Showing papers on "Robustness (computer science) published in 2014"

SVO: Fast semi-direct monocular visual odometry

Abstract: We propose a semi-direct monocular visual odometry algorithm that is precise, robust, and faster than current state-of-the-art methods. The semi-direct approach eliminates the need of costly feature extraction and robust matching techniques for motion estimation. Our algorithm operates directly on pixel intensities, which results in subpixel precision at high frame-rates. A probabilistic mapping method that explicitly models outlier measurements is used to estimate 3D points, which results in fewer outliers and more reliable points. Precise and high frame-rate motion estimation brings increased robustness in scenes of little, repetitive, and high-frequency texture. The algorithm is applied to micro-aerial-vehicle state-estimation in GPS-denied environments and runs at 55 frames per second on the onboard embedded computer and at more than 300 frames per second on a consumer laptop. We call our approach SVO (Semi-direct Visual Odometry) and release our implementation as open-source software.

Saliency Optimization from Robust Background Detection

Abstract: Recent progresses in salient object detection have exploited the boundary prior, or background information, to assist other saliency cues such as contrast, achieving state-of-the-art results. However, their usage of boundary prior is very simple, fragile, and the integration with other cues is mostly heuristic. In this work, we present new methods to address these issues. First, we propose a robust background measure, called boundary connectivity. It characterizes the spatial layout of image regions with respect to image boundaries and is much more robust. It has an intuitive geometrical interpretation and presents unique benefits that are absent in previous saliency measures. Second, we propose a principled optimization framework to integrate multiple low level cues, including our background measure, to obtain clean and uniform saliency maps. Our formulation is intuitive, efficient and achieves state-of-the-art results on several benchmark datasets.

MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization

Abstract: We propose a multi-expert restoration scheme to address the model drift problem in online tracking. In the proposed scheme, a tracker and its historical snapshots constitute an expert ensemble, where the best expert is selected to restore the current tracker when needed based on a minimum entropy criterion, so as to correct undesirable model updates. The base tracker in our formulation exploits an online SVM on a budget algorithm and an explicit feature mapping method for efficient model update and inference. In experiments, our tracking method achieves substantially better overall performance than 32 trackers on a benchmark dataset of 50 video sequences under various evaluation settings. In addition, in experiments with a newly collected dataset of challenging sequences, we show that the proposed multi-expert restoration scheme significantly improves the robustness of our base tracker, especially in scenarios with frequent occlusions and repetitive appearance variations.

5GNOW: non-orthogonal, asynchronous waveforms for future mobile applications

Abstract: This article provides some fundamental indications about wireless communications beyond LTE/LTE-A (5G), representing the key findings of the European research project 5GNOW. We start with identifying the drivers for making the transition to 5G networks. Just to name one, the advent of the Internet of Things and its integration with conventional human-initiated transmissions creates a need for a fundamental system redesign. Then we make clear that the strict paradigm of synchronism and orthogonality as applied in LTE prevents efficiency and scalability. We challenge this paradigm and propose new key PHY layer technology components such as a unified frame structure, multicarrier waveform design including a filtering functionality, sparse signal processing mechanisms, a robustness framework, and transmissions with very short latency. These components enable indeed an efficient and scalable air interface supporting the highly varying set of requirements originating from the 5G drivers.

Fast Visual Tracking via Dense Spatio-temporal Context Learning

Abstract: In this paper, we present a simple yet fast and robust algorithm which exploits the dense spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its locally dense contexts in a Bayesian framework, which models the statistical correlation between the simple low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is then posed by computing a confidence map which takes into account the prior information of the target location and thereby alleviates target location ambiguity effectively. We further propose a novel explicit scale adaptation scheme, which is able to deal with target scale variations efficiently and effectively. The Fast Fourier Transform (FFT) is adopted for fast learning and detection in this work, which only needs 4 FFT operations. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.

Towards Deep Neural Network Architectures Robust to Adversarial Examples

Abstract: Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are often imperceptible, but can result in 100% mis-classification for a state of the art DNN. We study the structure of adversarial examples and explore network topology, pre-processing and training strategies to improve the robustness of DNNs. We perform various experiments to assess the removability of adversarial examples by corrupting with additional noise and pre-processing with denoising autoencoders (DAEs). We find that DAEs can remove substantial amounts of the adversarial noise. How- ever, when stacking the DAE with the original DNN, the resulting network can again be attacked by new adversarial examples with even smaller distortion. As a solution, we propose Deep Contractive Network, a model with a new end-to-end training procedure that includes a smoothness penalty inspired by the contractive autoencoder (CAE). This increases the network robustness to adversarial examples, without a significant performance penalty.

