Filters








175,779 Hits in 5.8 sec

Object class and instance recognition on rgb-d data

Viktor Seib, Susanne Christ-Friedmann, Susanne Thierfelder, Dietrich Paulus, Branislav Vuksanovic, Jianhong Zhou, Antanas Verikas
2013 Sixth International Conference on Machine Vision (ICMV 2013)  
The object instance recognition algorithm was further evaluated during the RoboCup world championship 2012 in Mexico-City and won the first place in the Technical Challenge of the @Home-league.  ...  Both algorithms perform well on publicly available object databases as well as on acquired data with an RGB-D camera.  ...  The object instance recognition approach was evaluated on test data from the database presented in [19] . All images in this database have a resolution of 640×480 pixels.  ... 
doi:10.1117/12.2049915 fatcat:pv5fg4kv4zgwnodv4b3rt7x6l4

Neural Network Fusion of Color, Depth and Location for Object Instance Recognition on a Mobile Robot [chapter]

Louis-Charles Caron, David Filliat, Alexander Gepperth
2015 Lecture Notes in Computer Science  
We present a light-weight scene segmentation and object instance recognition algorithm using an RGB-D camera and demonstrate it in a semantic mapping experiment.  ...  Our results demonstrate that state of the art recognition rates on a database does not guarantee performance in a real world experiment.  ...  Acknowledgment The authors thank Jérôme Béchu for his help in the development of the visualization software.  ... 
doi:10.1007/978-3-319-16199-0_55 fatcat:pzswcyaknfguzel6lnnhasmo6q

Multidimensional indexing for recognizing visual shapes

A. Califano, R. Mohan
1994 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image.  ...  Model acquisition time is linear to cubic in the number of object features.  ...  Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image.  ... 
doi:10.1109/34.277591 fatcat:ihf2rphpezc2nhk3dlqcbkbneq

Multidimensional Indexing for Recognizing Visual Shapes [chapter]

Andrea Califano, Rakesh Mohan
1992 Visual Form  
Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image.  ...  Model acquisition time is linear to cubic in the number of object features.  ...  Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image.  ... 
doi:10.1007/978-1-4899-0715-8_12 fatcat:2h6gjsigzvbmpj5mwiers3fpkm

View-Based 3D Objects Recognition with Expectation Propagation Learning [chapter]

Adrien Bertrand, Faisal R. Al-Osaimi, Nizar Bouguila
2016 Lecture Notes in Computer Science  
Those objects are in our case from a view-based 3D models database that we have assembled.  ...  View-based 3D Objects Recognition with Expectation Propagation Learning In this thesis, we present an improvement on the Expectation Propagation learning framework, specifically various enhancements on  ...  Dirichlet Mixture Model Integration of these two models within an efficient view-based 3D object recognition framework Thesis overview The main objective of this thesis, presented in this document  ... 
doi:10.1007/978-3-319-50832-0_35 fatcat:gm4kbmutvrhw5ma2vusqkh5nr4

Real-time monocular object SLAM

Dorian Gálvez-López, Marta Salas, Juan D. Tardós, J.M.M. Montiel
2016 Robotics and Autonomous Systems  
We present a real-time object-based SLAM system that leverages the largest object database to date.  ...  based on bags of binary words, which provides live detections with a database of 500 3D objects.  ...  Simultaneously, object recognition is performed on as many frames as possible to search for known objects stored in an object model database.  ... 
doi:10.1016/j.robot.2015.08.009 fatcat:sxtxwwanqracrj5vrbwjwlfqny

Real-time Monocular Object SLAM [article]

Dorian Gálvez-López, Marta Salas, Juan D. Tardós, J. M. M. Montiel
2015 arXiv   pre-print
We present a real-time object-based SLAM system that leverages the largest object database to date.  ...  based on bags of binary words, which provides live detections with a database of 500 3D objects.  ...  Simultaneously, object recognition is performed on as many frames as possible to search for known objects stored in an object model database.  ... 
arXiv:1504.02398v1 fatcat:ym7gd46dkvdfhgzzmfbxykoaxq

GA-based learning for a model-based object recognition system

R. Soodamani, Z.Q. Liu
2000 International Journal of Approximate Reasoning  
Performance enhancement is achieved by incorporating an o-line learning mechanism using genetic algorithm in the feedback path of the recognition system. Ó  ...  The objective function aims at enhancing recognition performance in terms of maximizing the degree of discrimination among classes.  ...  In this test, the system showed its ability to recognize the correct instances corresponding to an object model and reject instances corresponding to the rest of the models within the same database.  ... 
doi:10.1016/s0888-613x(99)00036-5 fatcat:gpiwpubgufb5hgoyoefcxht4uu

