检索结果-内蒙古大学图书馆

ENDSTOPPED NEURONS IN THE VISUAL-CORTEX AS A SUBSTRATE FOR CALCULATING CURVATURE

NATURE 1987年第6138期329卷 438-441页

作者： DOBBINS, A ZUCKER, SW CYNADER, MS Computer Vision and Robotics Laboratory McGill Research Centre for Intelligent Machines McGill University 3480 University Street Montréal Québec H3A 2A7 Canada

Neurons in the visual cortex typically respond selectively to the orientation, and velocity and direction of movement, of moving-bar stimuli. These responses are generally thought to provide information about the orientation and position of lines and edges in the visual field. Some cells are also endstopped, that is selective for bars of specific lengths. Hubel and Wiesel first observed that endstopped hypercomplex cells1 could respond to curved stimuli and suggested they might be involved in detection of curvature, but the exact relationship between endstopping and curvature has never been determined. We present here a mathematical model relating endstopping to curvature in which the difference in response of two simple cells gives rise to endstopping and varies in proportion to curvature. We also provide physiological evidence that endstopped cells in area 17 of the cat visual cortex are selective for curvature, whereas non-endstopped cells are not, and that some are selective for the sign of curvature. The prevailing view of edge and curve determination is that orientations are selected locally by the class of simple cortical cells3 and then integrated to form global curves. We have developed a computational theory of orientation selection4,5 which shows that measurements of orientation obtained by simple cells are not sufficient because there will be strong, incorrect responses from cells whose receptive fields (RFs) span distinct curves (Fig. 1). If estimates of curvature are available, however, these inappropriate responses can be eliminated. Curvature provides the key to structuring the network that underlies our theory and distinguishes it from previous lateral inhibition schemes6,7.

关键词： Science Humanities and Social Sciences multidisciplinary

来源：评论

学校读者我要写书评

暂无评论

Comprehensive parameter sweep for learning-based detector on traffic lights 12th

Comprehensive parameter sweep for learning-based detector on...

引用

12th International Symposium on Visual Computing, ISVC 2016

作者： Jensen, Morten B. Philipsen, Mark P. Moeslund, Thomas B. Trivedi, Mohan Visual Analysis of People Laboratory Aalborg University Aalborg Denmark Computer Vision and Robotics Research Laboratory UC San Diego La Jolla United States

ISBN: (纸本)9783319508313

Determining the optimal parameters for a given detection algorithm is not straightforward and what ends up as the final values is mostly based on experience and heuristics. In this paper we investigate the influence of three basic parameters in the widely used Aggregate Channel Features (ACF) object detector applied for traffic light detection. Additionally, we perform an exhaustive search for the optimal parameters for the night time data from the LISA Traffic Light Dataset. The optimized detector reaches an Area-Under-Curve of 66.63% on calculated precision-recall curve. © Springer International Publishing AG 2016.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A biologically motivated approach to early visual computations: orientation selection, texture, and optical flow 4th

A biologically motivated approach to early visual computatio...

引用

4th International Conference on Pattern Recognition, 1988

作者： Zucker, Steven W. Computer Vision and Robotics Laboratory McGill Research Centre for Intelligent Machines McGill University MontréalQC Canada The Canadian Institute for Advanced Research Canada

ISBN: (纸本)9783540190363

The problem of curve detection decomposes naturally into two stages: (i) inferring the (discrete) trace and tangent to the curve;and (ii) finding integrals through the resultant tangent field. Orientation selection is the term used by physiologists for the first of these stages;i.e., for the process of extracting the tangents to piecewise smooth curves from a two-dimensional image. We present an analysis of the orientation selection process from a computational perspective that is strongly influenced by various biological constraints. As such, it provides both a solid foundation for curve detection algorithms within computer vision systems and illustrates the insights that can be gained by analyzing biological vision systems. Formal extensions to the algorithm can also be posed that provide further insight into texture and optical flow. © 1988, Springer-Verlag.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

vision-based Lane Analysis: Exploration of Issues and Approaches for Embedded Realization

Vision-based Lane Analysis: Exploration of Issues and Approa...

引用

IEEE Conference on computer vision and Pattern Recognition Workshops

作者： R. K. Satzoda Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California

ISBN: (纸本)9781479909940

Lane feature extraction is one of the key computational steps in lane analysis systems. In this paper, we propose a lane feature extraction method, which enables different configurations of embedded solutions that address both accuracy and embedded systems' constraints. The proposed lane feature extraction process is evaluated in detail using real world lane data, to explore its effectiveness for embedded realization and adaptability to varying contextual information like lane types and environmental conditions.

关键词： Lanes Feature extraction Extraction processes embedding

来源：评论

学校读者我要写书评

暂无评论

Multimodal stereo image registration for pedestrian detection

Multimodal stereo image registration for pedestrian detectio...