Learning Mid-level Filters for Person Re-identification

Abstract: In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification. It is well motivated by our study on what are good filters for person re-identification. Our mid-level filters are discriminatively learned for identifying specific visual patterns and distinguishing persons, and have good cross-view invariance. First, local patches are qualitatively measured and classified with their discriminative power. Discriminative and representative patches are collected for filter learning. Second, patch clusters with coherent appearance are obtained by pruning hierarchical clustering trees, and a simple but effective cross-view training strategy is proposed to learn filters that are view-invariant and discriminative. Third, filter responses are integrated with patch matching scores in RankSVM training. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. The learned mid-level features are complementary to existing handcrafted low-level features, and improve the best Rank-1 matching rate on the VIPeR dataset by 14%.

Outage Constrained Robust Transmit Optimization for Multiuser MISO Downlinks: Tractable Approximations by Conic Optimization

Abstract: In this paper, we study a probabilistically robust transmit optimization problem under imperfect channel state information (CSI) at the transmitter and under the multiuser multiple-input single-output (MISO) downlink scenario. The main issue is to keep the probability of each user's achievable rate outage as caused by CSI uncertainties below a given threshold. As is well known, such rate outage constraints present a significant analytical and computational challenge. Indeed, they do not admit simple closed-form expressions and are unlikely to be efficiently computable in general. Assuming Gaussian CSI uncertainties, we first review a traditional robust optimization-based method for approximating the rate outage constraints, and then develop two novel approximation methods using probabilistic techniques. Interestingly, these three methods can be viewed as implementing different tractable analytic upper bounds on the tail probability of a complex Gaussian quadratic form, and they provide convex restrictions, or safe tractable approximations, of the original rate outage constraints. In particular, a feasible solution from any one of these methods will automatically satisfy the rate outage constraints, and all three methods involve convex conic programs that can be solved efficiently using off-the-shelf solvers. We then proceed to study the performance-complexity tradeoffs of these methods through computational complexity and comparative approximation performance analyses. Finally, simulation results are provided to benchmark the three convex restriction methods against the state of the art in the literature. The results show that all three methods offer significantly improved solution quality and much lower complexity.

Realtime and Robust Hand Tracking from Depth

Abstract: We present a realtime hand tracking system using a depth sensor. It tracks a fully articulated hand under large viewpoints in realtime (25 FPS on a desktop without using a GPU) and with high accuracy (error below 10 mm). To our knowledge, it is the first system that achieves such robustness, accuracy, and speed simultaneously, as verified on challenging real data. Our system is made of several novel techniques. We model a hand simply using a number of spheres and define a fast cost function. Those are critical for realtime performance. We propose a hybrid method that combines gradient based and stochastic optimization methods to achieve fast convergence and good accuracy. We present new finger detection and hand initialization methods that greatly enhance the robustness of tracking.

Real-time non-rigid reconstruction using an RGB-D camera

Abstract: We present a combined hardware and software solution for markerless reconstruction of non-rigidly deforming physical objects with arbitrary shape in real-time. Our system uses a single self-contained stereo camera unit built from off-the-shelf components and consumer graphics hardware to generate spatio-temporally coherent 3D models at 30 Hz. A new stereo matching algorithm estimates real-time RGB-D data. We start by scanning a smooth template model of the subject as they move rigidly. This geometric surface prior avoids strong scene assumptions, such as a kinematic human skeleton or a parametric shape model. Next, a novel GPU pipeline performs non-rigid registration of live RGB-D data to the smooth template using an extended non-linear as-rigid-as-possible (ARAP) framework. High-frequency details are fused onto the final mesh using a linear deformation model. The system is an order of magnitude faster than state-of-the-art methods, while matching the quality and robustness of many offline algorithms. We show precise real-time reconstructions of diverse scenes, including: large deformations of users' heads, hands, and upper bodies; fine-scale wrinkles and folds of skin and clothing; and non-rigid interactions performed by users on flexible objects such as toys. We demonstrate how acquired models can be used for many interactive scenarios, including re-texturing, online performance capture and preview, and real-time shape and motion re-targeting.

Location-Aware Communications for 5G Networks: How location information can improve scalability, latency, and robustness of 5G

Abstract: Fifth-generation (5G) networks will be the first generation to benefit from location information that is sufficiently precise to be leveraged in wireless network design and optimization. We argue that location information can aid in addressing several of the key challenges in 5G, complementary to existing and planned technological developments. These challenges include an increase in traffic and number of devices, robustness for mission-critical services, and a reduction in total energy consumption and latency. This article gives a broad overview of the growing research area of location-aware communications across different layers of the protocol stack. We highlight several promising trends, tradeoffs, and pitfalls.

