Filters








78,936 Hits in 5.1 sec

Attention Architectures for Machine Vision and Mobile Robots [chapter]

Lucas Paletta, Erich Rome, Hilary Buxton
2005 Neurobiology of Attention  
Computer vision systems that are applied for image understanding in real-world environments require the capability to focus operations on task relevant events in an ongoing input stream of visual information  ...  We address successful methodologies on saliency and feature selection, describe attentive systems with respect to object and scene recognition, and review saccadic interpretation under decision processes  ...  Saliency from Feature Selection Saliency of a local image area must be defined on the basis of the specific visual information and, accordingly, on the basis of an appropriate feature detector.  ... 
doi:10.1016/b978-012375731-9/50109-9 fatcat:u33zz74qjnbkfeagryxffx7lve

Mobile product recognition with efficient Bag-of-Phrase visual search

Dajiang Zhang, Kim-Hui Yap, Sinduja Subbhuraam
2014 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP)  
It aims to develop a mobile product recognition and recommendation system where a user can recognize a commercial product of interest by taking a picture of it using the mobile phone, and then search for  ...  This paper presents a mobile product recognition system using bag-of-visual phrase (BoP).  ...  DISCRIMINATIVE VISUAL PHRASE SELECTION In the proposed method, SIFT features are extracted for all images.  ... 
doi:10.1109/isccsp.2014.6877817 dblp:conf/isccsp/ZhangYS14 fatcat:ufgsrez43ngn7j3mnlunse2rgi

Memory-Efficient Image Databases for Mobile Visual Search

David M. Chen, Bernd Girod
2014 IEEE Multimedia  
Acknowledgments We thank the editors and reviewers for their insightful comments and suggestions, which greatly helped to improve this article.  ...  Evaluation for Stanford Mobile Visual Search Dataset We measured the retrieval performance on the publicly available Stanford Mobile Visual Search (SMVS) dataset, 18 which contains 3,300 query images  ...  Bag-of-Visual-Words Histograms Many popular image retrieval systems are based on bag-of-visual-words histograms. 7-10 A codebook of visual words is generated from a sample set of local feature descriptors  ... 
doi:10.1109/mmul.2013.46 fatcat:byn3duemxrffjf6yfdi3tuzaxa

Visual Vocabulary Learning and Its Application to 3D and Mobile Visual Search [article]

Liujuan Cao
2012 arXiv   pre-print
In this technical report, we review related works and recent trends in visual vocabulary based web image search, object recognition, mobile visual search, and 3D object retrieval.  ...  Especial focuses would be also given for the recent trends in supervised/unsupervised vocabulary optimization, compact descriptor for visual search, as well as in multi-view based 3D object representation  ...  [115] further employed the geometrical feature to improve the feature-based method. V. Mobile Visual Search A.  ... 
arXiv:1207.7244v1 fatcat:b6y7yvvcu5davkwh3zuv762qq4

One Click Focus with Eye-in-hand/Eye-to-hand Cooperation

Claire Dune, Eric Marchand, Christophe Leroux
2007 Engineering of Complex Computer Systems (ICECCS), Proceedings of the IEEE International Conference on  
An initialization step is proposed for a hybrid eyein-hand/eye-to-hand grasping system to fullfil this requirement.  ...  Ensuring this line remains horizontal and centered, the mobile camera moves along it to search for the object. 1) Focusing on the epipolar line: Visual servoing is a robotic control based on visual features  ...  the initialization of the feature depth in Simultaneous Localization and Mapping issue [3] .  ... 
doi:10.1109/robot.2007.363690 dblp:conf/icra/DuneML07 fatcat:kwadikvfvbgb3okcda4tkxlxu4

Top-down Spatial Attention for Visual Search: Novelty Detection-Tracking Using Spatial Memory with a Mobile Robot

Nevrez Imamoglu, Enrique Dorronzoro, Masashi Sekine, Kahori Kita, Wenwei Yu
2014 Advances In Image and Video Processing  
Recent color and depth image based visual search methods can help to handle part of the problems, such as changing illumination, occlusion, and etc. but these methods generally use large amount of training  ...  The main challenges in such daily monitoring application, thus in visual search, are that the robot should track the subject successfully in several severe varying conditions.  ...  for local depth data depth k X of Kinect sensor.  ... 
doi:10.14738/aivp.25.556 fatcat:i26glmfecje73lubb2xonvxusi

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Gait Recognition based on Local Motion Feature Selection Multi-View Structure Computation without Explicitly Estimating Motion Li, Hongsheng Object Matching with a Locally Affine-Invariant Constraint  ...  to Support Real-Time Graphical Instruction for Student Who Have Visual Impairments Oliver, Kenton Free-Shape Subwindow Search for Object Localization Workshop: Feature Matching In Underwater Environments  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

A Target Searching Method of Mobile Robot Based on Scene Complexity

Xiao-Feng Jin
2012 2012 Second International Conference on Instrumentation, Measurement, Computer, Communication and Control  
a novel target searching method based on scene complexity was proposed.  ...  task, and a novel target searching method based on scene complexity was proposed.  ...  Here, target model has been simplified as Harris -SIFT local invariant feature [13] .  ... 
doi:10.1109/imccc.2012.374 fatcat:hu7fwkl7jnf7zeevs2up5zg2cy

