Filters








14,127 Hits in 4.0 sec

An Attentional Framework for Stereo Vision

N.D.B. Bruce, J.K. Tsotsos
The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)  
Finally, a stereo attention framework is presented by considering the tenets of an existing attentional architecture that extends naturally to the binocular domain, in conjunction with the connectivity  ...  of units involved in achieving stereo vision.  ...  An Attentional Framework for Stereo Vision The formulation of a framework for attentive processing in stereo vision is achieved in the context of an existing model of attention, the Selective Tuning Model  ... 
doi:10.1109/crv.2005.13 dblp:conf/crv/BruceT05 fatcat:k5uffjgw5zderd4a2vnkcslgyq

A Framework for Obstacles Avoidance of Humanoid Robot Using Stereo Vision

Widodo Budiharto, Jurike Moniaga, Meiliana Aulia, Alvina Aulia
2013 International Journal of Advanced Robotic Systems  
In this paper, we propose a framework for multiple moving obstacles avoidance strategy using stereo vision for humanoid robot in indoor environment.  ...  The contribution of this research is a new method for multiple moving obstacles avoidance strategy with Bayesian approach using stereo vision based on the direction and speed of obstacles.  ...  The framework is shown in fig. 3 : Figure 3 . The use case diagram for our multiple moving obstacles avoidance strategy using stereo vision.  ... 
doi:10.5772/55608 fatcat:4acreoc62ncoxnef5jj6l5rwty

Multiple Moving Obstacles Avoidance of Service Robot using Stereo Vision

Widodo Budiharto, Ari Santoso, Djoko Purwanto, Achmad Jazidie
2011 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
Abstract In this paper, we propose a multiple moving obstacles avoidance using stereo vision for service robots in indoor environments.  ...  To overcome the inaccuracies of vision sensor, Bayesian approach is used for estimate the absense and direction of obstacles.  ...  Figure 10 . 10 An example of framework of face recognition system.  ... 
doi:10.12928/telkomnika.v9i3.733 fatcat:tcabvsubnbatbmvikyh3h6g5t4

Robust Stereoscopic Head Pose Estimation in Human-Computer Interaction and a Unified Evaluation Framework [chapter]

Georg Layher, Hendrik Liebau, Robert Niese, Ayoub Al-Hamadi, Bernd Michaelis, Heiko Neumann
2011 Lecture Notes in Computer Science  
Furthermore, in order to facilitate the evaluation of computational vision results, we present a data generation framework capable of image synthesis under controlled pose conditions using an arbitrary  ...  In this work, we make a step towards the employment of robust computational vision mechanisms to estimate the actor's head pose and thus the direction of his focus of attention.  ...  This research has been supported by a Grant from the Transregional Collaborative Research Center SFB/TRR62 "Companion-Technology for Cognitive Technical Systems" funded by the German Research Foundation  ... 
doi:10.1007/978-3-642-24085-0_24 fatcat:5zte4utfqjeorlm5ng53sgw4fm

Stereoscopic image retargeting based on 3D saliency detection

Junle Wang, Yuming Fang, Manish Narwaria, Weisi Lin, Patrick Le Callet
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
A new 3D visual attention model is designed based on 2D visual feature detection, depth feature detection and the modeling of various viewing bias in stereo vision.  ...  A geometrically consistent seam carving technique is adopted for retargeting stereo image pair.  ...  Therefore, it is not a trivial work to develop new visual attention model for 3D content and integrate the 3D visual attention model into the stereoscopic image retargeting framework.  ... 
doi:10.1109/icassp.2014.6853680 dblp:conf/icassp/WangFNLC14 fatcat:vbhsmernojfqpfpf2e2bki4nsa

Stereoscopic visual saliency prediction based on stereo contrast and stereo focus

Hao Cheng, Jian Zhang, Qiang Wu, Ping An, Zhi Liu
2017 EURASIP Journal on Image and Video Processing  
We propose a visual saliency prediction model for stereoscopic images based on stereo contrast and stereo focus models.  ...  After obtaining the values of the stereo contrast and stereo focus models in parallel, an enhancement based on clustering is performed on both values.  ...  Visual attention enables the discovery of an object or region that efficiently represents a scene and, thus, harnesses complex vision problems, such as scene understanding.  ... 
doi:10.1186/s13640-017-0210-5 fatcat:zg26cy2d3rdmneeczkedf3a3zq

H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry [article]

Baoru Huang, Jian-Qing Zheng, Stamatia Giannarou, Daniel S. Elson
2021 arXiv   pre-print
In this paper, we introduce the H-Net, a deep-learning framework for unsupervised stereo depth estimation that leverages epipolar geometry to refine stereo matching.  ...  For the first time, a Siamese autoencoder architecture is used for depth estimation which allows mutual information between the rectified stereo images to be extracted.  ...  [44] presented a framework that learned stereo matching costs without human supervision, in which the network parameters were updated in an iterative manner and a left-right check was applied to guide  ... 
arXiv:2104.11288v1 fatcat:6txfiwgmqzg5jor3aga2z6onm4

