Edge-preserving color image denoising through tensor voting

This paper presents a new method for edge-preserving color image denoising based on the tensor voting framework, a robust perceptual grouping technique used to extract salient information from noisy data. The tensor voting framework is adapted to encode color information through tensors in order to propagate them in a neighborhood by using a specific voting process. This voting process is specifically designed for edge-preserving color image denoising by taking into account perceptual color differences, region uniformity and edginess according to a set of intuitive perceptual criteria. Perceptual color differences are estimated by means of an optimized version of the CIEDE2000 formula, while uniformity and edginess are estimated by means of saliency maps obtained from the tensor voting process. Measurements of removed noise, edge preservation and undesirable introduced artifacts, additionally to visual inspection, show that the proposed method has a better performance than the state-of-the-art image denoising algorithms for images contaminated with CCD camera noise.     

Illumination-robust variational optical flow using cross-correlation

We address the problem of variational optical flow for video processing applications that need fast operation and robustness to drastic variations in illumination. Recently, a solution [1] has been proposed based on the photometric invariants of the dichromatic reflection model [2]. However, this solution is only applicable to colour videos with brightness variations. Greyscale videos, or colour videos with colour illumination changes cannot be adequately handled. We propose two illumination-robust variational methods based on cross-correlation that are applicable to colour and grey-level sequences and robust to brightness and colour illumination changes. First, we present a general implicit nonlinear scheme that assumes no particular analytical form of energy functional and can accommodate different image components and data metrics, including cross-correlation. We test the nonlinear scheme on standard synthetic data with artificial brightness and colour effects added and conclude that cross-correlation is robust to both kinds of illumination changes. Then we derive a fast linearised numerical scheme for cross-correlation based variational optical flow. We test the linearised algorithm on challenging data and compare it to a number of state-of-the-art variational flow methods.     

On improving the efficiency of tensor voting

This paper proposes two alternative formulations to reduce the high computational complexity of tensor voting, a robust perceptual grouping technique used to extract salient information from noisy data. The first scheme consists of numerical approximations of the votes, which have been derived from an in-depth analysis of the plate and ball voting processes. The second scheme simplifies the formulation while keeping the same perceptual meaning of the original tensor voting: The stick tensor voting and the stick component of the plate tensor voting must reinforce surfaceness, the plate components of both the plate and ball tensor voting must boost curveness, whereas junctionness must be strengthened by the ball component of the ball tensor voting. Two new parameters have been proposed for the second formulation in order to control the potentially conflictive influence of the stick component of the plate vote and the ball component of the ball vote. Results show that the proposed formulations can be used in applications where efficiency is an issue since they have a complexity of order O(1). Moreover, the second proposed formulation has been shown to be more appropriate than the original tensor voting for estimating saliencies by appropriately setting the two new parameters.     

Discriminative optical flow tensor for video semantic analysis

This paper presents a novel framework for effective video semantic analysis. This framework has two major components, namely, optical flow tensor (OFT) and hidden Markov models (HMMs). OFT and HMMs are employed because: (1) motion is one of the fundamental characteristics reflecting the semantic information in video, so an OFT-based feature extraction method is developed to make full use of the motion information. Thereafter, to preserve the structure and discriminative information presented by OFT, general tensor discriminant analysis (GTDA) is used for dimensionality reduction. Finally, linear discriminant analysis (LDA) is utilized to further reduce the feature dimension for discriminative motion information representation; and (2) video is a sort of information intensive sequential media characterized by its context-sensitive nature, so the video sequences can be more effectively analyzed by some temporal modeling tools. In this framework, we use HMMs to well model different levels of semantic units (SU), e.g., shot and event. Experimental results are reported to demonstrate the advantages of the proposed framework upon semantic analysis of basketball video sequences, and the cross validations illustrate its feasibility and effectiveness.     

Stereo using monocular cues within the tensor voting framework

We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficulties within a perceptual organization framework, considering both binocular and monocular cues. Initially, matching candidates for all pixels are generated by a combination of matching techniques. The matching candidates are then embedded in disparity space, where perceptual organization takes place in 3D neighborhoods and, thus, does not suffer from problems associated with scanline or image neighborhoods. The assumption is that correct matches produce salient, coherent surfaces, while wrong ones do not. Matching candidates that are consistent with the surfaces are kept and grouped into smooth layers. Thus, we achieve surface segmentation based on geometric and not photometric properties. Surface overextensions, which are due to occlusion, can be corrected by removing matches whose projections are not consistent in color with their neighbors of the same surface in both images. Finally, the projections of the refined surfaces on both images are used to obtain disparity hypotheses for unmatched pixels. The final disparities are selected after a second tensor voting stage, during which information is propagated from more reliable pixels to less reliable ones. We present results on widely used benchmark stereo pairs.     

