Showing papers in "IEEE Signal Processing Magazine in 2017"
TL;DR: In many applications, such geometric data are large and complex (in the case of social networks, on the scale of billions) and are natural targets for machine-learning techniques as mentioned in this paper.
Abstract: Many scientific fields study data with an underlying structure that is non-Euclidean. Some examples include social networks in computational social sciences, sensor networks in communications, functional networks in brain imaging, regulatory networks in genetics, and meshed surfaces in computer graphics. In many applications, such geometric data are large and complex (in the case of social networks, on the scale of billions) and are natural targets for machine-learning techniques. In particular, we would like to use deep neural networks, which have recently proven to be powerful tools for a broad range of problems from computer vision, natural-language processing, and audio analysis. However, these tools have been most successful on data with an underlying Euclidean or grid-like structure and in cases where the invariances of these structures are built into networks used to model them.
2,565 citations
TL;DR: Deep reinforcement learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higher-level understanding of the visual world as discussed by the authors.
Abstract: Deep reinforcement learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higherlevel understanding of the visual world. Currently, deep learning is enabling reinforcement learning (RL) to scale to problems that were previously intractable, such as learning to play video games directly from pixels. DRL algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of RL, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep RL, including the deep Q-network (DQN), trust region policy optimization (TRPO), and asynchronous advantage actor critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via RL. To conclude, we describe several current areas of research within the field.
1,743 citations
TL;DR: Various aspects of automotive radar signal processing techniques are summarized, including waveform design, possible radar architectures, estimation algorithms, implementation complexity-resolution trade off, and adaptive processing for complex environments, as well as unique problems associated with automotive radars such as pedestrian detection.
Abstract: Automotive radars, along with other sensors such as lidar, (which stands for "light detection and ranging"), ultrasound, and cameras, form the backbone of self-driving cars and advanced driver assistant systems (ADASs). These technological advancements are enabled by extremely complex systems with a long signal processing path from radars/sensors to the controller. Automotive radar systems are responsible for the detection of objects and obstacles, their position, and speed relative to the vehicle. The development of signal processing techniques along with progress in the millimeter-wave (mm-wave) semiconductor technology plays a key role in automotive radar systems. Various signal processing techniques have been developed to provide better resolution and estimation performance in all measurement dimensions: range, azimuth-elevation angles, and velocity of the targets surrounding the vehicles. This article summarizes various aspects of automotive radar signal processing techniques, including waveform design, possible radar architectures, estimation algorithms, implementation complexity-resolution trade off, and adaptive processing for complex environments, as well as unique problems associated with automotive radars such as pedestrian detection. We believe that this review article will combine the several contributions scattered in the literature to serve as a primary starting point to new researchers and to give a bird's-eye view to the existing research community.
705 citations
TL;DR: Recent experimental work in convolutional neural networks to solve inverse problems in imaging, with a focus on the critical design decisions is reviewed, including sparsity-based techniques such as compressed sensing.
Abstract: In this article, we review recent uses of convolutional neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, superresolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions.
544 citations
TL;DR: This work first classify deep multimodal learning architectures and then discusses methods to fuse learned multi-modal representations in deep-learning architectures.
Abstract: The success of deep learning has been a catalyst to solving increasingly complex machine-learning problems, which often involve multiple data modalities. We review recent advances in deep multimodal learning and highlight the state-of the art, as well as gaps and challenges in this active research field. We first classify deep multimodal learning architectures and then discuss methods to fuse learned multimodal representations in deep-learning architectures. We highlight two areas of research–regularization strategies and methods that learn or optimize multimodal fusion structures–as exciting areas for future work.
529 citations
TL;DR: A practical overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, are provided as well as a review, with demonstrations, of several applications.
Abstract: Transport-based techniques for signal and data analysis have recently received increased interest. Given their ability to provide accurate generative models for signal intensities and other data distributions, they have been used in a variety of applications, including content-based retrieval, cancer detection, image superresolution, and statistical machine learning, to name a few, and they have been shown to produce state-of-the-art results. Moreover, the geometric characteristics of transport-related metrics have inspired new kinds of algorithms for interpreting the meaning of data distributions. Here, we provide a practical overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, as well as a review, with demonstrations, of several applications. Software accompanying this article is available from [43].
