Filters








1,499 Hits in 4.1 sec

Advanced Vision Processor with an Overall Image Processing Unit and Multiple Local Image Processing Modules

Hiroaki Kubota, Kazuhiro Fukui, Minoru Ishikawa, Hiroshi Mizoguchi, Yoshinori Kuno
1990 IAPR International Workshop on Machine Vision Applications  
The vision processor cames out feature extraction for image recognition by means of several local processors in parallel from time varying images on which an overall image processing unit has performed  ...  Special characteristics of the system are that each local processor processes only its region of interest, the division of regions being determined from the image feature and contents.  ...  The concept of this vision processor is that overall and local image processing are executed in parallel and that local processors take up various parallel computation styles according to the processing  ... 
dblp:conf/mva/KubotaFIMK90 fatcat:5g5oroumzrd2bpll54lvnxh6gy

Cutting-Edge Computing: Using New Commodity Architectures

Ming C. Lin, Dinesh Manocha
2008 Proceedings of the IEEE  
An ongoing and contrasting trend has been the development of heterogeneous processor architectures that combine fine-grain and coarse-grain parallelism using tens or hundreds of disparate processing cores  ...  parallel-code performance for a class of applications.  ...  He has published more than 230 papers in leading conferences and journals on computer graphics, geometric and solid modeling, robotics, symbolic and numeric computation, virtual reality, and computational  ... 
doi:10.1109/jproc.2008.917717 fatcat:cwrwaqy37ffdbdculjuwfwqv5y

Learning hardware using multiple-valued logic - Part 1: introduction and approach

M. Perkowski, D. Foote, Qihong Chen, A. Al-Rabadi, L. Jozwiak
2002 IEEE Micro  
Although these software solutions are too slow to be applied in real time, require too many parallel processors to put on a robot, or are too approximate to produce useful solu-tions.  ...  Many robotics, multimedia, and other types of tasks require fast, real-time realization of certain algorithms to solve problems presented by a human's or robot's environment.  ...  For example, the architecture involving both the two-directional pipelining and ping-ponging can compute the morphological Hough transform, which some robots use to find shapes and their locations.  ... 
doi:10.1109/mm.2002.1013303 fatcat:fjeo52iks5hafg5gcuz53h7sxy

The Rochester checkers player: multimodel parallel programming for animate vision

B. Marsh, C. Brown, T. LeBlanc, M. Scott, T. Becker, C. Quiroz, P. Das, J. Karlsson
1992 Computer  
Different parallel programming models are used for vision, robot motion planning, and strategy.  ...  These multi-model programs require an underlying software system that not only suppons several different models of parallel computation simultaneously, but that also allows tasks implemented in different  ...  Brian Marsh is supported by a DARPAI NASA Graduate Research Assistantship in Parallel Processing. The government has certain rights in this material.  ... 
doi:10.1109/2.121471 fatcat:s5i2gyx32jb7dgzsvv3bnx2nji

A Floating-point Extended Kalman Filter Implementation for Autonomous Mobile Robots

Vanderlei Bonato, Eduardo Marques, George A. Constantinides
2008 Journal of Signal Processing Systems  
The EKF simultaneously estimates a model of the environment (map) and the position of the robot based on odometric and exteroceptive sensor information.  ...  As this algorithm demands a considerable amount of computation, it is usually executed on high end PCs coupled to the robot.  ...  This architecture has been developed to be integrated with a light embedded processor to compute the prediction and measurement models from equations (2) and (10) along with their Jacobian matrices  ... 
doi:10.1007/s11265-008-0257-8 fatcat:d7lbdmtm2vgs5bkuebsdisfgxi

A Floating-Point Extended Kalman Filter Implementation for Autonomous Mobile Robots

Vanderlei Bonato, Eduardo Marques, George A. Constantinides
2007 2007 International Conference on Field Programmable Logic and Applications  
The EKF simultaneously estimates a model of the environment (map) and the position of the robot based on odometric and exteroceptive sensor information.  ...  As this algorithm demands a considerable amount of computation, it is usually executed on high end PCs coupled to the robot.  ...  This architecture has been developed to be integrated with a light embedded processor to compute the prediction and measurement models from equations (2) and (10) along with their Jacobian matrices  ... 
doi:10.1109/fpl.2007.4380720 dblp:conf/fpl/BonatoMC07 fatcat:6inek3poqnbkzpvtery7uxih3i

Geometric Algebra Computers [chapter]

Dietmar Hildenbrand
2012 Geometry and Computing  
On the other hand, there is a recent development of computer platforms from single processors to parallel computing platforms which are able to handle the high dimensional multivectors of geometric algebra  ...  On one hand, there is a recent development of geometric algebra to an easy handling of engineering applications, especially in computer graphics, computer vision and robotics.  ...  Figure 3 : 3 Computing architecture with a number of parallel processors, each consisting of local program memory. All the processors are able to communicate via global shared memory.  ... 
doi:10.1007/978-3-642-31794-1_14 fatcat:itwitou6yvgznjr566fm3jnvte

Gaalop—High Performance Parallel Computing Based on Conformal Geometric Algebra [chapter]

