检索结果-南通市图书馆

Towards reliable object representation via sparse directional patches and spatial center cues

FUNDAMENTAL RESEARCH 2025年第1期5卷 354-359页

作者： Jian, Muwei Yu, Hui Shandong Univ Finance & Econ Sch Comp Sci & Technol Jinan 250014 Peoples R China Univ Portsmouth Sch Creat Technol Portsmouth 200021 Hants England

In the process of image understanding, the human visual system (HVS) performs multiscale analysis on various objects. HVS primarily focuses on marginally conspicuous image patches located within or around distinct objects rather than scanning the image pixels point by point. Inspired by the HVS mechanism, in this paper, we aimed to describe and exploit multiscale decomposition-based patch detection models for automatic visual feature representation and object localization in images. Our investigation into mimicking and modeling the HVS to capture conspicuous sparse patches and their spatial distribution clues makes a profound contribution to the automatic comprehension and characterization of images by machines. This study demonstrates that the sparse patch-based visual representation with spatial center cues is intrinsically tolerant to object positioning and understanding beyond object variations in spatial position, multiresolution, and chrominance, which has significant implications for many vision-based automatic object grabbing and perception applications, such as robotics, human -machine interaction, and unmanned aerial vehicles (UAVs).

关键词： Multiscale analysis Image patches Visual perception Shearlet transform object representation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Local structured representation for generic object detection

引用

Frontiers of Computer Science 2017年第4期11卷 632-648页

作者： Junge ZHANG Kaiqi HUANG Tieniu TAN Zhaoxiang ZHANG Center for Research on Intelligent Perception and Computing Chinese Academy of Sciences Beijing 100190 China Research Center lbr Brain-inspired Intelligence Chinese Academy of Sciences Beijing 100190 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Structure information plays an important role in both object recognition and detection. This paper studies what visual structure is and addresses the problem of struc- ture modeling and representation from two aspects： visual feature and topology model. Firstly, at feature level, we pro- pose Local Structured Descriptor to capture the object＇s local structure effectively, and develop the descriptors from shape and texture information, respectively. Secondly, at topology level, we present a local strnctured model with a boosted fea- ture selection and fusion scheme. All experiments are conducted on the challenging PASCAL Visual object Classes （VOC） datasets from VOC2007 to VOC2010. Experimental results show that our method achieves very competitive performance.

关键词： Local Structured Descriptor Local StructuredModel object representation object Structure object De-tection PASCAL VOC

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A system of robotic grasping with experience acquisition

引用

Science China(Information Sciences) 2014年第12期57卷 18-28页

作者： GUO Di SUN FuChun LIU ChunFang State Key Laboratory of Intelligence Technology and Systems Department of Computer Science and TechnologyTsinghua Univerisity

Robotic grasping has played a fundamental role in the robotic manipulation,while grasping an unknown object is still a challenge.A successful grasp is largely determined by the object representation and the corresponding grasp planning *** the help of RGBD camera,the point cloud of the object can be obtained ***,the large amount of point cloud is often unorganized with some inevitable *** may result in the geometry of the object imprecise and lead to some poor grasp *** this paper,a parametric model—superquadric is chosen to represent the shape of an *** firstly recover the superquadric of an object from the raw point cloud in a single view with conjugate gradient *** a force-closure grasp planning strategy is applied to this object to obtain stable grasp *** we store the grasp parameters as grasp experience in a grasp dataset which can be used for future grasping *** performance of the proposed grasping system is represented both in simulation and actual experiment scenario successfully.

关键词： object representation grasp planning experience acquisition point cloud superquadric recovery force closure grasp

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

腹侧视觉通路中的物体范畴特异性表征是否依赖于视觉经验和输入通道?(英文)

腹侧视觉通路中的物体范畴特异性表征是否依赖于视觉经验和输入通...

引用

第一届全国神经动力学学术会议

作者：贺晨曦 Marius V.Peelen 韩在柱林楠 Alfonso Caramazza 毕彦超认知神经科学与学习国家重点实验室北京师范大学 Center for Mind/Brain Sciences University of Trento Department of Psychology Harvard University

The principles that determine the organization of object representation in ventral temporal cortex (VTC) remain elusive. At one extreme, it could be proposed that the observed organization is fully determined by visual processing factors and therefore depends primarily on visual experience. Alternatively, the organization could also be shaped by nonvisual factors such as down-stream computational constraints. On this view, visual experience would not exclusively determine the organization of object representation in VTC. Here, we explore the organization of animate and inanimate object domains in VTC in total absence of visual experience. We tested 14 congenitally blind and matched sighted participants on two auditory experiments involving three object categories: animals, tools, and nonmanipulable objects. Sighted participants additionally participated in picture-viewing experiments. Both blind and sighted participants showed selectivity for large nonmanipulable objects in medial VTC, relative to animals and tools. This region overlapped with the scene-selective parahippocampal place area localized in the sighted group. The picture-viewing data in the sighted revealed additional selectivity for animals in lateral VTC, but this selectivity did not generalize to the auditory experiments in either group, suggesting that the animate-inanimate organization of VTC may be specific to the visual modality. Together these results show that the object domain organization of VTC is highly similar in blind and sighted performing auditory tasks. We conclude that the large-scale organization of high-order visual cortex may be shaped in part by down-stream computational constraints.

关键词： domain specific visual experience congenitally blind ventral temporal cortex object representation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：