349 citations
TL;DR: Progress is assayed in this rapidly evolving field of CNNs, focusing, in particular, on new ways to collect large quantities of ground-truth data and on recent CNN-based picture-quality prediction models that deliver excellent results in a large, real-world, picture- quality database.
Abstract: Convolutional neural networks (CNNs) have been shown to deliver standout performance on a wide variety of visual information processing applications. However, this rapidly developing technology has only recently been applied with systematic energy to the problem of picture-quality prediction, primarily because of limitations imposed by a lack of adequate ground-truth human subjective data. This situation has begun to change with the development of promising data-gathering methods that are driving new approaches to deep-learning-based perceptual picture-quality prediction. Here, we assay progress in this rapidly evolving field, focusing, in particular, on new ways to collect large quantities of ground-truth data and on recent CNN-based picture-quality prediction models that deliver excellent results in a large, real-world, picture-quality database.
237 citations
TL;DR: In this article, a review of computer vision techniques used in the assessment of image aesthetic quality is presented, which aims at computationally distinguishing high quality from low quality photos based on photographic rules, typically in the form of binary classification or quality scoring.
Abstract: This article reviews recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality from low-quality photos based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature to try to solve this challenging problem. In this article, we summarize these approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (data set characteristics and evaluation metrics). The main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep-learning techniques, we systematically evaluate recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring.
193 citations
TL;DR: Developing approximate inference techniques to solve fundamental problems in signal processing, such as localization of objects in wireless sensor networks and the Internet of Things, and multiple source reconstruction from electroencephalograms.
Abstract: A fundamental problem in signal processing is the estimation of unknown parameters or functions from noisy observations. Important examples include localization of objects in wireless sensor networks [1] and the Internet of Things [2]; multiple source reconstruction from electroencephalograms [3]; estimation of power spectral density for speech enhancement [4]; or inference in genomic signal processing [5]. Within the Bayesian signal processing framework, these problems are addressed by constructing posterior probability distributions of the unknowns. The posteriors combine optimally all of the information about the unknowns in the observations with the information that is present in their prior probability distributions. Given the posterior, one often wants to make inference about the unknowns, e.g., if we are estimating parameters, finding the values that maximize their posterior or the values that minimize some cost function given the uncertainty of the parameters. Unfortunately, obtaining closed-form solutions to these types of problems is infeasible in most practical applications, and therefore, developing approximate inference techniques is of utmost interest.
187 citations
TL;DR: An overview of personal digital assistants (PDAs) is given; the system architecture, key components, and technology behind them are described; and their future potential to fully redefine human?computer interaction is discussed.
Abstract: We have long envisioned that one day computers will understand natural language and anticipate what we need, when and where we need it, and proactively complete tasks on our behalf. As computers get smaller and more pervasive, how humans interact with them is becoming a crucial issue. Despite numerous attempts over the past 30 years to make language understanding (LU) an effective and robust natural user interface for computer interaction, success has been limited and scoped to applications that were not particularly central to everyday use. However, speech recognition and machine learning have continued to be refined, and structured data served by applications and content providers has emerged. These advances, along with increased computational power, have broadened the application of natural LU to a wide spectrum of everyday tasks that are central to a user's productivity. We believe that as computers become smaller and more ubiquitous [e.g., wearables and Internet of Things (IoT)], and the number of applications increases, both system-initiated and user-initiated task completion across various applications and web services will become indispensable for personal life management and work productivity. In this article, we give an overview of personal digital assistants (PDAs); describe the system architecture, key components, and technology behind them; and discuss their future potential to fully redefine human?computer interaction.
180 citations
TL;DR: The goal of this article is to discuss the robustness of deep networks to a diverse set of perturbation that may affect the samples in practice, including adversarial perturbations, random noise, and geometric transformations.