基于张量投票的摄像机自标定方法研究

针对传统的基于Kruppa方程摄像机自标定算法的欠鲁棒性,首次提出将鲁棒的张量投票算法用于摄像机自标定方法中。利用基于尺度不变的SIFT算法查找并匹配出每对图像的特征点,其中待匹配图像由摄像机对同一场景从三个不同角度位置拍摄,对图像张量投票后按棒张量特征值降序排序,由此筛选得到具有鲁棒性边缘特征的前八对特征点,利用八点算法求解相应的基础矩阵和极点,根据Kruppa方程和三维重建（SFM）算法求得摄像机参数矩阵。实验结果证明,该方法具有较高标定精度,并通过加入高斯噪声的仿真实验证明该算法是一种鲁棒的摄像机自标定方法。     

A combined post-filtering method to improve accuracy of variational optical flow estimation

We present a novel combined post-filtering (CPF) method to improve the accuracy of optical flow estimation. Its attractive advantages are that outliers reduction is attained while discontinuities are well preserved, and occlusions are partially handled. Major contributions are the following: First, the structure tensor (ST) based edge detection is introduced to extract flow edges. Moreover, we improve the detection performance by extending the traditional 2D spatial edge detector into spatial-scale 3D space, and also using a gradient bilateral filter (GBF) to replace the linear Gaussian filter to construct a multi-scale nonlinear ST. GBF is useful to preserve discontinuity but it is computationally expensive. A hybrid GBF and Gaussian filter (HGBGF) approach is proposed by means of a spatial-scale gradient signal-to-noise ratio (SNR) measure to solve the low efficiency issue. Additionally, a piecewise occlusion detection method is used to extract occlusions. Second, we apply a CPF method, which uses a weighted median filter (WMF), a bilateral filter (BF) and a fast median filter (MF), to post-smooth the detected edges and occlusions, and the other flat regions of the flow field, respectively. Benchmark tests on both synthetic and real sequences demonstrate the effectiveness of our method.     

Robust estimation of adaptive tensors of curvature by tensor voting

Although curvature estimation from a given mesh or regularly sampled point set is a well-studied problem, it is still challenging when the input consists of a cloud of unstructured points corrupted by misalignment error and outlier noise. Such input is ubiquitous in computer vision. In this paper, we propose a three-pass tensor voting algorithm to robustly estimate curvature tensors, from which accurate principal curvatures and directions can be calculated. Our quantitative estimation is an improvement over the previous two-pass algorithm, where only qualitative curvature estimation (sign of Gaussian curvature) is performed. To overcome misalignment errors, our improved method automatically corrects input point locations at subvoxel precision, which also rejects outliers that are uncorrectable. To adapt to different scales locally, we define the RadiusHit of a curvature tensor to quantify estimation accuracy and applicability. Our curvature estimation algorithm has been proven with detailed quantitative experiments, performing better in a variety of standard error metrics (percentage error in curvature magnitudes, absolute angle difference in curvature direction) in the presence of a large amount of misalignment noise.     

Determination of Horizontal Motion through Optical Flow Computations

For intelligent/autonomous subsea vehicles,reliable short-range horizontal positioning is difficult to achieve,particularly over flat bottom topography.A potential solution proposed in this paper utilized a passive optical sensing method to estimate the vehicle displacement using the bottom surface texture.The suggested optical flow method does not require any feature correspondences in images and it is robust in allowing brightness changes between image frames.Fundamentally,this method is similar to correlation methods attempting to match images and compute the motion disparity.However,in correlation methods,searching a neighbor region blindly for best match is lengthy.Main contributions of this paper come from the analysis showing that optical flow computation based on the general model cannot avoid errors except for null motion although the sign of optical flow keeps correct,and from the development of an iterative shifting method based on the error characteristics to accurately determine motions.Advantages of the proposed method are verified by real image experiments.     

Feature detection of triangular meshes based on tensor voting theory

This paper presents n-dimensional feature recognition of triangular meshes that can handle both geometric properties and additional attributes such as color information of a physical object. Our method is based on a tensor voting technique for classifying features and integrates a clustering and region growing methodology for segmenting a mesh into sub-patches. We classify a feature into a corner, a sharp edge and a face. Then, finally we detect features via region merging and cleaning processes. Our feature detection shows good performance with efficiency for various dimensional models.     

Inference of segmented color and texture description by tensor voting

A robust synthesis method is proposed to automatically infer missing color and texture information from a damaged 2D image by (N)D tensor voting (N > 3). The same approach is generalized to range and 3D data in the presence of occlusion, missing data and noise. Our method translates texture information into an adaptive (N)D tensor, followed by a voting process that infers noniteratively the optimal color values in the (N)D texture space. A two-step method is proposed. First, we perform segmentation based on insufficient geometry, color, and texture information in the input, and extrapolate partitioning boundaries by either 2D or 3D tensor voting to generate a complete segmentation for the input. Missing colors are synthesized using (N)D tensor voting in each segment. Different feature scales in the input are automatically adapted by our tensor scale analysis. Results on a variety of difficult inputs demonstrate the effectiveness of our tensor voting approach.     

