Gary Bradski

Bio: Gary Bradski is an academic researcher from Willow Garage. The author has contributed to research in topics: Pose & Object (computer science). The author has an hindex of 41, co-authored 82 publications receiving 23763 citations. Previous affiliations of Gary Bradski include Intel & Stanford University.

Perception for mobile manipulation and grasping using active stereo

Abstract: In this paper we present a comprehensive perception system with applications to mobile manipulation and grasping for personal robotics. Our approach makes use of dense 3D point cloud data acquired using stereo vision cameras by projecting textured light onto the scene. To create models suitable for grasping, we extract the supporting planes and model object clusters with different surface geometric primitives. The resultant decoupled primitive point clusters are then reconstructed as smooth triangular mesh surfaces, and their use is validated in grasping experiments using OpenRAVE [1]. To annotate the point cloud data with primitive geometric labels we make use of our previously proposed Fast Point Feature Histograms [2] and probabilistic graphical methods (Conditional Random Fields), and obtain a classification accuracy of 98.27% for different object geometries. We show the validity of our approach by analyzing the proposed system for the problem of building object models usable in grasping applications with the PR2 robot (see Figure 1).

Motion detection using normal optical flow

Abstract: A system and method obtain images of an object and generate a motion region image of the object. The motion region image is processed to obtain normal gradients of the portion of the object that has been moved. The normal gradient data is further processed to remove erroneous data points. The erroneous data can be removed by using either an eroding method or a threshold method. After the erroneous data is removed, the remaining gradient information is used to identify a motion of the object. This can be performed using a histogram recognition operation.

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Abstract: This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.

Augmented reality devices, systems and methods for purchasing

Abstract: Disclosed herein is an augmented reality (AR) system that provides information about purchasing alternatives to a user who is about to purchase an item or product (e.g., a target product) in a physical retail location. In some variations, offers to purchase the product and/or an alternative product are provided by the merchant and/or competitors via the AR system. An offer negotiation server (ONS) aggregates offer data provided various external parties (EPs) and displays these offers to the user as the user is considering the purchase of a target product. In some variations, an AR system may be configured to facilitate the process of purchasing items at a retail location.

Methods and systems for recognizing machine-readable information on three-dimensional objects

Abstract: Methods and systems for recognizing machine-readable information on three-dimensional (3D) objects are described. A robotic manipulator may move at least one physical object through a designated area in space. As the at least one physical object is being moved through the designated area, one or more optical sensors may determine a location of a machine-readable code on the at least one physical object and, based on the determined location, scan the machine-readable code so as to determine information associated with the at least one physical object encoded in the machine-readable code. Based on the information associated with the at least one physical object, a computing device may then determine a respective location in a physical environment of the robotic manipulator at which to place the at least one physical object. The robotic manipulator may then be directed to place the at least one physical object at the respective location.

MapReduce: simplified data processing on large clusters

Abstract: 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.

MapReduce: simplified data processing on large clusters

Abstract: 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.

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

Abstract: 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.

Mean shift: a robust approach toward feature space analysis

Abstract: 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.

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

Abstract: 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