Abstract: Deep neural networks have recently shown impressive classification performance on a diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is equally important that these classifiers satisfy robustness guarantees: small perturbations applied to the samples should not yield significant loss to the performance of the predictor. The goal of this article is to discuss the robustness of deep networks to a diverse set of perturbations that may affect the samples in practice, including adversarial perturbations, random noise, and geometric transformations. This article further discusses the recent works that build on the robustness analysis to provide geometric insights on the classifier's decision surface, which help in developing a better understanding of deep networks. Finally, we present recent solutions that attempt to increase the robustness of deep networks. We hope this review article will contribute to shed ding light on the open research challenges in the robustness of deep networks and stir interest in the analysis of their fundamental properties.
TL;DR: A flexible framework for computationally efficient high-resolution frequency estimation based on decoupled frequency estimation in the Fourier domain, where high- resolution processing can be applied to either the range, relative velocity, or angular dimension is presented.
Abstract: Radar technology is used for many applications of advanced driver assistance systems (ADASs) and is considered as one of the key technologies for highly automated driving (HAD). An overview of conventional automotive radar processing is presented and critical use cases are pointed out in which conventional processing is bound to fail due to limited frequency resolution. Consequently, a flexible framework for computationally efficient high-resolution frequency estimation is presented. This framework is based on decoupled frequency estimation in the Fourier domain, where high-resolution processing can be applied to either the range, relative velocity, or angular dimension. Real data obtained from series-production automotive radar sensor are presented to show the effectiveness of the presented approach.
TL;DR: An analysis of this four-year-long evaluation study's results is provided and the current state of the art in indoor localization is discussed.
Abstract: We present the results, experiences, and lessons learned from comparing a diverse set of indoor location technologies during the Microsoft Indoor Localization Competition. Over the last four years (2014-2017), more than 100 teams from academia and industry deployed their indoor location solutions in realistic, unfamiliar environments, allowing us to directly compare their accuracies and overhead. In this article, we provide an analysis of this four-year-long evaluation study's results and discuss the current state of the art in indoor localization.
TL;DR: Global navigation satellite systems have been the prevalent positioning, navigation, and timing technology over the past few decades, but they suffer from four main limitations.
Abstract: Global navigation satellite systems (GNSSs) have been the prevalent positioning, navigation, and timing technology over the past few decades. However, GNSS signals suffer from four main limitations.
TL;DR: A variety of metric learning methods have been proposed in the literature and many of them have been successfully employed in visual understanding tasks such as face recognition, image classification, and image-based geolocalization.
Abstract: Metric learning aims to learn a distance function to measure the similarity of samples, which plays an important role in many visual understanding applications. Generally, the optimal similarity functions for different visual understanding tasks are task specific because the distributions for data used in different tasks are usually different. It is generally believed that learning a metric from training data can obtain more encouraging performances than handcrafted metrics [1]-[3], e.g., the Euclidean and cosine distances. A variety of metric learning methods have been proposed in the literature [2]-[5], and many of them have been successfully employed in visual understanding tasks such as face recognition [6], [7], image classification [2], [3], visual search [8], [9], visual tracking [10], [11], person reidentification [12], cross-modal matching [13], image set classification [14], and image-based geolocalization [15]-[17].
TL;DR: The design of conventional sensors is based primarily on the Shannon?Nyquist sampling theorem, which states that a signal of bandwidth W Hz is fully determined by its discrete time samples provided the sampling rate exceeds 2 W samples per second.
Abstract: The design of conventional sensors is based primarily on the Shannon?Nyquist sampling theorem, which states that a signal of bandwidth W Hz is fully determined by its discrete time samples provided the sampling rate exceeds 2 W samples per second. For discrete time signals, the Shannon?Nyquist theorem has a very simple interpretation: the number of data samples must be at least as large as the dimensionality of the signal being sampled and recovered. This important result enables signal processing in the discrete time domain without any loss of information. However, in an increasing number of applications, the Shannon-Nyquist sampling theorem dictates an unnecessary and often prohibitively high sampling rate (see lWhat Is the Nyquist Rate of a Video Signal?r). As a motivating example, the high resolution of the image sensor hardware in modern cameras reflects the large amount of data sensed to capture an image. A 10-megapixel camera, in effect, takes 10 million measurements of the scene. Yet, almost immediately after acquisition, redundancies in the image are exploited to compress the acquired data significantly, often at compression ratios of 100:1 for visualization and even higher for detection and classification tasks. This example suggests immense wastage in the overall design of conventional cameras.
