Filters








44 Hits in 8.6 sec

Attention-driven object detection and segmentation of cluttered table scenes using 2.5D symmetry

Ekaterina Potapova, Karthik M. Varadarajan, Andreas Richtsfeld, Michael Zillich, Markus Vincze
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
The task of searching and grasping objects in cluttered scenes, typical of robotic applications in domestic environments requires fast object detection and segmentation.  ...  Attentional mechanisms provide a means to detect and prioritize processing of objects of interest.  ...  CONCLUSION AND FUTURE WORK In this paper we proposed a novel attention-driven algorithm for cluttered table scene segmentation.  ... 
doi:10.1109/icra.2014.6907584 dblp:conf/icra/PotapovaVRZV14 fatcat:rhp3dcsspvcb5o7ywyseatmkbi

Local 3D Symmetry for Visual Saliency in 2.5D Point Clouds [chapter]

Ekaterina Potapova, Michael Zillich, Markus Vincze
2013 Lecture Notes in Computer Science  
The estimation of symmetry saliency maps is done on different scales to detect objects of various sizes. For evaluation a Winner-Take-All neural network is used to calculate attention points.  ...  ., attract attention, but complete objects do. Symmetry is a feature of many man-made and also natural objects and has thus been identified as a candidate for attentional operators.  ...  It means that after all relatively big objects were detected in cluttered scenes, smaller objects were ignored.  ... 
doi:10.1007/978-3-642-37331-2_33 fatcat:5qdaf25q4zcifhnp5ooro7rcpi

3D attention-driven depth acquisition for object identification

Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or, Baoquan Chen
2016 ACM Transactions on Graphics  
The effectiveness of our method is demonstrated on an autonomous robot (PR) that explores a scene and identifies the objects to construct a 3D scene model.  ...  Fine-grained shape identification demands a meticulous series of observations attending to varying views and parts of the object of interest.  ...  Acknowledgements We thank the anonymous reviewers for their valuable comments and suggestions.  ... 
doi:10.1145/2980179.2980224 fatcat:wrvfjdz54bdnfmh5mui3itjnt4

Efficient inverse graphics in biological face processing

Ilker Yildirim, Mario Belledonne, Winrich Freiwald, Josh Tenenbaum
2020 Science Advances  
Vision not only detects and recognizes objects, but performs rich inferences about the underlying scene structure that causes the patterns of light we see.  ...  The model fits both behavioral and neural data better than state-of-the-art computer vision models, and suggests an interpretable reverse-engineering account of how the brain transforms images into percepts  ...  They can be deployed in parallel or in series (using attention) to parse out multiple objects in a scene (17) .  ... 
doi:10.1126/sciadv.aax5979 pmid:32181338 pmcid:PMC7056304 fatcat:zbec5hkntjb2hpc4q3tdwwrf2a

How Do You Connect Moving Dots? Insights from User Studies on Dynamic Network Visualizations [chapter]

Michael Smuc, Paolo Federico, Florian Windhager, Wolfgang Aigner, Lukas Zenk, Silvia Miksch
2013 Handbook of Human Centric Visualization  
The second one addresses the avoidance of visual clutter, or at least its moderation.  ...  , changes caused by user interactions, and changes of analytical perspectives.  ...  In scene perception, top-down and bottom-up influences control where one looks [18, 46] . Bottom-up influences are stimulus-driven, whereas topdown influences are viewer-driven.  ... 
doi:10.1007/978-1-4614-7485-2_25 fatcat:7m46p7qyezc4necyz6cphvexc4

Efficient inverse graphics in biological face processing [article]

Ilker Yildirim, Winrich Freiwald, Joshua Tenenbaum
2018 bioRxiv   pre-print
The model also fits qualitatively better than state-of-the-art computer vision models, and suggests an interpretable reverse-engineering account of how images are transformed into scene percepts in the  ...  The visual system must not only recognize and localize objects, but perform much richer inferences about the underlying causes in the world that give rise to observed sense data.  ...  They be deployed in parallel or in series (using attention) to parse out multiple objects in a scene 24, 63-66 .  ... 
doi:10.1101/282798 fatcat:3gqbq3hguvh7zf76aemvssws5m

An experimental study of four variants of pose clustering from dense range data

Ulrich Hillenbrand, Alexander Fuchs
2011 Computer Vision and Image Understanding  
data from a public database of models and cluttered scenes.  ...  For data of sufficient quality, however, sampling points with normals is more efficient; this is most evident when detecting objects in cluttered scenes.  ...  Acknowledgments This work has been partially funded by the German Federal Ministry of Education and Research as part of the integrated project Lynkeus (www.lynkeus-3d.de).  ... 
doi:10.1016/j.cviu.2011.06.007 fatcat:dq5iv37tifh4ha6yhz4yzam6ue

iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos [article]

