检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer vision (WACV)

作者： Raktim Gautam Goswami Naman Patel Prashanth Krishnamurthy Farshad Khorrami Department of Electrical and Computer Engineering Control/Robotics Research Laboratory (CRRL) NYU Tandon School of Engineering Brooklyn NY USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long training times hinder rapid adaptation to new environments. To address this, we propose FlashMix, which uses a frozen, scene-agnostic backbone to extract local point descriptors, aggregated with an MLP mixer to predict sensor pose. A buffer of local descriptors is used to accelerate training by orders of magnitude, combined with metric learning or contrastive loss regularization of aggregated descriptors to improve performance and convergence. We evaluate FlashMix on various LiDAR localization benchmarks, examining different regularizations and aggregators, and demonstrating its effectiveness for rapid and accurate LiDAR localization in real-world scenarios. The code is available at https://***/raktimgg/FlashMix.

关键词： Location awareness Training Measurement Point cloud compression Laser radar Accuracy Pose estimation Benchmark testing Mixers Convergence

来源：评论

学校读者我要写书评

暂无评论

SENSOR-DRIVEN INTELLIGENT robotics

引用

ADVANCES IN computerS 1991年第C期32卷 105-148页

作者： TRIVEDI, MM CHEN, CX Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department The University of Tennessee Knoxville Tennessee

Intelligent robotic systems should be capable of performing a range of complex tasks in unstructured and dynamic environments. This chapter discusses a number of important items associated with intelligent robots, role of vision sensing in intelligent robotics, and architecture for the design of an intelligent robot. The chapter also describes the computational task hierarchy that governs a model-based robot vision system, and presents a detailed tutorial on two important components of this hierarchy: image segmentation and matching. The main capabilities that intelligent robotic systems should possess include ability for perception of their environment, planning of their actions, and execution of the planned action. The two important components of a model-based vision system are image segmentation and the matching module. A procedure that allows transformation of 2D image coordinates into 3D world coordinates is also discussed in the chapter. The architecture and control aspects of an integrated sensor-based robotic system consist of six modules: supervisor, task planner, perception, motor, user interface, and knowledge-base. Intelligent, sensor-driven systems pose many challenging basic-research problems from a broad range of scientific and technological disciplines; however, there are many important application areas where such systems would be of significant value and utility, including hazardous environments such as nuclear plants, underwater, and space as well as many industrial-automation tasks. Recent advancements in the VLSI, computer-architectures, sensor-and robot-hardware, and artificial-intelligence fields may aid to the development of robust, practical, and cost-effective intelligent robotic systems for a wide variety of applications.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTS IN ACTIVE vision WITH REAL AND VIRTUAL ROBOT HEADS

引用

APPLIED INTELLIGENCE 1995年第3期5卷 237-250页

作者： MARAPANE, SB TRIVEDI, MM Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department The University of Tennessee 37996-2100 Knoxville TN

In the emerging paradigm of animate vision, the visual processes are not thought of as being independent of cognitive or motor processing, but as an integrated system within the context of visual behavior. Intimate coupling of sensory and motor systems have found to improve significantly the performance of behavior based vision systems. In order to study active vision systems one requires sensory-motor systems. Designing, building, and operating such a test bed is a challenging task. In this paper we describe the status of on-going work in developing a sensory-motor robotic system, R2H, with ten degrees of freedoms (DOF) for research in active vision. To complement the R2H system a Graphical Simulation and Animation (GSA) environment is also developed. The objective of building the GSA system is to create a comprehensive design tool to design and study the behavior of active systems and their interactions with the environment. GSA system aids the researchers to develop high performance and reliable software and hardware in a most effective manner. The GSA environment integrates sensing and motor actions and features complete kinematic simulation of the R2H system, it's sensors and it's workspace. With the aid of the GSA environment a Depth from Focus (DFF), Depth from Vergence, and Depth from Stereo modules are implemented and tested. The power and usefulness of the GSA system as a research tool is demonstrated by acquiring and analyzing images in the real and virtual worlds using the same software implemented and tested in the virtual world.

