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

A radiation sensing structure includes red, green and blue photodiodes stacked Above an infrared radiation sensing photodiode.

Stacked semiconductor radiation sensors having color component and infrared sensing capability

A tracking method is disclosed. The method of the present invention tracks a object using a probability distribution of the desired object. The method operates by first calculating a mean location of a probability distribution within a search window. Next, the search window is centered on the calculated mean location. The steps of calculating a mean location and centering the search window may be performed until convergence. The search window may then be resized. Successive iterations of calculating a mean, centering on the mean, and resizing the search window track an object represented by the probability distribution. In one embodiment, a flesh hue probability distribution is generated from an input video image. The flesh hue probability distribution is used to track a human head within the video image.

Method and apparatus for tracking an object using a continuously adapting mean shift

This paper describes a stereo-based approach for gesture recognition that works well under extreme lighting conditions and tolerates a large range of hand poses. The approach proposes a hybrid gesture representation that models the user's arm as a 3D line and uses images to represent the hand gestures. The algorithm finds the arm orientation and the hand location from the disparity data and uses this information to initialize a color based segmentation algorithm that cleanly separates the hand from the background. Finally, our approach uses the arm orientation to compute a frontal view of the hand through perspective unwarping producing easily recognizable hand gesture templates. The classification algorithm uses statistical moments of the binarized gesture templates to find the match. We achieve 96% recognition rates under varying lighting and 3D poses for a set of 6 gestures.

Stereo based gesture recognition invariant to 3D pose and lighting

Example methods and systems for determining 3D scene geometry by projecting patterns of light onto a scene are provided. In an example method, a first projector may project a first random texture pattern having a first wavelength and a second projector may project a second random texture pattern having a second wavelength. A computing device may receive sensor data that is indicative of an environment as perceived from a first viewpoint of a first optical sensor and a second viewpoint of a second optical sensor. Based on the received sensor data, the computing device may determine corresponding features between sensor data associated with the first viewpoint and sensor data associated with the second viewpoint. And based on the determined corresponding features, the computing device may determine an output including a virtual representation of the environment that includes depth measurements indicative of distances to at least one object.

Determining a virtual representation of an environment by projecting texture patterns

A robust robot perception system intended to enable object manipulation needs to be able to accurately identify objects and their pose at high speeds. Since objects vary considerably in surface properties, rigidity and articulation, no single detector or object estimation method has been shown to provide reliable detection across object types to date. This indicates the need for an architecture that is able to quickly swap detectors, pose estimators, and filters, or to run them in parallel or serial and combine their results, preferably without any code modifications at all. In this paper, we present our implementation of such an infrastructure, ReIn (REcognition INfrastructure), to answer these needs. ReIn is able to combine a multitude of 2D/3D object recognition and pose estimation techniques in parallel as dynamically loadable plugins. It also provides an extremely efficient data passing architecture, and offers the possibility to change the parameters and initial settings of these techniques during their execution. In the course of this work we introduce two new classifiers designed for robot perception needs: BiGGPy (Binarized Gradient Grid Pyramids) for scalable 2D classification and VFH (Viewpoint Feature Histograms) for 3D classification and pose. We then show how these two classifiers can be easily combined using ReIn to solve object recognition and pose identification problems.

/pdf/rein-a-fast-robust-scalable-recognition-infrastructure-47acvefp2a.pdf

Gary Bradski

Papers

Stacked semiconductor radiation sensors having color component and infrared sensing capability

Method and apparatus for tracking an object using a continuously adapting mean shift

Stereo based gesture recognition invariant to 3D pose and lighting

Determining a virtual representation of an environment by projecting texture patterns

REIN - A fast, robust, scalable REcognition INfrastructure