Visually Imbalanced Stereo Matching

Yicun Liu, Jimmy Ren, Jiawei Zhang, Jianbo Liu, Mude Lin
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Understanding of human vision system (HVS) has inspired many computer vision algorithms.  ...  To avoid such collapse, we propose a solution to recover the stereopsis by a joint guided-viewrestoration and stereo-reconstruction framework.  ...  However, little attention has been drawn on the imbalanced condition between the stereo views.  ... 
doi:10.1109/cvpr42600.2020.00210 dblp:conf/cvpr/LiuRZLL20 fatcat:2op5thaezzddvhz6f3wjzdehsa

A Vehicle-Borne Mobile Mapping System Based Framework for Semantic Segmentation and Modeling on Overhead Catenary System Using Deep Learning

Lei Xu, Shunyi Zheng, Jiaming Na, Yuanwei Yang, Chunlin Mu, Debin Shi
2021 Remote Sensing  
Firstly, an enhanced VMMS is designed for accurate data generation. Secondly, an automatic searching method based on a two-level stereo frame is designed to filter the irrelevant non-OCS point cloud.  ...  Then, a deep learning network based on multi-scale feature fusion and an attention mechanism (MFF_A) is trained for semantic segmentation on a catenary facility.  ...  Then, a deep learning network based on multi-scale feature System Based Framework for fusion and an attention mechanism (MFF_A) is trained for semantic segmentation on a catenary Semantic  ... 
doi:10.3390/rs13234939 fatcat:ookfz7r3qbgjvhoxtzzfdu3y3i

Scene Segmentation Assisted by Stereo Vision

Carlo Dal Mutto, Pietro Zanuttigh, Guido M. Cortelazzo, Stefano Mattoccia
2011 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission  
This paper proposes a new framework for scene segmentation where color information is assisted by 3D geometry data, obtained by stereo vision techniques.  ...  Stereo vision systems for 3D reconstruction have been deeply studied and are nowadays capable to provide a reasonably accurate estimate of the 3D geometry of a framed scene.  ...  Section II presents an overall synthesis of the proposed scene segmentation framework. Section II-A reports all the considered stereo algorithms.  ... 
doi:10.1109/3dimpvt.2011.16 dblp:conf/3dim/MuttoZCM11 fatcat:dfnpfnmjd5bvrpcbbzijjbfxpm

Computer Generated Stereoscopic Artwork [article]

Stathis Stavrakis, Margrit Gelautz
2005 Computational Aesthetics in Graphics  
involved in the generation of stereo artwork.  ...  We describe a framework that we use in our stereoscopic image-based non-photorealistic rendering algorithms, but it can be adopted by other single-view artistic image synthesis techniques in order to generate  ...  We would like to thank fine artist Roger Ferragallo for sharing with us his experience on stereoscopic painting.  ... 
doi:10.2312/compaesth/compaesth05/143-149 fatcat:2t6dc7a5uncbph3u2w6cmelpyy

Review of Environment Perception for Intelligent Vehicles

N.Dhamanam, Dr. M.Kathirvelu, T. GovindaRao
2019 Zenodo  
We detail advances in vehicle detection, discussing monocular, stereo vision, and active sensor–vision fusion for on-road vehicle detection.  ...  A special attention is paid to methods for lane and road detection, traffic sign recognition, vehicle tracking, behavior analysis, and scene understanding.  ...  Vision sensor can be grouped as camera, lowlight level night vision, infrared night vision, and stereo vision.  ... 
doi:10.5281/zenodo.3355886 fatcat:wi77szgt5vhj7cxuwo5rj5ztju

Deep Learning for Confidence Information in Stereo and ToF Data Fusion

Gianluca Agresti, Ludovico Minto, Giulio Marin, Pietro Zanuttigh
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
This paper proposes a novel framework for the fusion of depth data produced by a Time-of-Flight (ToF) camera and a stereo vision system.  ...  The machine learning framework estimates the reliability of both data sources at each pixel location.  ...  Calvagno for his support and gratefully acknowledge NVIDIA Corporation for the donation of the GPUs used for this research.  ... 
doi:10.1109/iccvw.2017.88 dblp:conf/iccvw/AgrestiMMZ17 fatcat:rfk5ebzi7vdslhtrf3xulkabfe

Biologically Inspired Vision for Indoor Robot Navigation [chapter]

M. Saleiro, K. Terzić, D. Lobato, J. M. F. Rodrigues, J. M. H. du Buf
2014 Lecture Notes in Computer Science  
It comprises stereo vision for obstacle detection, and object recognition for landmark-based navigation. We employ a novel keypoint descriptor which codes responses of cortical complex cells.  ...  In this paper we present a completely biologically inspired vision system for robot navigation.  ...  and Fast Saliency [3] algorithm for focus of attention.  ... 
doi:10.1007/978-3-319-11755-3_52 fatcat:cqbabb2vrjfw5b2nvt7oirnkqu

Parallax‐based second‐order mixed attention for stereo image super‐resolution

Chenyang Duan, Nanfeng Xiao
2021 IET Computer Vision  
To address this issue, in this work, a parallax-based second-order mixed attention stereo SR network (PSMASSRnet) is proposed to integrate the cross-view information from a stereo image pair for SR.  ...  Most recent methods use the attention mechanism to get stereo correspondence.  ...  of our parallax-based second-order mixed attention stereo SR network for 4� SR.  ... 
doi:10.1049/cvi2.12063 fatcat:mghofhx75zdu3cawc5wxlw3ufy
« Previous Showing results 1 — 15 out of 14,127 results