关键词： ACTIVE vision ROBOT HEADS ROBOT SIMULATION DEPTH EXTRACTION

来源：评论

学校读者我要写书评

暂无评论

High-speed extraction of 3D structure of selectable quality using a translating camera

引用

computer vision AND IMAGE UNDERSTANDING 1996年第1期64卷 97-110页

作者： Dalmia, AK Trivedi, M Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department The University of Tennessee Knoxville Tennessee 37996-2100

In this paper we present a computational approach for extracting three-dimensional structure of controllable resolution, depth of field, and accuracy, all made available at real-time speeds, This approach utilizes the spatial and the temporal gradients of the streams of images acquired using an actively controlled camera, Depending on the requirements of a particular task, appropriate parameters such as disparity value sought, interframe camera displacement, and number of frames in a stream are chosen to control the resolution, depth of field, and accuracy, The acquisition and processing of the image stream are done in real time on a pipeline architecture based processor. Extensive experiments are presented to demonstrate the system's accuracy, controllability of depth of field and resolution, and ability to perform successfully in a variety of scenes. The system operated with no latency between image acquisition and processing. The total acquisition and processing time in these experiments is in the range from 0.27 to 1.56 s. The depth results have an accuracy of 85% to 92%. (C) 1996 Academic Press, Inc.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMATION RELATIONSHIPS FOR 2 COMMONLY UTILIZED EULER ANGLE REPRESENTATIONS

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1992年第3期22卷 555-559页

作者： CHEN, CX TRIVEDI, MM Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA

There is no standard representation scheme that is followed by different groups of robot designers to describe the orientation of a rotating rigid body. For a sensor-based robot, the particular rotation representation scheme used by the robot affects not only the specification of the positioning of the arm and end-effector, but also the specification of the placement of the sensors and the method of computing the sensory-to-world transformation. Thus the need for finding the transformation between different rotation representations is obvious for one involved in the development of high-level software systems that need to be transported to different robots utilizing different rotation representation schemes. Among those representation schemes, Euler angle representations are widely used in commercial robots as well as in research laboratory robots. Typically, there are three different Euler angle representation systems, and each system describes a particular orientation of a rigid body in a reference coordinate frame by specifying three angles. Mathematical derivations of the transformation relationships underlying the parameters from two most commonly utilized representation schemes are presented. These relationships are derived in two different ways. One is based upon the solution of the inverse transform for Euler angles and the other is based upon the Napier's rules associated with spherical trigonometry.

关键词： Robot kinematics Robot sensing systems Manipulators Laboratories Quaternions US department of Energy Software systems Hardware Software standards Control systems

来源：评论

学校读者我要写书评

暂无评论

RESIDUAL UNCERTAINTY IN 3-DIMENSIONAL RECONSTRUCTION USING 2-PLANES CALIBRATION AND STEREO METHODS

引用

PATTERN RECOGNITION 1995年第7期28卷 1073-1082页

作者： THAYER, S TRIVEDI, M Electrical and Computer Engineering Department Computer Vision and Robotics Research Laboratory The University of Tennessee Knoxville TN 37996-2100 U.S.A.

A necessary goal in the calibration of any instrument is an indication of how well the particular device performs. In the specific case where a camera system is used in the process of three-dimensional reconstruction or stereopsis, geometric measures of the accuracy, precision, and repeatability of 3-D point measurements give a quantitative evaluation of the success of that algorithm. This paper presents an experimental performance analysis of a traditional calibration algorithm as applied to the problem of three-dimensional vision. The study begins with an analysis of the algorithm in a single camera or monocular system. Monocular analysis concludes with a derivation of error boundaries under different. geometric constraints. Showing how this residual error propagates from the component monocular systems into a three-dimensional reconstruction, a binocular analysis derives the desired performance monitors. The paper concludes with a geometric interpretation of the results.

关键词： STEREOPSIS ACCURACY PRECISION REPEATABILITY MONOCULAR BINOCULAR 2-PLANES CALIBRATION

来源：评论

学校读者我要写书评

暂无评论

EARLY ORIENTATION SELECTION - TANGENT FIELDS AND THE DIMENSIONALITY OF THEIR SUPPORT

引用

computer vision GRAPHICS AND IMAGE PROCESSING 1985年第1期32卷 74-103页

作者： ZUCKER, SW Computer Vision and Robotics Laboratory Department of Electrical Engineering McGill University Montréal Québec Canada

Orientation selection is the inference of orientation information out of images. It is one of the foundations on which other visual structures are built, since it must precede the formation of contours out of pointillist data and surfaces out of surface markings. We take a differential geometric view in defining orientation selection, and develop algorithms for actually doing it. The goal of these algorithms is formulated in mathematical terms as the inference of a vector field of tangents (to the contours), and the algorithms are studied in both abstract and computational forms. They are formulated as matching problems, and algorithms for solving them are reduced to biologically plausible terms. We show that two different matching problems are necessary, the first for 1-dimensional contours (which we refer to as Type I processes) and second for 2-dimensional flows (or Type II processes). We conjecture that this difference is reflected in the response properties of “simple” and “complex” cells, respectively, and predict several other psychophysical phenomena.