TL;DR: This lecture note describes the development of image prior modeling and learning techniques, including sparse representation models, low-rank models, and deep learning models.
Abstract: The use of digital imaging devices, ranging from professional digital cinema cameras to consumer grade smartphone cameras, has become ubiquitous. The acquired image is a degraded observation of the unknown latent image, while the degradation comes from various factors such as noise corruption, camera shake, object motion, resolution limit, hazing, rain streaks, or a combination of them. Image restoration (IR), as a fundamental problem in image processing and low-level vision, aims to reconstruct the latent high-quality image from its degraded observation. Image degradation is, in general, irreversible, and IR is a typical ill-posed inverse problem. Due to the large space of natural image contents, prior information on image structures is crucial to regularize the solution space and produce a good estimation of the latent image. Image prior modeling and learning then are key issues in IR research. This lecture note describes the development of image prior modeling and learning techniques, including sparse representation models, low-rank models, and deep learning models.
TL;DR: This work presents a localization approach based on a prior that vehicles spend the most time on the road, with the odometer as the primary input, and presents an approach solely based on inertial sensors, which also can be used as a speedometer.
Abstract: Most navigation systems today rely on global navigation satellite systems (gnss), including in cars. With support from odometry and inertial sensors, this is a sufficiently accurate and robust solution, but there are future demands. Autonomous cars require higher accuracy and integrity. Using the car as a sensor probe for road conditions in cloud-based services also sets other kind of requirements. The concept of the Internet of Things requires stand-alone solutions without access to vehicle data. Our vision is a future with both invehicle localization algorithms and after-market products, where the position is computed with high accuracy in gnss-denied environments. We present a localization approach based on a prior that vehicles spend the most time on the road, with the odometer as the primary input. When wheel speeds are not available, we present an approach solely based on inertial sensors, which also can be used as a speedometer. The map information is included in a Bayesian setting using the particle filter (PF) rather than standard map matching. In extensive experiments, the performance without gnss is shown to have basically the same quality as utilizing a gnss sensor. Several topics are treated: virtual measurements, dead reckoning, inertial sensor information, indoor positioning, off-road driving, and multilevel positioning.
TL;DR: The latest research in domain adaptation using deep neural networks and a brief survey of nondeep-learning techniques are outlined, which highlights some drawbacks with the current state of research in this area and offers directions for future research.
Abstract: Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.
TL;DR: This lecture note introduces a rectified-correlations on a sphere (RECOS) transform as a basic building block of CNNs, and provides a full explanation to the operating principle ofCNNs.
Abstract: There is a resurging interest in developing a neural-network-based solution to the supervised machine-learning problem. The convolutional neural network (CNN) will be studied in this lecture note. We introduce a rectified-correlations on a sphere (RECOS) [1] transform as a basic building block of CNNs. It consists of two main concepts: 1) data clustering on a sphere and 2) rectification. We then interpret a CNN as a network that implements the guided multilayer RECOS transform with two highlights. First, we compare the traditional single-layer and modern multilayer signal-analysis approaches, point out key areas that enable the multilayer approach, and provide a full explanation to the operating principle of CNNs. Second, we discuss how guidance is provided by labels through backpropagation (BP) in the training.
TL;DR: Human behavior offers a window into the mind when the authors observe someone's actions-their beliefs, intents, and knowledge-a concept known as theory of mind.
Abstract: Human behavior offers a window into the mind. When we observe someone's actions, we are constantly inferring his or her mental states-their beliefs, intents, and knowledge-a concept known as theory of mind. For example.
TL;DR: The key development and the major progress the community has made, their impact in both research and industry deployment, and what lies ahead in future breakthroughs are analyzed.
Abstract: Generating a natural language description from an image is an emerging interdisciplinary problem at the intersection of computer vision, natural language processing, and artificial intelligence (AI). This task, often referred to as image or visual captioning, forms the technical foundation of many important applications, such as semantic visual search, visual intelligence in chatting robots, photo and video sharing in social media, and aid for visually impaired people to perceive surrounding visual content. Thanks to the recent advances in deep learning, the AI research community has witnessed tremendous progress in visual captioning in recent years. In this article, we will first summarize this exciting emerging visual captioning area. We will then analyze the key development and the major progress the community has made, their impact in both research and industry deployment, and what lies ahead in future breakthroughs.
