MapReduce is a programming model and an associated implementation for processing and generating large data sets. Users specify a map function that processes a key/value pair to generate a set of intermediate key/value pairs, and a reduce function that merges all intermediate values associated with the same intermediate key. Many real world tasks are expressible in this model, as shown in the paper.

Programs written in this functional style are automatically parallelized and executed on a large cluster of commodity machines. The run-time system takes care of the details of partitioning the input data, scheduling the program's execution across a set of machines, handling machine failures, and managing the required inter-machine communication. This allows programmers without any experience with parallel and distributed systems to easily utilize the resources of a large distributed system.

Our implementation of MapReduce runs on a large cluster of commodity machines and is highly scalable: a typical MapReduce computation processes many terabytes of data on thousands of machines. Programmers find the system easy to use: hundreds of MapReduce programs have been implemented and upwards of one thousand MapReduce jobs are executed on Google's clusters every day.

/pdf/mapreduce-simplified-data-processing-on-large-clusters-16emdgg5h5.pdf

MapReduce: simplified data processing on large clusters

MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a map and a reduce function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day.

/pdf/mapreduce-simplified-data-processing-on-large-clusters-1zth35tzla.pdf

Many problems of recent interest in statistics and machine learning can be posed in the framework of convex optimization. Due to the explosion in size and complexity of modern datasets, it is increasingly important to be able to solve problems with a very large number of features or training examples. As a result, both the decentralized collection or storage of these datasets as well as accompanying distributed solution methods are either necessary or at least highly desirable. In this review, we argue that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas. The method was developed in the 1970s, with roots in the 1950s, and is equivalent or closely related to many other algorithms, such as dual decomposition, the method of multipliers, Douglas–Rachford splitting, Spingarn's method of partial inverses, Dykstra's alternating projections, Bregman iterative algorithms for l1 problems, proximal methods, and others. After briefly surveying the theory and history of the algorithm, we discuss applications to a wide variety of statistical and machine learning problems of recent interest, including the lasso, sparse logistic regression, basis pursuit, covariance selection, support vector machines, and many others. We also discuss general distributed optimization, extensions to the nonconvex setting, and efficient implementation, including some details on distributed MPI and Hadoop MapReduce implementations.

/pdf/distributed-optimization-and-statistical-learning-via-the-8s9gtddw0d.pdf

Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers

A general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern recognition procedure: the mean shift. For discrete data, we prove the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density. The relation of the mean shift procedure to the Nadaraya-Watson estimator from kernel regression and the robust M-estimators; of location is also established. Algorithms for two low-level vision tasks discontinuity-preserving smoothing and image segmentation - are described as applications. In these algorithms, the only user-set parameter is the resolution of the analysis, and either gray-level or color images are accepted as input. Extensive experimental results illustrate their excellent performance.

Mean shift: a robust approach toward feature space analysis

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti

/pdf/are-we-ready-for-autonomous-driving-the-kitti-vision-zygefho352.pdf

Are we ready for autonomous driving? The KITTI vision benchmark suite

Methods and devices for estimating position of a device within a 3D environment are described. Embodiments of the methods include sequentially receiving multiple image segments forming an image representing a field of view (FOV) comprising a portion of the environment. The image includes multiple sparse points that are identifiable based in part on a corresponding subset of image segments of the multiple image segments. The method also includes sequentially identifying one or more sparse points of the multiple sparse points when each subset of image segments corresponding to the one or more sparse points is received and estimating a position of the device in the environment based on the identified the one or more sparse points.

Estimating pose in 3D space

A method and apparatus for boosted linear modeling of non-linear time series. An embodiment of a method includes receiving a series of data elements, where the series of data elements is a time series and where the time series has a non-linearity. One or more decision trees are generated for the data elements, with the decision tree models dividing the time series into a plurality of data groups. Further, each of the data groups is modeled as a linear function.

Boosted linear modeling of non-linear time series

A wearable device can include an inward-facing imaging system configured to acquire images of a user's periocular region. The wearable device can determine a relative position between the wearable device and the user's face based on the images acquired by the inward-facing imaging system. The relative position may be used to determine whether the user is wearing the wearable device, whether the wearable device fits the user, or whether an adjustment to a rendering location of virtual object should be made to compensate for a deviation of the wearable device from its normal resting position.

Periocular test for mixed reality calibration

A method, apparatus and system identify the location of eyes. Specifically, a 360-degree camera is used to generate images of a face and identify the location of eyes in the face. A first light source on the axis of the 360-degree camera projects light towards the face and a first polar coordinate image is generated from the light that is returned from the face. A second light source off the axis of the 360-degree camera projects light towards the face and a second polar coordinate image is generated from the light that is returned from the face. The first and the second images are then compared to each other and a contrast area is identified to indicate the location of the eyes. The first and second polar coordinate images may be automatically converted into perspective images for various applications such as teleconferencing.

Method, apparatus and system for using 360-degree view cameras to identify facial features

We present a novel method for solving the challenging problem of generating 3D models of generic object categories from just one single un-calibrated image. Our method leverages the algorithm proposed in [1] which enables a partial reconstruction of the object from a single view. A full reconstruction is achieved in a subsequent object completion stage where modified or state-of-the-art 3D shape and texture completion techniques are used to recover the complete 3D model. We present results of our method on a number of images containing objects from five generic categories (mice, staplers, mugs, cars, and bicycles). We demonstrate (numerically and qualitatively) that our method produces convincing 3D models from a single image using minimal or no human intervention. Our technique is targeted to applications where users are interested in building virtual collections of 3D models of objects, and sharing such models in virtual environments such as Google 3D Warehouse or Second Life (secondlife.com).

Gary Bradski

Papers

Estimating pose in 3D space

Boosted linear modeling of non-linear time series

Periocular test for mixed reality calibration

Method, apparatus and system for using 360-degree view cameras to identify facial features

Toward Automatic 3D Generic Object Modeling from One Single Image