Filters








484,967 Hits in 6.6 sec

Combining Appearance and Range Based Information for Multi-class Generic Object Recognition [chapter]

Doaa Hegazy, Joachim Denzler
2009 Lecture Notes in Computer Science  
First, a new object category dataset of 2D and range images of different object classes is presented. Second, a new generic object recognition model from range and 2D images is proposed.  ...  The model is able to use either appearance (2D) or range based information or a combination of both of them for multi-class object learning and recognition.  ...  However, the range data of a TOF camera suffer from large amount of noise.  ... 
doi:10.1007/978-3-642-10268-4_87 fatcat:wqgjefxclvdp3ovjbicwieolte

MMM-classification of 3D range data

A. Agrawal, A. Nakazawa, H. Takemura
2009 2009 IEEE International Conference on Robotics and Automation  
This paper presents a method for accurately segmenting and classifying 3D range data into particular object classes.  ...  In addition, rather than processing raw points, we reconstruct polygons from the point data, introducing connectivity to the points.  ...  The authors gratefully acknowledge the contribution of the Ministry of Internal Affairs and Communications.  ... 
doi:10.1109/robot.2009.5152539 dblp:conf/icra/AgrawalNT09 fatcat:bxfytdxa3fawve5dm2rhr6izni

Real-time Object Recognition in Sparse Range Images Using Error Surface Embedding

Limin Shang, Michael Greenspan
2009 International Journal of Computer Vision  
In this work we address the problem of object recognition and localization from sparse range data.  ...  Specifically, we present a new approach to the problems of pose determination, object recognition and object class recognition.  ...  The range data 10: Recognition Result, Real-time. a) Angel b) Zoe c) Gnome d) Big Bird e) Watermelon Kid Figure 6 . 1 : 61 Example of Object Class Recognition 1 Example of Object Class Recognition  ... 
doi:10.1007/s11263-009-0276-3 fatcat:npcqoaxswbefxb5btmigxtqdg4

Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM [chapter]

Rohan Ghosh, Tang Siyi, Mahdi Rasouli, Nitish V. Thakor, Sunil L. Kukreja
2016 Lecture Notes in Computer Science  
These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation  ...  The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.  ...  on aggregated data from successive viewpoints spanning different range of 2D-pose Pose-invariant object recognition for event-based vision with slow-ELM  ... 
doi:10.1007/978-3-319-44781-0_54 fatcat:wup64xpzavdb7pmg67msivnszy

AGA: Attribute-Guided Augmentation

Mandar Dixit, Roland Kwitt, Marc Niethammer, Nuno Vasconcelos
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We demonstrate the utility of our approach on the problems of (1) one-shot object recognition in a transferlearning setting where we have no prior knowledge of the new classes, as well as (2) object-based  ...  As external data, we leverage 3D depth and pose information from the SUN RGB-D dataset.  ...  This work is supported by NSF awards IIS-1208522, CCF-0830535, ECCS-1148870 and a generous donation of GPUs from Nvidia.  ... 
doi:10.1109/cvpr.2017.355 dblp:conf/cvpr/DixitKNV17 fatcat:xf3vpummtjailpjywvqxotil2y

AGA: Attribute Guided Augmentation [article]

Mandar Dixit, Roland Kwitt, Marc Niethammer, Nuno Vasconcelos
2017 arXiv   pre-print
We demonstrate the utility of our approach on the problems of (1) one-shot object recognition in a transfer-learning setting where we have no prior knowledge of the new classes, as well as (2) object-based  ...  As external data, we leverage 3D depth and pose information from the SUN RGB-D dataset.  ...  This work is supported by NSF awards IIS-1208522, CCF-0830535, ECCS-1148870 and a generous donation of GPUs from Nvidia.  ... 
arXiv:1612.02559v2 fatcat:7245k2qjrbgfxhigzxwisu2r5u

Range Loss for Deep Face Recognition with Long-tail [article]

Xiao Zhang, Zhiyuan Fang, Yandong Wen, Zhifeng Li, Yu Qiao
2016 arXiv   pre-print
The optimization objective of range loss is the k greatest range's harmonic mean values in one class and the shortest inter-class distance within one batch.  ...  Contrary to most of the existing works that alleviate this problem by simply cutting the tailed data for uniform distributions across the classes, this paper proposes a new loss function called range loss  ...  The the objective of designing range loss is summarized as: • Range loss should be able to strengthen the tailed data's impact in the training process to prevent poor classes from being submerged by the  ... 
arXiv:1611.08976v1 fatcat:in5pcfkdgvghhijir3qrln2a4u

Multi-class recognition of objects technical condition by classifier based on probabilistic neural network

Nadiia Bouraou, Diana Pivtorak, Sergey Rupich
2017 Eastern-European Journal of Enterprise Technologies  
%) in the range of spread values from 0.005 to 0.07.  ...  efficiency is 100 % in the range of values of the influence parameter spread from 0.005 to 0.1; -with the deviation δ=±9 %, the classifier provides error-free recognition at the spread values in the range  ...  T a v r o v PhD* E-mail: dan.tavrov@i.ua *Department of Applied Mathematics National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" Peremohy ave., 37, Kyiv, Ukraine, 03056 Запропоновано  ... 
doi:10.15587/1729-4061.2017.109968 fatcat:p2znwunvqjas7meztc43zvxape

