检索结果-南通市图书馆

Full-viewpoint 3D Space object recognition Based on Kernel Locality Preserving Projections

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2010年第5期23卷 563-572页

作者：孟钢姜志国刘正一张浩鹏赵丹培北京航空航天大学宇航学院图像中心

Space object recognition plays an important role in spatial exploitation and surveillance, followed by two main problems： lacking of data and drastic changes in viewpoints. In this article, firstly, we build a three-dimensional （3D） satellites dataset named BUAA Satellite Image Dataset （BUAA-SID 1.0） to supply data for 3D space object research. Then, based on the dataset, we propose to recognize full-viewpoint 3D space objects based on kernel locality preserving projections （KLPP）. To obtain more accurate and separable description of the objects, firstly, we build feature vectors employing moment invariants, Fourier descriptors, region covariance and histogram of oriented gradients. Then, we map the features into kernel space followed by dimensionality reduction using KLPP to obtain the submanifold of the features. At last, k-nearest neighbor （kNN） is used to accomplish the classification. Experimental results show that the proposed approach is more appropriate for space object recognition mainly considering changes of viewpoints. Encouraging recognition rate could be obtained based on images in BUAA-SID 1.0, and the highest recognition result could achieve 95.87%.

关键词： satellites object recognition three-dimensional image dataset full-viewpoint kernel locality preserving projections

Biological object recognition approach using space variant resolution and pigeon-inspired optimization for UAV

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2017年第10期60卷 1577-1584页

作者： XIN Long XIAN Ning State Key Laboratory of 14rtual Reality Technology and Systems Beihang University Beijing 100191 China

Recognizing the target from a rotated and scaled image is an important and difficult task for computer vision. Visual system of humans has a unique space variant resolution mechanism(SVR) and log-polar transformations(LPT) is a mapping method that is invariant to rotation and scale. Motivated by biological vision, we propose a novel global LPT based template-matching algorithm(GLPT-TM) which is invariant to rotational and scale changes; and with pigeon-inspired optimization(PIO) used to optimize search strategy, a hybrid model of SVR and pigeon-inspired optimization(SVRPIO) is proposed to accomplish object recognition for unmanned aerial vehicles(UAV) with rotational and scale changes of the target. To demonstrate the efficiency, effectiveness and reliability of the proposed method, a series of experiments are carried out. By rotating and scaling the sample image randomly and recognizing the target with the method, the experimental results demonstrate that our proposed method is not only efficient due to the optimization, but effective and accurate in recognizing the target for UAV.

关键词： biological vision space variant resolution mechanism (SVR) log-polar transformations (LPT) pigeon-inspiredoptimization (PIO) object recognition

VFM： Visual Feedback Model for Robust object recognition

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2015年第2期30卷 325-339页

作者：王冲黄凯奇 National Laboratory of Pattern recognition Institute of Automation Chinese Academy of Sciences Beijing 100190 China

object recognition, which consists of classification and detection, has two important attributes for robustness： 1） closeness： detection windows should be as close to object locations as possible, and 2） adaptiveness： object matching should be adaptive to object variations within an object class. It is difficult to satisfy both attributes using traditional methods which consider classification and detection separately; thus recent studies propose to combine them based on confidence contextualization and foreground modeling. However, these combinations neglect feature saliency and object structure, and biological evidence suggests that the feature saliency and object structure can be important in guiding the recognition from low level to high level. In fact, object recognition originates in the mechanism of ＂what＂ and ＂where＂ pathways in human visual systems. More importantly, these pathways have feedback to each other and exchange useful information, which may improve closeness and adaptiveness. Inspired by the visual feedback, we propose a robust object recognition framework by designing a computational visual feedback model （VFM） between classification and detection. In the ＂what＂ feedback, the feature saliency from classification is exploited to rectify detection windows for better closeness; while in the ＂where＂ feedback, object parts from detection are used to match object structure for better adaptiveness. Experimental results show that the ＂what＂ and ＂where＂ feedback is effective to improve closeness and adaptiveness for object recognition, and encouraging improvements are obtained on the challenging PASCAL VOC 2007 dataset.

关键词： object recognition object classification object detection visual feedback

Numerical　Analysis　of　Three-Dimensional　object　recognition　with　Digital　Holography

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

Chinese Physics Letters 2004年第6期21卷 1067-1070页

作者： DINGDe-Hua HEQing-Sheng WANGJian-Gang WUMin-Xian JINGuo-Fan StateKeyLaboratoryofPrecisionMeasurementTechnologyandInstruments TsinghuaUniversityBeijing100084

We describe an intrinsic correlation peak of three-dimensional (3D) pattern recognition, which is higher than that of the two-dimensional (2D) pattern recognition and whose difference can reach up to five orders of magnitude in our numerical simulation. The relationship between the 3D objects and their recognition result is formalized and the comparison between the 3D and 2D pattern recognitions as well as the former's independency of the reconstruction distance is presented. Finally, the augmentation of the 3D pattern recognition sensitivity with the increasing surface complexity of the 3D object is also demonstrated.