A New Bio-inspired Algorithm: Chicken Swarm Optimization

Abstract: A new bio-inspired algorithm, Chicken Swarm Optimization (CSO), is proposed for optimization applications. Mimicking the hierarchal order in the chicken swarm and the behaviors of the chicken swarm, including roosters, hens and chicks, CSO can efficiently extract the chickens’ swarm intelligence to optimize problems. Experiments on twelve benchmark problems and a speed reducer design were conducted to compare the performance of CSO with that of other algorithms. The results show that CSO can achieve good optimization results in terms of both optimization accuracy and robustness. Future researches about CSO are finally suggested.

Displaced dynamic expression regression for real-time facial tracking and animation

Abstract: We present a fully automatic approach to real-time facial tracking and animation with a single video camera. Our approach does not need any calibration for each individual user. It learns a generic regressor from public image datasets, which can be applied to any user and arbitrary video cameras to infer accurate 2D facial landmarks as well as the 3D facial shape from 2D video frames. The inferred 2D landmarks are then used to adapt the camera matrix and the user identity to better match the facial expressions of the current user. The regression and adaptation are performed in an alternating manner. With more and more facial expressions observed in the video, the whole process converges quickly with accurate facial tracking and animation. In experiments, our approach demonstrates a level of robustness and accuracy on par with state-of-the-art techniques that require a time-consuming calibration step for each individual user, while running at 28 fps on average. We consider our approach to be an attractive solution for wide deployment in consumer-level applications.

Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees

Abstract: Maximally Stable Extremal Regions (MSERs) have achieved great success in scene text detection. However, this low-level pixel operation inherently limits its capability for handling complex text information efficiently (e. g. connections between text or background components), leading to the difficulty in distinguishing texts from background components. In this paper, we propose a novel framework to tackle this problem by leveraging the high capability of convolutional neural network (CNN). In contrast to recent methods using a set of low-level heuristic features, the CNN network is capable of learning high-level features to robustly identify text components from text-like outliers (e.g. bikes, windows, or leaves). Our approach takes advantages of both MSERs and sliding-window based methods. The MSERs operator dramatically reduces the number of windows scanned and enhances detection of the low-quality texts. While the sliding-window with CNN is applied to correctly separate the connections of multiple characters in components. The proposed system achieved strong robustness against a number of extreme text variations and serious real-world problems. It was evaluated on the ICDAR 2011 benchmark dataset, and achieved over 78% in F-measure, which is significantly higher than previous methods.

Training Deep Neural Networks on Noisy Labels with Bootstrapping

Abstract: Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled examples, and in current practice the labels are assumed to be unambiguous and accurate. However, this assumption often does not hold; e.g. in recognition, class labels may be missing; in detection, objects in the image may not be localized; and in general, the labeling may be subjective. In this work we propose a generic way to handle noisy and incomplete labeling by augmenting the prediction objective with a notion of consistency. We consider a prediction consistent if the same prediction is made given similar percepts, where the notion of similarity is between deep network features computed from the input data. In experiments we demonstrate that our approach yields substantial robustness to label noise on several datasets. On MNIST handwritten digits, we show that our model is robust to label corruption. On the Toronto Face Database, we show that our model handles well the case of subjective labels in emotion recognition, achieving state-of-the- art results, and can also benefit from unlabeled face images with no modification to our method. On the ILSVRC2014 detection challenge data, we show that our approach extends to very deep networks, high resolution images and structured outputs, and results in improved scalable detection.

Adaptive Robust Control of DC Motors With Extended State Observer

Abstract: Structured and unstructured uncertainties always exist in physical servo systems and degrade their tracking accuracy. In this paper, a practical method named adaptive robust control with extended state observer (ESO) is synthesized for high-accuracy motion control of a dc motor. The proposed controller accounts for not only the structured uncertainties (i.e., parametric uncertainties) but also the unstructured uncertainties (i.e., nonlinear friction, external disturbances, and/or unmodeled dynamics). Adaptive control for the structured uncertainty and ESO for the unstructured uncertainty are designed for compensating them respectively and integrated together via a feedforward cancellation technique. The global robustness of the controller is guaranteed by a feedback robust law. Furthermore, the controller theoretically guarantees a prescribed tracking performance in the presence of various uncertainties, which is very important for high-accuracy control of motion systems. Extensive comparative experimental results are obtained to verify the high-performance nature of the proposed control strategy.