Object Recognition for the Internet of Things [chapter]

Till Quack, Herbert Bay, Luc Van Gool
2008 Lecture Notes in Computer Science  
At the core of our system lies an object recognition method, which identifies an object from a query image through multiple recognition stages, including local visual features, global geometry, and optionally  ...  Experiments evaluate the performance of our approach in both application scenarios and show good recognition results under challenging conditions.  ...  The recognition rate with a modern phone reaches 100%, the lower quality camera in the older 6230 model results in lower recognition rates.  ... 
doi:10.1007/978-3-540-78731-0_15 fatcat:ajznvurncjcxpaszc23hwcugbu

Developing a STEP-Compliant Database System in Supporting Product Life Cycle Applications

Yusri Yusof, Chen Wong Keong, D. Zhang, B. Zi, G. Cui, H. Ding
2016 MATEC Web of Conferences  
Currently, most of CAD systems have the ability to generate geometrical and topological data in STEP file format.  ...  This developed STEP-compliant database management system has shown its ability to convert this generated STEP file format to database format, which is more suitable for the downstream of manufacturing  ...  Acknowledgment The work reported in this paper has been supported by Research Fund of Universiti Tun Hussein Onn Malaysia (UTHM), and scholarship for Doctoral Program of Ministry of Education (MOE) of  ... 
doi:10.1051/matecconf/20167704002 fatcat:csu7ucvgyzbydgqcwklh2jrbp4

Object Recognition Approach Based on Generalized Hough Transform and Color Distribution Serving in Generating Arabic Sentences

Nada Farhani, Naim Terbeh, Mounir Zrigui
2019 Zenodo  
In this paper, we will be interested in the recognition of objects. The classical Hough Transform (HT) presented a tool for detecting straight line segments in images.  ...  The recognition of the objects contained in images has always presented a challenge in the field of research because of several difficulties that the researcher can envisage because of the variability  ...  an object, then a comparison between these characteristics and the characteristics of the models stored in a database will take place.  ... 
doi:10.5281/zenodo.3299705 fatcat:wrczd2v6grchzjfpqxa23ucmke

A Discriminative Framework for Texture and Object Recognition Using Local Image Features [chapter]

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
2006 Lecture Notes in Computer Science  
This implicitly assumes that an object can contain at most one instance of each part.  ...  Summary and Future Work In this chapter, we have presented an approach to texture and object recognition that uses a visual dictionary of textons or object parts in combination with a discriminative maximum  ... 
doi:10.1007/11957959_22 fatcat:hikapmxufjdbbeypuzljlmbgwm

Content-based indexing of images and video

A. Pentland
1997 Philosophical Transactions of the Royal Society of London. Biological Sciences  
SU M M A RY By representing image content using probabilistic models of an object's appearance we can obtain semantics-preserving compression of the image data.  ...  Such compact representations of an image's salient features allow rapid computer searches of even large image databases.  ...  For instance, one cannot reconstruct an image region from its moment invariants or its colour histogram. In contrast, the models we present use coe¤cients which allow reconstruction.  ... 
doi:10.1098/rstb.1997.0111 pmid:9304695 pmcid:PMC1692008 fatcat:tqtyk56vqrd7nnc73u67mrxonm

Personalized Health Framework for Visually Impaired

Megha Rathi, Shruti Sahu, Ankit Goel, Pramit Gupta
2022 Informatica (Ljubljana, Tiskana izd.)  
Broadly, the application consists of the following modules: object recognition in immediate surroundings using region-based convolutional neural networks, disease prediction with the help of symptoms,  ...  This research work discusses an easily-operable and affordable android application designed to aid the visually impaired in healthcare management.  ...  error in top 5 models of the object recognition & image classification task of ImageNet Large Scale Visual Recognition [6] .  ... 
doi:10.31449/inf.v46i1.2934 dblp:journals/informaticaSI/RathiSGG22 fatcat:hivu2tuyzjcrxklmg2us4ypqny

Viewpoint detection models for sequential embodied object category recognition

David Meger, Ankur Gupta, James J Little
2010 2010 IEEE International Conference on Robotics and Automation  
Finally, we illustrate the applicability of our method as a component of a completely autonomous visual recognition platform that has previously been demonstrated in an object category recognition competition  ...  Our learning procedure has been evaluated using an exhaustive multiview category database recently collected for multiview category recognition research.  ...  All results are averages over 160 random selections of an object instance and starting viewpoint.  ... 
doi:10.1109/robot.2010.5509703 dblp:conf/icra/MegerGL10 fatcat:xkeoqjzmbfdrjaby3urlzr34p4
« Previous Showing results 1 — 15 out of 175,779 results