Aron Monszpart, Paul Guerrero, Duygu Ceylan, Ersin Yumer, Niloy J. Mitra
2018 arXiv   pre-print
Hence, we exploit the correlation between scene object arrangement and motions performed in that scene in both directions: first, typical motions performed when interacting with objects inform us about  ...  We present iMapper, a data-driven method that focuses on identifying human-object interactions, and jointly reasons about objects and human movement over space-time to recover both a plausible scene arrangement  ...  This classification is then used to extract depth layers for the scene yielding a 2.5D representation.  ... 
arXiv:1806.07889v1 fatcat:dt25djebsvcf3ek5swwpqyfvqy

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art [article]

Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
2021 arXiv   pre-print
, scene understanding, and end-to-end learning for autonomous driving.  ...  Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes.  ...  Mitzel and Leibe [469] extract observations of objects by segmenting the scene using depth from stereo.  ... 
arXiv:1704.05519v3 fatcat:xiintiarqjbfldheeg2hsydyra

A Novice Guide towards Human Motion Analysis and Understanding [article]

Ahmed Nabil Mohamed
2015 arXiv   pre-print
Human motion analysis and understanding has been, and is still, the focus of attention of many disciplines which is considered an obvious indicator of the wide and massive importance of the subject.  ...  Sixth, we examine many of the most cited and recent reviews in the field that have been published during the past two decades to reveal various approaches used for implementing different stages of the  ...  His three stages of vision for object recognition are: 1-primal sketch of the visual scene (which detects image intensity changes and identify primitives such as blobs, edges, boundaries, etc), 2-2.5D  ... 
arXiv:1509.01074v1 fatcat:kpqf277iw5f2bmlmog2ya2awci

Optimal Model Fitting for Building Reconstruction From Point Clouds

Wenyuan Zhang, Zhixin Li, Jie Shan
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Conventional building modeling methods often rely on successive roof plane segmentation and fitting.  ...  We propose an optimal model fitting approach that holistically determines all of its parameters from segmented point cloud data.  ...  The segmented building point clouds are reconstructed using 2.5D dual contouring method.  ... 
doi:10.1109/jstars.2021.3110429 fatcat:wyj5zvwyyvelfgeoaab4vep4se

Glyph-based Visualization: Foundations, Design Guidelines, Techniques and Applications [article]

Rita Borgo, Johannes Kehrer, David H. S. Chung, Eamonn Maguire, Robert S. Laramee, Helwig Hauser, Matthew Ward, Min Chen
2012 Eurographics State of the Art Reports  
and implementation techniques, and surveying the use of glyph-based visualization in many applications.  ...  This state of the art report focuses on glyph-based visualization, a common form of visual design where a data set is depicted by a collection of visual objects referred to as glyphs.  ...  [IG98] use halos to emphasize discontinuity in depth and to draw the users attention towards objects.  ... 
doi:10.2312/conf/eg2013/stars/039-063 fatcat:72lte7n3crb5ncclsde3bb4jsq

Diverse Visualization Techniques and Methods of Moving-Object-Trajectory Data: A Review

Jing He, Haonan Chen, Yijin Chen, Xinming Tang, Yebin Zou
2019 ISPRS International Journal of Geo-Information  
study the spatiotemporal conditions of the entire trajectory set and microscopically analyze the individual movement of each trajectory; such methods are widely used in screen display and flat mapping  ...  of visualizing trajectory data and mining hidden information.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijgi8020063 fatcat:fjd5jjfrhncfpowutovxxiyhpe

Computational Support for Sketching in Design: A Review

Gabe Johnson, Mark D. Gross, Jason Hong, Ellen Yi-Luen Do
2007 Foundations and Trends® in Human–Computer Interaction  
First, we describe the practical basis of sketching -why people sketch, what significance it has in design and problem solving, and the cognitive activities it supports.  ...  Computational support for sketching is an exciting research area at the intersection of design research, human-computer interaction, and artificial intelligence.  ...  What to recognize 4.2 Sketches may represent objects (e.g. tables and chairs) and spatial or functional relationships between those objects (e.g. chairs positioned around table perimeter).  ... 
doi:10.1561/1100000013 fatcat:5r74v4r56nasdedplfnemebpw4

A model of computation and representation in the brain

James S. Albus
2010 Information Sciences  
In sensory-processing areas of the brain, CCU processes enable focus of attention, segmentation, grouping, and classification.  ...  CCU frame pointers also link objects and events to class prototypes and overlay them with meaning and emotional values.  ...  To understand complex dynamic scenes, the vision system must be able to quickly and reliably segment objects from the background.  ... 
doi:10.1016/j.ins.2009.12.031 fatcat:elx5lctcuna7bkx4iunglxkpsi
« Previous Showing results 1 — 15 out of 44 results