TL;DR: The current threats and vulnerabilities of GNSS receivers are mapped and a survey of recent defenses is presented, focusing on cryptographic solutions suitable to authenticate civil signals, with particular emphasis on spreading code authentication techniques.
Abstract: A key aspect to be considered in the design of new generations of global navigation satellite system (GNSS) signals and receivers is a proper partition between system and receiver contribution to the robustness against spoofing attacks. This article maps the current threats and vulnerabilities of GNSS receivers and presents a survey of recent defenses, focusing on cryptographic solutions suitable to authenticate civil signals. Future perspectives and trends are analyzed, with particular emphasis on spreading code authentication techniques, considered as a key innovation for the next generation of civil GNSS signals. An assessment of the robustness and feasibility of the various presented solutions is also provided, analyzing in particular the impact on both current and future receivers.
TL;DR: The ionosphere has been the most challenging source of error to mitigate within the community of global navigation satellite system (GNSS)-based safety-critical systems, and ionospheric monitoring and mitigation techniques become more important to support such systems.
Abstract: The ionosphere has been the most challenging source of error to mitigate within the community of global navigation satellite system (GNSS)-based safety-critical systems. Users of those systems should be assured that the difference between an unknown true position and a system-derived position estimate is bounded with an extremely high degree of confidence. One of the major concerns for meeting this requirement, known as integrity, is ionosphere-induced error or discontinuity of GNSS signals significant enough to threaten the safety of users. The potentially hazardous ionospheric anomalies of interest in this article are ionospheric spatial decorrelation and ionospheric scintillation under disturbed conditions. As the demand of safety-critical navigation applications increases with the rapid growth of the autonomous vehicle sector, ionospheric monitoring and mitigation techniques become more important to support such systems.
TL;DR: Inferring information from a set of acquired data is the main objective of any signal processing (SP) method as discussed by the authors, which is at the core of a plethora of scientific and technological advances in recent decades, including wireless communications, radar and sonar, biomedicine, image processing and seismology.
Abstract: Inferring information from a set of acquired data is the main objective of any signal processing (SP) method. The common problem of estimating the value of a vector of parameters from a set of noisy measurements is at the core of a plethora of scientific and technological advances in recent decades, including wireless communications, radar and sonar, biomedicine, image processing, and seismology.
TL;DR: The article describes the fundamental role of TFDs in monitoring the performance of new GNSSs, including satellite clocks and ionospheric scintillation data, and the integration of the spatial domain with the TFDs, through the use of multiantenna receivers, permits the applications of space-time processing for effective jamming mitigation.
Abstract: In this article, we discuss the important role of time-frequency (TF) signal representations in enhancing global navigation satellite system (GNSS) receiver performance. Both linear transforms and quadratic TF distributions (QTFDs) are considered. We review recent advances of antijam techniques that exploit the distinction in the TF signatures between the desired and undesired signals, enabling effective jammer excision with minimum distortion to the navigation signals. The characterization of jammers by their instantaneous frequencies (IFs) lends itself to sparse structures in the TF domain and, as such, invites compressive sensing (CS) and sparse reconstruction to aid in joint-variable domain jamming localization and suppression. Furthermore, the integration of the spatial domain with the TFDs, through the use of multiantenna receivers, permits the applications of space-time processing for effective jamming mitigation. The article also describes the fundamental role of TFDs in monitoring the performance of new GNSSs, including satellite clocks and ionospheric scintillation data. Real GNSS data collected in the presence of jamming are used to demonstrate the effectiveness of TF-based antijam approaches
TL;DR: This work states that there is a greater need for high-quality, diverse, and very large amounts of data in terms of ASA system accuracy and robustness, enabling the extraction of feature representations or the learning of model parameters immune to confounding factors.
