater freedom for choosing the virtual viewpoint in a Free Viewpoint Video context, compared with the usual camera configurations intended for use in 3DTV settings. We implement a backward mapping approach with a custom filtering scheme based on median filters. Whilst the results back our initial assumption that this camera configuration provides good mobility, we show that the usual encoding for depth information referred to a global reference system is wrong and reference systems local to each camera should be used instead.

Objective and subjective evaluation of static 3D mesh compression

There is a huge proliferation of surveillance systems that require strategies for detecting different kinds of stationary foreground objects (e.g., unattended packages or illegally parked vehicles). As these strategies must be able to detect foreground objects remaining static in crowd scenarios, regardless of how long they have not been moving, several algorithms for detecting different kinds of such foreground objects have been developed over the last decades. This paper presents an efficient and high-quality strategy to detect stationary foreground objects, which is able to detect not only completely static objects but also partially static ones. Three parallel nonparametric detectors with different absorption rates are used to detect currently moving foreground objects, short-term stationary foreground objects, and long-term stationary foreground objects. The results of the detectors are fed into a novel finite state machine that classifies the pixels among background, moving foreground objects, stationary foreground objects, occluded stationary foreground objects, and uncovered background. Results show that the proposed detection strategy is not only able to achieve high quality in several challenging situations but it also improves upon previous strategies.