关键词： object recognition

A distributed computational cognitive model for object recognition

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

Science China(Information Sciences) 2013年第12期56卷 5-17页

作者： LIU YongJin FU QiuFang LIU Ye FU XiaoLan Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University State Key Lab of Brain and Cognitive Science Institute of Psychology Chinese Academy of Sciences

Based on cognitive functionalities in human vision processing, we propose a computational cognitive model for object recognition with detailed algorithmic descriptions. The contribution of this paper is of two folds. Firstly, we present a systematic review on psychological and neurophysiological studies, which provide collective evidence for a distributed representation of 3D objects in the human brain. Secondly, we present a computational model which simulates the distributed mechanism of object vision pathway. Experimental results show that the presented computational cognitive model outperforms five representative 3D object recognition algorithms in computer science research.

关键词： distributed cognition computational model object recognition human vision system

Optimizing Deep Learning Parameters Using Genetic Algorithm for object recognition and Robot Grasping

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2018年第1期16卷 11-15页

作者： Delowar Hossain Genci Capi Mitsuru Jindai Graduate School of Science and Engineering for Education University of ToyamaToyama 9350343 Department of Mechanical Engineering Hosei UniversityTokyo 184-0002

The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.

关键词： Deep learning(DL) deep belief neural network(DBNN) genetic algorithm(GA) object recognition robot grasping

Spatio-temporal pattern analysis of single-trial EEG signals recorded during visual object recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2011年第12期54卷 2519-2527页

作者： WANG ChangMing 1 , HU XiaoPing 3 , YAO Li 1,2 , XIONG Shi 2 & ZHANG JiaCai 2 1 National Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China 2 College of Information Science and Technology, Beijing Normal University, Beijing 100875, China 3 Biomedical Imaging Technology Center, Emory University/Georgia Institute of Technology, Atlanta 30322, USA National Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Beijing China Biomedical Imaging Technology Center Emory University/Georgia Institute of Technology Atlanta USA College of Information Science and Technology Beijing Normal University Beijing China

object discrimination is a fundamental cognitive function for human brains. In this study, we utilized an analysis approach for single-trial electroencephalography (EEG) to analyze the spatio-temporal activation patterns of visual objects processing in human brains, and attempted to apply it to discriminate different visual objects. The spatial patterns were respectively extracted from scalp EEG and the reconstructed cortical sources, while the experiment participants were perceiving 4 different categories of visual objects (faces, buildings, cats and cars). By classifying the patterns extracted from single-trial EEG, the presented visual objects could be discriminated by a computer, and the classification accuracies may provide a quantitative index to evaluate the spatial differences of the brain activations related to different visual objects. Our results demonstrated that the spatial patterns on both the scalp and the sources levels resulted in higher classification accuracies than chance rate. We also examined the classification results using temporally non-overlapping time intervals of different event-related potential (ERP) components. The temporal changes of classification accuracies may reflect the temporal distribution of the discriminative information in the EEG responses. The present pattern extraction and classification methods may compose a computational model for single-trial EEG data analysis in investigations of the spatio-temporal activation patterns for object recognition. These spatio-temporal patterns in EEG may be useful to identifying the discriminative spatial areas and time stages to improve the accuracies and efficiencies of object discrimination. In addition, investigating and utilizing humans'cognitive mechanisms of object recognition may improve computers' processing efficiency of visual information.

关键词： EEG spatio-temporal pattern object recognition single-trial analysis visual information processing

Salient region detection and segmentation for general object recognition and image understanding

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2011年第12期54卷 2481-2490页

作者： HUANG TieJun 1 , TIAN YongHong 1 , LI Jia 2 & YU HaoNan 11 National Engineering Laboratory for Video Technology, School of Electrical Engineering and Computer Science, Peking University, Beijing 100871, China 2 Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China National Engineering Laboratory for Video Technology School of Electrical Engineering and Computer Science Peking University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open problem. In this paper, we propose a selective attention-driven model for general image understanding, named GORIUM (general object recognition and image understanding model). The key idea of our model is to discover recurring visual objects by selective attention modeling and pairwise local invariant features matching on a large image set in an unsupervised manner. Towards this end, it can be formulated as a four-layer bottom-up model, i.e., salient region detection, object segmentation, automatic object discovering and visual dictionary construction. By exploiting multi-task learning methods to model visual saliency simultaneously with the bottom-up and top-down factors, the lowest layer can effectively detect salient objects in an image. The second layer exploits a simple yet effective learning approach to generate two complementary maps from several raw saliency maps, which then can be utilized to segment the salient objects precisely from a complex scene. For the third layer, we have also implemented an unsupervised approach to automatically discover general objects from large image set by pairwise matching with local invariant features. Afterwards, visual dictionary construction can be implemented by using many state-of-the-art algorithms and tools available nowadays.

关键词： object recognition image understanding visual saliency salient object segmentation visual dictionary

object recognition and Obstacle Avoidance Robot

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Object Recognition and Obstacle Avoidance Robot