Abstract: With recent advances in machine-learning techniques for automatic speech analysis (ASA)-the computerized extraction of information from speech signals-there is a greater need for high-quality, diverse, and very large amounts of data. Such data could be game-changing in terms of ASA system accuracy and robustness, enabling the extraction of feature representations or the learning of model parameters immune to confounding factors, such as acoustic variations, unrelated to the task at hand. However, many current ASA data sets do not meet the desired properties. Instead, they are often recorded under less than ideal conditions, with the corresponding labels sparse or unreliable.
TL;DR: Challenges in achieving effective modeling, detection, and assessment of driver distraction using both UTDrive instrumented vehicle data and naturalistic driving data are highlighted.
Abstract: Vehicle technologies have advanced significantly over the past 20 years, especially with respect to novel in-vehicle systems for route navigation, information access, infotainment, and connected vehicle advancements for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) connectivity and communications. While there is great interest in migrating to fully automated, self-driving vehicles, factors such as technology performance, cost barriers, public safety, insurance issues, legal implications, and government regulations suggest it is more likely that the first step in the progression will be multifunctional vehicles. Today, embedded controllers as well as a variety of sensors and high-performance computing in present-day cars allow for a smooth transition from complete human control toward semisupervised or assisted control, then to fully automated vehicles. Next-generation vehicles will need to be more active in assessing driver awareness, vehicle capabilities, and traffic and environmental settings, plus how these factors come together to determine a collaborative safe and effective driver-vehicle engagement for vehicle operation. This article reviews a range of issues pertaining to driver modeling for the detection and assessment of distraction. Examples from the UTDrive project are used whenever possible, along with a comparison to existing research programs. The areas addressed include 1) understanding driver behavior and distraction, 2) maneuver recognition and distraction analysis, 3) glance behavior and visual tracking, and 4) mobile platform advancements for in-vehicle data collection and human-machine interface. This article highlights challenges in achieving effective modeling, detection, and assessment of driver distraction using both UTDrive instrumented vehicle data and naturalistic driving data
TL;DR: In the future, machine-type communication is expected to play a major role in vehicular environments, with more sensors that monitor the internal state of vehicles and autonomously exchange service and maintenance information with cloud servers of manufacturers.
Abstract: Vehicular communications is an important enabler for enhancing the safety on roads by supporting mutual awareness of vehicles as well as for improving the efficiency of transportation through smart traffic management by intelligent transport systems (ITSs). Governments around the world have set ambitious goals for road fatality reduction in the near future; e.g., the European Union targets a 50% reduction of road fatalities by 2020 as compared to the year 2010. Furthermore, traffic telematic systems aim to minimize the environmental impact of transportation and maximize the utilization of available road infrastructure by adaptive traffic management. To realize these challenging targets, autonomous wireless information exchange among vehicles-vehicle to vehicle (V2V)-and with roadside infrastructure-vehicle to infrastructure (V2I)-are central ingredients. In addition to traffic efficiency and safetyrelated issues, vehicular communications is increasingly recognized as an important revenue driver by car manufacturing companies since it enables wirelessly connected in-vehicle entertainment systems that support on-demand video streaming and online Internet access for passengers. Also, in the future, machine-type communication is expected to play a major role in vehicular environments, with more sensors that monitor the internal state of vehicles and autonomously exchange service and maintenance information with cloud servers of manufacturers. Depending on the considered use-case, distinct quality of service (QoS) requirements come into play [1]: infotainment applications for in-car users require high bandwidth and network capacity, active road safety relies on delay- and outage-critical data transmission, whereas information exchange for road traffic efficiency management typically comes without strict QoS requirements and exhibits graceful degradation of performance with increasing latency.
TL;DR: Many current and emerging applications require low-latency communication, including interactive voice and video communication, multiplayer gaming, multiperson augmented/virtual reality, and various Internet of Things (IoT) applications.
Abstract: Many current and emerging applications require low-latency communication, including interactive voice and video communication, multiplayer gaming, multiperson augmented/virtual reality, and various Internet of Things (IoT) applications. Forward error correction (FEC) codes for low-delay interactive applications have several characteristics that distinguish them from traditional FEC. The encoding and decoding operations must process a stream of data packets in a sequential fashion. Strict latency constraints limit the use of long block lengths, interleaving, or large buffers. Furthermore, these codes must achieve fast recovery from burst losses and yet be robust to other types of loss patterns.