关键词： vision

来源：评论

学校读者我要写书评

暂无评论

SIMULATION AND ANIMATION OF SENSOR-DRIVEN ROBOTS

引用

IEEE TRANSACTIONS ON robotics AND AUTOMATION 1994年第5期10卷 684-704页

作者： CHEN, CX TRIVEDI, MM BIDLACK, CR Computer Vision and Robotics Research Laboratory the Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA Artificial Intelligence Laboratory College of Engineering University of Michigan Ann Arbor MI USA

Most simulation and animation systems utilized in robotics are concerned with simulation of the robot and its environment without simulation of sensors. These systems have difficulty in handling robots that utilize sensory feedback in their operation. In this paper, a new design of an environment for simulation, animation, and visualization of sensor-driven robots is presented. As sensor technology advances, increasing numbers of robots are equipped with various types of sophisticated sensors. The main goal of creating the visualization environment is to aid the automatic robot programming and off-line programming capabilities of sensor-driven robots. The software system will help the users visualize the motion and reaction of the sensor-driven robot under their control program. Therefore, the efficiency of the software development is increased, the reliability of the software and the operation safety of the robot are ensured, and the cost of new software development is reduced. Conventional computer-graphics-based robot simulation and animation software packages lack of capabilities for robot sensing simulation. This paper describes a system designed to overcome this deficiency.

关键词： Animation Robot sensing systems robotics and automation Visualization Robot programming Software safety Computational modeling computer simulation Automatic programming Software systems

来源：评论

学校读者我要写书评

暂无评论

ROBOT PERFORMANCE-MEASUREMENT AND CALIBRATION USING A 3D computer vision SYSTEM

引用

ROBOTICA 1995年第4期13卷 327-337页

作者： PREISING, B HSIA, TC Robotics Research Laboratory Department of Electrical and Computer Engineering University of California Davis Davis California 95616 (USA)

Present day robot systems are manufactured to perform within industry accepted tolerances. However, to use such systems for tasks requiring high precision, various methods of robot calibration are generally required. These procedures can improve the accuracy of a robot within a small volume of the robot's workspace. The objective of this paper is to demonstrate the use of a single camera 3D computer vision system as a position sensor in order to perform robot calibration. A vision feedback scheme, termed vision-guided Robot Control (VRC), is described which can improve the accuracy of a robot in an on-line iterative manner. This system demonstrates the advantage that can be achieved by a Cartesian space robot control scheme when end effector position/orientation are actually sensed instead of calculated from the kinematic equations. The degree of accuracy is determined by setting a tolerance level for each of the six robot Cartesian space coordinates. In general, a small tolerance level requires a large number of iterations in order to position the end effector, and a large tolerance level requires fewer iterations. The viability of using a vision system for robot calibration is demonstrated by experimentally showing that the accuracy of a robot can be drastically improved. In addition, the vision system can also be used to determine the repeatability and accuracy of a robot in a simple, efficient, and quick manner. Experimental work with an IBM Electric Drive Robot (EDR) and the proposed vision system produced a 97 and a 145 fold improvement in the position and orientation accuracy of the robot, respectively.

关键词： 3D vision ROBOT PERFORMANCE CALIBRATION POSITION SENSOR

来源：评论

学校读者我要写书评

暂无评论

A REAL-TIME IMPLEMENTATION OF STRUCTURE ESTIMATION USING IMAGE STREAMS 6

A REAL-TIME IMPLEMENTATION OF STRUCTURE ESTIMATION USING IMA...

引用

CONF ON SENSOR FUSION 6

作者： DALMIA, AK TRIVEDI, MM Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee Knoxville 37996-2100 TN United States

ISBN: (纸本)0819413240

The computation of 3-D structure from motion using a monocular sequence of images in the paradigm of active vision is investigated in this paper. Robotic tasks such as navigation, manipulation, and object recognition all require 3-D description of scene. The 3-D description for these tasks varies in resolution, accuracy, robustness, range, and time. In developing such a system, it must have the capability to actively control the imaging parameters so that a 3-D description sufficient enough for that task is generated. The objective of this paper is to investigate a strategy suitable for fast and active 3-D structure estimation. First, the process of 3-D structure estimation in the paradigm of active vision is discussed. Second, implication of image streams in 3-D structure computation is analyzed. The three approaches to structure from motion, feature based, optical flow based, and spatial and temporal gradient based, are reviewed for their efficacy in fast and active estimation of 3-D structure. Finally, a pipeline based implementation of a spatial and temporal gradient based approach is presented alongwith detailed experimental analysis. © 1993 SPIE. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：