Dietmar Hildenbrand, Joachim Pitt, Andreas Koch
2010 Geometric Algebra Computing  
An inverse kinematics algorithm of a humanoid robot is described as an example.  ...  We present Gaalop (Geometric algebra algorithms optimizer), our tool for high performance computing based on conformal geometric algebra.  ...  The Architecture of Gaalop Inverse Kinematics of the Leg of a Humanoid Robot In this section we present an inverse kinematics algorithm for the leg of the humanoid robot 'Mr.  ... 
doi:10.1007/978-1-84996-108-0_22 fatcat:d2ymfzzfbbau7i2xymhst4vbm4

Advancements in Microprocessor Architecture for Ubiquitous AI—An Overview on History, Evolution, and Upcoming Challenges in AI Implementation

Fatima Hameed Khan, Muhammad Adeel Pasha, Shahid Masud
2021 Micromachines  
In tandem with the emergence of multicore processors, ML techniques started to be embedded in a range of scenarios and applications.  ...  Since the 1990s, advancements in computer architecture and memory organization have enabled microprocessors to deliver much higher performance.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/mi12060665 fatcat:edbpii37wfgnxamx76k42qldsq

Tagged behavior based systems: integrating cognition with embodied activity

I. Horswill
2001 IEEE Intelligent Systems  
A utomated reasoning systems are typically built on a transaction-oriented model of computation.  ...  The relevant distinction is not between symbolic and nonsymbolic computation but rather between a transaction-based model of computation and a circuit-based model of computation.  ...  Real robots consist of a large number of sensory, motor, and reasoning processes operating in parallel, on separate processors, and often on simple processors with little or no operating system.  ... 
doi:10.1109/5254.956079 fatcat:jda4icawkvdhxbxufj47w6n25y

Tagged behavior based systems: integrating cognition with embodied activity

I. Horswill
2001 IEEE Intelligent Systems  
A utomated reasoning systems are typically built on a transaction-oriented model of computation.  ...  The relevant distinction is not between symbolic and nonsymbolic computation but rather between a transaction-based model of computation and a circuit-based model of computation.  ...  Real robots consist of a large number of sensory, motor, and reasoning processes operating in parallel, on separate processors, and often on simple processors with little or no operating system.  ... 
doi:10.1109/mis.2001.956079 fatcat:fgcttbcjqnevxiwpw4shoc5oaa

Operating system support for animate vision

B. Marsh, C. Brown, T. LeBlanc, M. Scott, T. Becker, P. Das, J. Karlsson, C. Quiroz
1992 Journal of Parallel and Distributed Computing  
These multi-model programs require an underlying software system that not only supports several different models of parallel computation simultaneously, but which also allows tasks implemented in different  ...  The implementation of the Checkers Player, in which different parallel programming models are used for vision, robot motion planning, and strategy, illustrates the use of the Psyche mechanisms in an application  ...  several choices of general-purpose MIMD parallel processors for computations from high-level vision and planning to motor control.  ... 
doi:10.1016/0743-7315(92)90104-u fatcat:sl7jyz5jazg4jmyrjxqzsvqnaa

A two-level real-time vision machine combining coarse- and fine-grained parallelism

Lars Baunegaard With Jensen, Anders Kjær-Nielsen, Karl Pauwels, Jeppe Barsøe Jessen, Marc Van Hulle, Norbert Krüger
2010 Journal of Real-Time Image Processing  
The system operates at more than 20 Hz using a hybrid architecture consisting of one dual-GPU card and one quad-core CPU.  ...  We show that with such hybrid parallelism, we can achieve a speed up of approximately a factor 90 and a reduction of latency of a factor 26 compared to processing on a single CPU-core.  ...  Coarse-grained parallelization scheme According to Tröger [45] the wide variety of parallel hardware architectures in today's computers is moving the parallelization problem to software.  ... 
doi:10.1007/s11554-010-0159-4 fatcat:fxwmjqaxk5gslhbtttetbu3tqq

IntelliSoC: A System Level Design and Conception of a System- on-a-Chip (SoC) to Cognitive Agents Architecture [chapter]

Diego Ferreira, Augusto Loureiro da Costa, Wagner Luiz Alves De Oliveira
2019 Applications of Mobile Robots  
The computational architecture of this SoC will be presented using the cognitive model of the concurrent autonomous agent (CAA) as a reference.  ...  Thus, this work proposes a novel SoC whose architecture fits the computational demands of the aforementioned cognitive model, allowing for fast, energy-efficient, embedded intelligent applications.  ...  The search processors consist of a 6-stage pipeline that uses a three-level cache to implement a transposition and avoid redundant computation between threads.  ... 
doi:10.5772/intechopen.79265 fatcat:uucfl4pz4fbvxbmhbyevg7hlaq

Book of abstracts

2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
This hierarchical approach emulates the organizational principles of biological vision systems, by using an array of elementary and relatively coarse processors to achieve global computation, and also  ...  Instead, we are working in adapted architectures in which the parallelism that is inherent to lower level vision tasks is largely exploited.  ...  the Office of Naval Research (USA) through contract N000141110312.  ... 
doi:10.1109/iros.2012.6385435 fatcat:d77yaqbnlng2fmdnbqa6hau4pu
« Previous Showing results 1 — 15 out of 1,499 results