Improving the robustness of GNP-PCA using the multiagent system

In order to improve the robustness of Genetic Network Programming fuzzy data mining and PCA (GNP-PCA) based face recognition in the Gaussian and Salt&Pepper noisy testing environments, a GNP-based multi-agent system is constructed using GNP-PCA and multi-resolution analysis in this paper. In the proposed approach, the different scales of training images in the Laplacian pyramid are regarded as sub-environments and each GNP-PCA is performed as an agent in its corresponding environment. Face recognition is finally realized by maximizing the weighted average matching degrees of all the persons in the training database. Experimental results indicate that the proposed method has improved the robustness of GNP-PCA in the Gaussian and Salt&Pepper noisy testing environments considerably.     

Improving SoC design quality through a reproducible design flow

The author examines the dynamics of system-on-a-chip design and addresses the fundamental question of whether there is a reproducible process for achieving the right design at the right time     

Improving the robustness of gaze tracking under unconstrained illumination conditions

Multimedia Tools and Applications - In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze...     

The robustness of majority voting compared to filtering misclassified instances in supervised classification tasks

Removing or filtering outliers and mislabeled instances prior to training a learning algorithm has been shown to increase classification accuracy, especially in noisy data sets. A popular approach is to remove any instance that is misclassified by a learning algorithm. However, the use of ensemble methods has also been shown to generally increase classification accuracy. In this paper, we extensively examine filtering and ensembling. We examine 9 learning algorithms individually and ensembled together as filtering algorithms as well as the effects of filtering in the 9 chosen learning algorithms on a set of 54 data sets. We compare the filtering results with using a majority voting ensemble. We find that the majority voting ensemble significantly outperforms filtering unless there are high amounts of noise present in the data set. Additionally, for most cases, using an ensemble of learning algorithms for filtering produces a greater increase in classification accuracy than using a single learning algorithm for filtering.     

Improving the robustness of parametric shape tracking with switched multiple models

This paper addresses the problem of tracking objects with complex motion dynamics or shape changes. It is assumed that some of the visual features detected in the image (e.g., edge strokes) are outliers i.e., they do not belong to the object boundary. A robust tracking algorithm is proposed which allows to efficiently track an object with complex shape or motion changes in clutter environments. The algorithm relies on the use of multiple models, i.e., a bank of stochastic motion models switched according to a probabilistic mechanism. Robust filtering methods are used to estimate the label of the active model as well as the state trajectory.     

Improving the robustness and accuracy of the marching cubes algorithm for isosurfacing

This paper proposes a modification of the Marching Cubes algorithm for isosurfacing, with the intent of improving the representation of the surface in the interior of each grid cell. Our objective is to create a representation which correctly models the topology of the trilinear interpolant within the cell and which is robust under perturbations of the data and threshold value. To achieve this, we identify a small number of key points in the cell interior that are critical to the surface definition. This allows us to efficiently represent the different topologies that can occur, including the possibility of "tunnels." The representation is robust in the sense that the surface is visually continuous as the data and threshold change in value. Each interior point lies on the isosurface. Finally, a major feature of our new approach is the systematic method of triangulating the polygon in the cell interior.     

Improving robustness of P2P applications in mobile environments

Mobile P2P networks possess particular characteristics which make accessibility of services deployed on peers a challenge. This has to be taken into account when considering robustness of applications that depend on successfully accessing a set of services. While ensuring robustness is traditionally handled through replication or redundancy, those solutions are not readily applicable to decentralized and dynamic networks. Instead, current solutions are based on efficient P2P structure maintenance or unstructured network search algorithms. A novel and alternative method proposed in this paper is based on the observation that some redundancy may exist between services offered on the network, a fact which could be used to recreate an unavailable service from services accessible to a peer. Instead of adding redundancy to the system, our solution exploits the already existing redundancy to improve robustness of mobile P2P applications. We model the interaction with services as finite-state transducers and propose a heuristic to obtain redundancy between any pair of services. Then, a set of algorithms that uses this inter-service redundancy to recreate the interaction with one service from the other is discussed. The computational cost is polynomial with respect to services’ size, and in practice, the non-redundant functionality and related control need to be implemented locally.

Improving robustness of rolling stock circulations in rapid transit networks

The rolling stock circulation depends on two different problems: the rolling stock assignment and the train routing problems, which up to now have been solved sequentially. We propose a new approach to obtain better and more robust circulations of the rolling stock train units, solving the rolling stock assignment while accounting for the train routing problem. Here robustness means that difficult shunting operations are selectively penalized and propagated delays together with the need for human resources are minimized. This new integrated approach provides a huge model. Then, we solve the integrated model using Benders decomposition, where the main decision is the rolling stock assignment and the train routing is in the second level. For computational reasons we propose a heuristic based on Benders decomposition. Computational experiments show how the current solution operated by RENFE (the main Spanish train operator) can be improved: more robust and efficient solutions are obtained.