DESIGNING OF NEW PATTERN CLASSIFIER BASED ON MORPHOLOGICAL PARAMETER

TRIPTY SINGH
2013 Graduate Research in Engineering and Technology  
These are than tested and compared for the template of face and text recognition of facial and textual images database.  ...  Face and text recognition system should be able to automatically detect a face and text in any sample video or images. This involves extraction and analysis of its features.  ...  INTRODUCTION Pattern recognition is the science of making inferences from perceptual data, using tools from statistics, probability, computational geometry, machine learning, signal processing, and algorithm  ... 
doi:10.47893/gret.2013.1010 fatcat:jmwqkae5wvbgndzy6jfh72i4hi

A new paradigm for recognizing 3-D objects from range data

Ruiz-Correa, Shapiro, Meila
2003 Proceedings Ninth IEEE International Conference on Computer Vision  
Most of the work on 3-D object recognition from range data has used an alignment-verification approach in which a specific 3-D object is matched to an exact instance of the same object in a scene.  ...  a hierarchy of classifiers that learn object-class parts and their spatial relationships from examples.  ...  Introduction Over the past two decades, the problem of recognizing free form objects from 3-D range data scenes has been intensively studied in computer vision research due to its prominent relevance to  ... 
doi:10.1109/iccv.2003.1238475 dblp:conf/iccv/Ruiz-CorreaSM03 fatcat:czy6xecluzb7vo4mtih5ka2w5a

Open-Environment Robotic Acoustic Perception for Object Recognition

Shaowei Jin, Huaping Liu, Bowen Wang, Fuchun Sun
2019 Frontiers in Neurorobotics  
In real life, exploring objects is dynamically changing, so it is necessary to develop methods that can recognize all classes of objects in an open environment.  ...  An acoustic dataset is collected, and the feasibility of the method is verified on the dataset, which greatly promotes the recognition of objects in an open environment.  ...  range is larger than the falling range of the known classes.  ... 
doi:10.3389/fnbot.2019.00096 pmid:31824277 pmcid:PMC6883290 fatcat:2azzvd2qczd6xnuypxm37b6x3u

3-D Visual Object Classification with Hierarchical Radial Basis Function Networks [chapter]

F. Schwenker, H. A. Kestler
2001 Studies in Fuzziness and Soft Computing  
Often synthetic images or well prepared data sets ignoring problems which are present at lower processing levels have been used in order to simplify the recognition problem, e.g. the 3-D objects are always  ...  The recognition of a 3-D object consisted of the following three subtasks which will be discussed throughout this chapter: 1. Localization of objects in the camera image.  ...  Acknowledgments The research described here was part of the Collaborative Research Center (SFB 527) and is supported by the German Science Foundation (DFG).  ... 
doi:10.1007/978-3-7908-1826-0_8 fatcat:cjdb6b7kijgqbldf3bwslw7l3i

Object Recognition Based on Three-Dimensional Model [chapter]

Jun Liang, Yanning Zhang, Zenggang Lin, Zhe Guo, Chao Zhang
2012 Lecture Notes in Computer Science  
of cluster classes and increases the recognition rate.  ...  It is a challenging work to achieve viewpoint independent object recognition. A new efficient method of object recognition based on 3D model is proposed in this paper.  ...  This work is supported by School Foundation of Northwestern Polytechnical University (No.JC201122).  ... 
doi:10.1007/978-3-642-31919-8_28 fatcat:ulguci4xcfdn5c6xsomy2wy3qa

A Real-time Hand Gesture Recognition Technique and Its Application to Music Display System

Jun-Yong Lee, Joong-Eun Jung, Ho-Joon Kim
2016 Journal of Automation and Control Engineering  
We have defined a relevance factor which can measure the relevance of a feature to classify the specific pattern classes.  ...  In the paper, we introduce a real-time hand gesture recognition method using a neural network.  ...  ACKNOWLEDGMENT This research was financially supported by the Ministry of Education (MOE) and National Research Foundation of Korea (NRF) through the Human Resource Training Project for Regional Innovation  ... 
doi:10.12720/joace.4.2.177-180 fatcat:yd3lmso56bakdpn5telibwlasq

Semi-Automatic Objects Recognition in Urban Areas Based on Fuzzy Logic

Federico Prandi, Raffaella Brumana, Francesco Fassi
2010 Journal of Geographic Information System  
Three dimensional object extraction and recognition (OER) from geographic data has been definitely one of more important topic in photogrammetry for quite a long time.  ...  The recognition algorithm has been tested with to different data set and different objectives.  ...  However, most of the existing methods for automatic object extraction and recognition from data are just based on the range information and employ parametric methods while object's vagueness behaviour  ... 
doi:10.4236/jgis.2010.22011 fatcat:yytlocu4ajbcpmsm2ekjnrstqi
« Previous Showing results 1 — 15 out of 484,967 results