Natural evolution strategies

Abstract: This paper presents Natural Evolution Strategies (NES), a recent family of black-box optimization algorithms that use the natural gradient to update a parameterized search distribution in the direction of higher expected fitness. We introduce a collection of techniques that address issues of convergence, robustness, sample complexity, computational complexity and sensitivity to hyperparameters. This paper explores a number of implementations of the NES family, such as general-purpose multi-variate normal distributions and separable distributions tailored towards search in high dimensional spaces. Experimental results show best published performance on various standard benchmarks, as well as competitive performance on others.

Learning with Pseudo-Ensembles

Abstract: We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout [9] in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in the parent network. We examine the relationship of pseudo-ensembles, which involve perturbation in model-space, to standard ensemble methods and existing notions of robustness, which focus on perturbation in observation-space. We present a novel regularizer based on making the behavior of a pseudo-ensemble robust with respect to the noise process generating it. In the fully-supervised setting, our regularizer matches the performance of dropout. But, unlike dropout, our regularizer naturally extends to the semi-supervised setting, where it produces state-of-the-art results. We provide a case study in which we transform the Recursive Neural Tensor Network of [19] into a pseudo-ensemble, which significantly improves its performance on a real-world sentiment analysis benchmark.

A Robust Infrared Small Target Detection Algorithm Based on Human Visual System

Abstract: Robust human visual system (HVS) properties can effectively improve the infrared (IR) small target detection capabilities, such as detection rate, false alarm rate, speed, etc. However, current algorithms based on HVS usually improve one or two of the aforementioned detection capabilities while sacrificing the others. In this letter, a robust IR small target detection algorithm based on HVS is proposed to pursue good performance in detection rate, false alarm rate, and speed simultaneously. First, an HVS size-adaptation process is used, and the IR image after preprocessing is divided into subblocks to improve detection speed. Then, based on HVS contrast mechanism, the improved local contrast measure, which can improve detection rate and reduce false alarm rate, is proposed to calculate the saliency map, and a threshold operation along with a rapid traversal mechanism based on HVS attention shift mechanism is used to get the target subblocks quickly. Experimental results show the proposed algorithm has good robustness and efficiency for real IR small target detection applications.

Projective dynamics: fusing constraint projections for fast simulation

Abstract: We present a new method for implicit time integration of physical systems. Our approach builds a bridge between nodal Finite Element methods and Position Based Dynamics, leading to a simple, efficient, robust, yet accurate solver that supports many different types of constraints. We propose specially designed energy potentials that can be solved efficiently using an alternating optimization approach. Inspired by continuum mechanics, we derive a set of continuum-based potentials that can be efficiently incorporated within our solver. We demonstrate the generality and robustness of our approach in many different applications ranging from the simulation of solids, cloths, and shells, to example-based simulation. Comparisons to Newton-based and Position Based Dynamics solvers highlight the benefits of our formulation.

Strokelets: A Learned Multi-scale Representation for Scene Text Recognition

Abstract: Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision. Though extensively studied, localizing and reading text in uncontrolled environments remain extremely challenging, due to various interference factors. In this paper, we propose a novel multi-scale representation for scene text recognition. This representation consists of a set of detectable primitives, termed as strokelets, which capture the essential substructures of characters at different granularities. Strokelets possess four distinctive advantages: (1) Usability: automatically learned from bounding box labels, (2) Robustness: insensitive to interference factors, (3) Generality: applicable to variant languages, and (4) Expressivity: effective at describing characters. Extensive experiments on standard benchmarks verify the advantages of strokelets and demonstrate the effectiveness of the proposed algorithm for text recognition.

Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern

Abstract: Designing effective features is a fundamental problem in computer vision However, it is usually difficult to achieve a great tradeoff between discriminative power and robustness Previous works shown that spatial co-occurrence can boost the discriminative power of features However the current existing co-occurrence features are taking few considerations to the robustness and hence suffering from sensitivity to geometric and photometric variations In this work, we study the Transform Invariance (TI) of co-occurrence features Concretely we formally introduce a Pairwise Transform Invariance (PTI) principle, and then propose a novel Pairwise Rotation Invariant Co-occurrence Local Binary Pattern (PRICoLBP) feature, and further extend it to incorporate multi-scale, multi-orientation, and multi-channel information Different from other LBP variants, PRICoLBP can not only capture the spatial context co-occurrence information effectively, but also possess rotation invariance We evaluate PRICoLBP comprehensively on nine benchmark data sets from five different perspectives, eg, encoding strategy, rotation invariance, the number of templates, speed, and discriminative power compared to other LBP variants Furthermore we apply PRICoLBP to six different but related applications-texture, material, flower, leaf, food, and scene classification, and demonstrate that PRICoLBP is efficient, effective, and of a well-balanced tradeoff between the discriminative power and robustness