引用

ITSC 2006: 2006 IEEE Intelligent Transportation Systems Conference

作者： Krotosky, Stephen Trivedi, Mohan Computer Vision and Robotics Research Laboratory University of California San Diego 9500 Gilman Dr. 0434 San Diego CA 92093 United States

ISBN: (纸本)1424400945

This paper presents an approach for the registration of multimodal imagery for pedestrian detection when the significant depth differences of objects in the scene precludes a global alignment assumption. Using maximization-of-mutual- information matching techniques and sliding correspondence windows over calibrated image pairs, we demonstrate successful registration of color and thermal data. We develop a robust method using disparity voting for determining the registration of each object in the scene and provide a statistically based measure for evaluating the match confidence. Testing shows successful registration in complex scenes with multiple people at different depths and levels of occlusion. © 2006 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Complexity based investigation in collaborative assembly scenarios via non intrusive techniques 4

Complexity based investigation in collaborative assembly sce...

引用

4th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2022

作者： Panagou, Sotirios Sileo, Monica Papoutsakis, Konstantinos Fruggiero, Fabio Qammaz, Ammar Argyros, Antonis School of Engineering University of Basilicata Potenza85100 Italy Computational Vision and Robotics Laboratory Institute of Computer Science Foundation for Research and Technology - Hellas Heraklion70013 Greece

Human and robot collaboration in assembly tasks is an integral part in modern manufactories. Robots provide advantages in both process and productivity with their repeatability and usability in different tasks, while human operators provide flexibility and can act as safeguards. However, process complexity increases which can lower the overall quality. Increased complexity can negatively influence decision making due to cognitive load on human operators, which can lead to lower quality, be it product, process or human work. Moreover, it can lead to safety risks, human-system error and accidents. In this work, we present the preliminary results on an experiment performed with student-participants, based on an assembly task. The experiment was set up to emulate an industrial assembly, and data collection was performed through qualitative and non-intrusive quantitative methods. Questionnaires were used to assess perceptual task complexity and cognitive load, while a stereo camera provided recordings for after-task analysis on process errors and human work quality based on a 3D skeleton-based human pose estimation and tracking method. The aim of the study is to investigate causes of errors and implications on quality. Future direction of the work is discussed. © 2022 The Authors. Published by ELSEVIER B.V.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Motion perception using spatiotemporal frequency analysis

Motion perception using spatiotemporal frequency analysis

引用

IEEE International Conference on Image Processing

作者： G. Ravichandran M.M. Trivedi Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee Knoxville TN USA

Motion information is extracted by identifying the temporal signature associated with the textured objects in the scene. We present a new computational framework for motion perception. Our methodology considers spatiotemporal frequency (STF) domain analysis to extract the optical flow information. First, we show that a sequence of image frames can be used to extract the motion parameters for the different regions in a dynamic scene using the basic Fourier transform properties in the STF analysis approach. A detailed analytical description of this model to interchangably extract motion and depth parameters and results to highlight their salient properties are presented.< >

关键词： Motion analysis Spatiotemporal phenomena Image motion analysis Data mining Layout Frequency domain analysis Information analysis Fourier transforms Image analysis Image sequence analysis

来源：评论

学校读者我要写书评

暂无评论

On describing a robotic scene

On describing a robotic scene

引用

Intelligent Robots and computer vision VI 1987

作者： Hayward, Vincent Aubry, Stéphane Computer Vision and Robotics Laboratory McGill Research Center for Intelligent Machines 3480 University Street MontréalQCH3A 2A7 Canada

The focus of this article is the presentation of the issues involved in the design of a system able to automatically or semi-automatically construct a global, world-centered model of an industrial scene. In a robotic context, the uses of such a model could be the detection and prevention of collisions, and the interactive off-line programming of manipulators. More generally, such a model can be useful for a variety of automation tasks, including graphic simulation and machining operations sequencing. We first review range acquisition and solid modelling techniques in light of' their respective appropriateness to the above problem. Then we explain how the process of constructing a scene differs from both object recognition and image processing, since we are a priori not interested in isolating distinguishing features of objects but rather in faithfully describing entire scenes. We also discuss how the merging of the several views of the scene is a central element of the scene acquisition process and how great care must be exercised in order to maintain connectivity consistency. Finally, we show that data acquisition, solid modelling as well the actual process of constructing the scene are closely interrelated and that these three issues, all of which are necessary components of the scene description process, should not be considered independently of each other. © 1988 SPIE. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

vision on Wheels: Looking at Driver, Vehicle, and Surround for On-Road Maneuver Analysis

Vision on Wheels: Looking at Driver, Vehicle, and Surround f...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Eshed Ohn-Bar Ashish Tawari Sujitha Martin Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego

Automotive systems provide a unique opportunity for mobile vision technologies to improve road safety by understanding and monitoring the driver. In this work, we propose a real-time framework for early detection of driver maneuvers. The implications of this study would allow for better behavior prediction, and therefore the development of more efficient advanced driver assistance and warning systems. Cues are extracted from an array of sensors observing the driver (head, hand, and foot), the environment (lane and surrounding vehicles), and the ego-vehicle state (speed, steering angle, etc.). Evaluation is performed on a real-world dataset with overtaking maneuvers, showing promising results. In order to gain better insight into the processes that characterize driver behavior, temporally discriminative cues are studied and visualized.

关键词： Vehicles Sensors Cameras Foot Histograms Radar tracking Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

To boost or not to boost? on the limits of boosted trees for object detection

arXiv

引用

arXiv 2017年

作者： Ohn-Bar, Eshed Trivedi, Mohan M. Computer Vision and Robotics Research Laboratory University of California San Diego

We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

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：