Mobile Robot Simultaneous Localization and Mapping Based on a Monocular Camera

Songmin Jia, Ke Wang, Xiuzhi Li
2016 Journal of Robotics  
This paper proposes a novel monocular vision-based SLAM (Simultaneous Localization and Mapping) algorithm for mobile robot.  ...  In the tracking thread, a ground feature-based pose estimation method is employed to initialize the algorithm for the constraint moving of the mobile robot.  ...  For the outlier measurement of triangulated features' depth, a Bayesian filter was used to estimate the depth at feature locations.  ... 
doi:10.1155/2016/7630340 fatcat:udba7l2qm5c45drafo2vr2w5ma

Context-aware vocabulary tree for mobile landmark recognition

Tao Chen, Shijian Lu, Jiayuan Fan
2015 Journal of Visual Communication and Image Representation  
For most existing mobile landmark recognition works, the context information (GPS or direction) is mainly used to reduce the search space in a heuristic and insufficient manner.  ...  This paper presents an effective approach that incorporates contextual information into vocabulary tree learning for mobile landmark recognition.  ...  During the offline stage, the visual local features such as SIFT are first extracted from the captured image.  ... 
doi:10.1016/j.jvcir.2015.05.002 fatcat:t7kcev64tfec5ixg7epn5kla2u

Dense reconstruction on-the-fly

A. Wendel, M. Maurer, G. Graber, T. Pock, H. Bischof
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
The distributed reconstruction pipeline is based on state-of-the-art approaches to visual SLAM and variational depth map fusion, and is designed to exploit the individual capabilities of the system components  ...  Results are visualized in real-time on a tablet interface, which gives the user the opportunity to interact.  ...  We thank NVIDIA for providing a Tegra3 prototype tablet and Ascending Technologies for providing thermal imagery.  ... 
doi:10.1109/cvpr.2012.6247833 dblp:conf/cvpr/WendelMGPB12 fatcat:gwjfod7mtbga7luicrlucw6qla

3D Scene Mesh from CNN Depth Predictions and Sparse Monocular SLAM

Tomoyuki Mukasa, Jiu Xu, Stenger Bjorn
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
We further propose a system architecture suitable for mobile devices, where feature tracking and CNN-based depth prediction modules are separated, and only the former is run on the device.  ...  In this paper, we propose a novel framework for integrating geometrical measurements of monocular visual simultaneous localization and mapping (SLAM) and depth prediction using a convolutional neural network  ...  ., feature-based monocular visual SLAM and CNN-based depth prediction.  ... 
doi:10.1109/iccvw.2017.112 dblp:conf/iccvw/MukasaXS17 fatcat:tdnufowpo5hb3lr4p32aueuxfq

GPS-DENIED GEO-LOCALISATION USING VISUAL ODOMETRY

Ashish Gupta, Huan Chang, Alper Yilmaz
2016 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The primary method for geo-localization is based on GPS which has issues of localization accuracy, power consumption, and unavailability.  ...  A search for the trajectory in real time in the graph yields the geo-location of the mobile platform. Our approach uses a simple visual sensor and it has a low memory and computational footprint.  ...  Figure 6 : 6 Visual Odometry3.2.1 Feature detection and tracking Feature extraction and tracking is the essential work for vision-based mapping and trajectory estimation.  ... 
doi:10.5194/isprs-annals-iii-3-263-2016 fatcat:2fp6px63bnf6xlisck633vrdye

GPS-DENIED GEO-LOCALISATION USING VISUAL ODOMETRY

Ashish Gupta, Huan Chang, Alper Yilmaz
2016 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The primary method for geo-localization is based on GPS which has issues of localization accuracy, power consumption, and unavailability.  ...  A search for the trajectory in real time in the graph yields the geo-location of the mobile platform. Our approach uses a simple visual sensor and it has a low memory and computational footprint.  ...  Figure 6 : 6 Visual Odometry3.2.1 Feature detection and tracking Feature extraction and tracking is the essential work for vision-based mapping and trajectory estimation.  ... 
doi:10.5194/isprsannals-iii-3-263-2016 fatcat:forvulfavzdyrjbaza4kywv7wm

Predictive Control-Based Completeness Analysis and Global Calibration of Robot Vision Features

Jingjing Lou, Akshi Kumar
2021 Computational Intelligence and Neuroscience  
This paper provides an in-depth study and analysis of robot vision features for predictive control and a global calibration of their feature completeness.  ...  The task is guaranteed to be completely based on a robust calibration-free visual serving strategy based on interference observer that is proposed to complete the visual serving task with high performance  ...  as examples to investigate how to select, extract, and use the complete feature set for different visual servo tasks, respectively.  ... 
doi:10.1155/2021/7241659 pmid:34925495 pmcid:PMC8677366 fatcat:ripbxkqbq5ehbpsddeup6koiwm
« Previous Showing results 1 — 15 out of 78,936 results