Dynamic supply chain network design for the supply of blood in disasters: A robust model with real world application

Abstract: This paper presents a robust network design model for the supply of blood during and after disasters. A practical optimization model is developed that can assist in blood facility location and allocation decisions for multiple post-disaster periods. The application of the proposed model is investigated in a case problem where real data is utilized to design a network for emergency supply of blood during potential disasters. Our analysis on the tradeoff between solution robustness and model robustness arrives at important practical insights. The performance of the proposed ‘robust optimization’ approach is also compared with that of an ‘expected value’ approach.

Direction of Arrival Estimation Using Co-Prime Arrays: A Super Resolution Viewpoint

Abstract: We consider the problem of direction of arrival (DOA) estimation using a recently proposed structure of nonuniform linear arrays, referred to as co-prime arrays. By exploiting the second order statistical information of the received signals, co-prime arrays exhibit O(MN) degrees of freedom with only M+N sensors. A sparsity-based recovery algorithm is proposed to fully utilize these degrees of freedom. The suggested method is based on the developing theory of super resolution, which considers a continuous range of possible sources instead of discretizing this range onto a grid. With this approach, off-grid effects inherent in traditional sparse recovery can be neglected, thus improving the accuracy of DOA estimation. We show that in the noiseless case it is theoretically possible to detect up to [MN/ 2] sources with only 2M+N sensors. The noise statistics of co-prime arrays are also analyzed to demonstrate the robustness of the proposed optimization scheme. A source number detection method is presented based on the spectrum reconstructed from the sparse method. By extensive numerical examples, we show the superiority of the suggested algorithm in terms of DOA estimation accuracy, degrees of freedom, and resolution ability over previous techniques, such as MUSIC with spatial smoothing and discrete sparse recovery.

Global image registration using a symmetric block-matching approach

Abstract: Most medical image registration algorithms suffer from a directionality bias that has been shown to largely impact subsequent analyses. Several approaches have been proposed in the literature to address this bias in the context of nonlinear registration, but little work has been done for global registration. We propose a symmetric approach based on a block-matching technique and least-trimmed square regression. The proposed method is suitable for multimodal registration and is robust to outliers in the input images. The symmetric framework is compared with the original asymmetric block-matching technique and is shown to outperform it in terms of accuracy and robustness. The methodology presented in this article has been made available to the community as part of the NiftyReg open-source package.

Model Predictive Control of Swarms of Spacecraft Using Sequential Convex Programming

Abstract: DOI: 10.2514/1.G000218 This paper presents a decentralized, model predictive control algorithm for the optimal guidance and reconfiguration of swarms of spacecraft composed of hundreds to thousands of agents with limited capabilities. In previous work, J2-invariantorbitshavebeenfoundtoprovidecollision-freemotionforhundredsoforbitsinalowEarthorbit. This paper develops real-time optimal control algorithms for the swarm reconfiguration that involve transferring from one J2-invariant orbit to another while avoidingcollisions and minimizing fuel. The proposedmodel predictive control-sequential convex programming algorithm uses sequential convex programming to solve a series of approximate path planning problems until the solution converges. By updating the optimal trajectories during the reconfiguration, the model predictive control algorithm results in decentralized computations and communication between neighboring spacecraft only. Additionally, model predictive control reduces the horizon of the convex optimizations, which reduces the run time of the algorithm. Multiple time steps, time-varying collision constraints, and communication requirements are developed to guarantee stability, feasibility, and robustness of the model predictive control-sequential convex programming algorithm.

An Analysis of the Viola-Jones Face Detection Algorithm

Abstract: In this article, we decipher the Viola-Jones algorithm, the first ever real-time face detection system. There are three ingredients working in concert to enable a fast and accurate detection: the integral image for feature computation, Adaboost for feature selection and an attentional cascade for efficient computational resource allocation. Here we propose a complete algorithmic description, a learning code and a learned face detector that can be applied to any color image. Since the Viola-Jones algorithm typically gives multiple detections, a post-processing step is also proposed to reduce detection redundancy using a robustness argument. Source Code The source code and the online demo are accessible at the IPOL web page of this article 1 .