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

Method and apparatus of the present invention include an image-capturing device coupled to a computer system. An image captured by the image-capturing device is analyzed using a face tracking technique to learn behaviors of the user. This may include determining if the user is paying attention. The attention may be toward a display of the computer system. When the user does not pay attention, power consumption of one or more components of the computer system is reduced.

Method and apparatus for monitoring human attention in dynamic power management

Recognizing and determining the 6DOF pose of transparent objects is necessary in order for robots to manipulate such objects. However, it is a challenging problem for computer vision. We propose new algorithms for segmentation, pose estimation and recognition of transparent objects from a single RGB-D image from a Kinect sensor. Kinect's weakness in the perception of transparent objects is exploited in their segmentation. Following segmentation, edge fitting is used for recognition and pose estimation. A 3D model of the object is created automatically during training and it is required for pose estimation and recognition. The algorithm is evaluated in different conditions of a domestic environment within the framework of a robotic grasping pipeline where it demonstrates high grasping success rates compared to the state-of-the-art results. The method doesn't deal with occlusions and overlapping transparent objects currently but it is robust against non-transparent clutter.

http://www.roboticsproceedings.org/rss08/p35.pdf

Recognition and Pose Estimation of Rigid Transparent Objects with a Kinect Sensor

A method, apparatus and system identify the location of eyes. Specifically, structured light is transmitted towards an object from a structured light source off the optical axis of a structured light depth imaging device. The light returned from the object to the structured light depth imaging device is used to generate a depth image. In the event the object is a face, contrast areas in the depth image indicate the location of the eyes.

Method, apparatus and system for using computer vision to identify facial characteristics

Existing methods for visual recognition based on quantized local features can perform poorly when local features exist on transparent surfaces, such as glass or plastic objects. There are characteristic patterns to the local appearance of transparent objects, but they may not be well captured by distances to individual examples or by a local pattern codebook obtained by vector quantization. The appearance of a transparent patch is determined in part by the refraction of a background pattern through a transparent medium: the energy from the background usually dominates the patch appearance. We model transparent local patch appearance using an additive model of latent factors: background factors due to scene content, and factors which capture a local edge energy distribution characteristic of the refraction. We implement our method using a novel LDA-SIFT formulation which performs LDA prior to any vector quantization step; we discover latent topics which are characteristic of particular transparent patches and quantize the SIFT space into transparent visual words according to the latent topic dimensions. No knowledge of the background scene is required at test time; we show examples recognizing transparent glasses in a domestic environment.

/pdf/an-additive-latent-feature-model-for-transparent-object-1b97z2d92c.pdf

An Additive Latent Feature Model for Transparent Object Recognition

The present invention allows for the locations of points of interest in a calibration object in a calibration image for a digital camera to be identified automatically. The image is an array of pixels corresponding to the calibration object, which has a known reference pattern. In a preferred embodiment, the invention includes receiving an array of pixels produced by a camera, classifying each pixel of the image as light or dark, extracting contours from the image by identifying lines between light and dark pixels, comparing the extracted contours to the shapes of the known reference pattern, and identifying the shapes of the known reference pattern in the image using the extracted contours. Preferably, the image is a color image, and the color information in the pixels of the image are converted into gray scale values to render the image as a gray scale image before the pixels are classified. Classifying each pixel includes applying a brightness threshold to each pixel of the image to classify those pixels having a brightness greater than the threshold as light and those below the threshold as dark.

Gary Bradski

Papers

Method and apparatus for monitoring human attention in dynamic power management

Recognition and Pose Estimation of Rigid Transparent Objects with a Kinect Sensor

Method, apparatus and system for using computer vision to identify facial characteristics

An Additive Latent Feature Model for Transparent Object Recognition

Method and apparatus for determining points of interest on an image of a camera calibration object