Filters








979 Hits in 2.7 sec

GeoS: Geodesic Image Segmentation [chapter]

Antonio Criminisi, Toby Sharp, Andrew Blake
2008 Lecture Notes in Computer Science  
This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data.  ...  Numerous results on interactive and automatic segmentation of photographs, video and volumetric medical image data are presented.  ...  (a) Two input images. (b) unaries (from user strokes); (c) GeoS mean segmentation with no contrast.  ... 
doi:10.1007/978-3-540-88682-2_9 fatcat:qjnfzheufvarhertqd6soek5e4

Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement [article]

Da Chen, Jian Zhu, Xinxin Zhang, Minglei Shu, Laurent D. Cohen
2021 arXiv   pre-print
Experimental results prove that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.  ...  Minimal paths are regarded as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and the well-established numerical solutions such as fast marching  ...  image segmentation issues.  ... 
arXiv:2008.06909v4 fatcat:xltfsff6ineszmvnhtlmdk77gi

A Convex Geodesic Selective Model for Image Segmentation

Michael Roberts, Ke Chen, Klaus L. Irion
2018 Journal of Mathematical Imaging and Vision  
Selective segmentation is an important application of image processing.  ...  In contrast to global segmentation in which all objects are segmented, selective segmentation is used to isolate specific objects in an image and is of particular interest in medical imaging -- permitting  ...  Row 2 shows the original image with one marker point, the normalised geodesic distance map and the final segmentation result.  ... 
doi:10.1007/s10851-018-0857-2 fatcat:u6ygncaehjaujp4peqo4xsxv6q

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

Guotai Wang, Maria A. Zuluaga, Wenqi Li, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sebastien Ourselin, Tom Vercauteren
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications.  ...  We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images.  ...  Let i be a pixel in an image I, then the unsigned geodesic distance from i to the scribble set SðS 2 fS f ; S b gÞ is: Gði; S; IÞ ¼ min j2S D geo ði; j; IÞ (1) D geo ði; j; IÞ ¼ min p2P i;j Z 1 0 krIðpðsÞÞ  ... 
doi:10.1109/tpami.2018.2840695 pmid:29993532 pmcid:PMC6594450 fatcat:u4ljunhfarclzlmlipbprvdi2e

Image Segmentation with Elastic Shape Priors via Global Geodesics in Product Spaces

T. Schoenemann, F.R. Schmidt, D. Cremers
2008 Procedings of the British Machine Vision Conference 2008  
It is based on finding a globally optimal geodesic in the product space spanned by the image and the prior contour. To this end a branch-and-bound scheme is combined with shortest path techniques.  ...  We propose an efficient polynomial time algorithm to match an elastically deforming shape to an image.  ...  Global Geodesics vs. Ratio Minimizers in Tracking and Image Segmentation In this section we evaluate the proposed method for shape-based tracking and image segmentation.  ... 
doi:10.5244/c.22.28 dblp:conf/bmvc/SchoenemannSC08 fatcat:6lcndfglfbdztje5x5aeszfhya

Computerized tongue image segmentation via the double geo-vector flow

Miao-Jing Shi, Guo-Zheng Li, Fu-Feng Li, Chao Xu
2014 Chinese Medicine  
Third, a double geo-vector flow (DGF) was proposed to detect the tongue edge and segment the tongue region in the image, such that the geodesic flow was evaluated in the lower part, and the geo-gradient  ...  segmentation.  ...  Third, the DGF was proposed to detect the tongue edge and segment the tongue region in the image, such that the geodesic flow was evaluated in the under part, and the Geo-GVF was evaluated in the upper  ... 
doi:10.1186/1749-8546-9-7 pmid:24507094 pmcid:PMC3922256 fatcat:tqyaahnw2rgsphqbrlkgw6h37e

Segmentation of Façades from Urban 3D Point Clouds Using Geometrical and Morphological Attribute-Based Operators

Andrés Serna, Beatriz Marcotegui, Jorge Hernández
2016 ISPRS International Journal of Geo-Information  
Our methods are based on geometrical and geodesic constraints. Parameters are related to urban and architectural constraints.  ...  In this paper, we propose automatic, parametric and robust approaches to segment façades from 3D point clouds.  ...  The geodesic diameter L(X) = sup x∈X {l x (X)} is the length of the longest geodesic arc of X, i.e. the longest internal segment l x (X) connecting the two end points of X [31] .  ... 
doi:10.3390/ijgi5010006 fatcat:vn4rsfs2grhh5fzjnselvaodxa

Hierarchical sparse coding with geometric prior for visual geo-location

Raghuraman Gopalan
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We then extend this approach to account for the availability of heterogeneous data modalities such as geo-tags and videos pertaining to different locations, and also study a relatively under-addressed  ...  We address the problem of estimating location information of an image using principles from automated representation learning.  ...  line segments of ground view images to perform location matching of planar structures under projective uncertainty.  ... 
doi:10.1109/cvpr.2015.7298857 dblp:conf/cvpr/Gopalan15 fatcat:aka4cafrgvekriqdsrscvxq2pi

Recognizing City Identity via Attribute Analysis of Geo-tagged Images [chapter]

Bolei Zhou, Liu Liu, Aude Oliva, Antonio Torralba
2014 Lecture Notes in Computer Science  
Then, we conduct the city identity recognition experiments on the geo-tagged images and identify images with salient city identity on each city attribute.  ...  In this work, we propose to characterize the identity of a city via an attribute analysis of 2 million geo-tagged images from 21 cities over 3 continents.  ...  Here we choose geo-tagged images from photo sharing websites.  ... 
doi:10.1007/978-3-319-10578-9_34 fatcat:i73k63d77jh2hl2pr744gmp37a

Clustering geo-tagged photo collections using dynamic programming

Matthew L. Cooper
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
[4] studied hierarchical image annotation using event clustering of photos. Their method first processed time and then location using mean shift clustering.  ...  For spatial reference clusterings, we use the distance between photo locations to construct a similar hierarchical spatial partitioning: sσ(i, j) = exp − dg(li, lj) σ . (4) dg is the approximate geodesic  ... 
doi:10.1145/2072298.2071929 dblp:conf/mm/Cooper11 fatcat:c6toarr7gvcdzktubrpfys6ah4

Multimodal geo-tagging in social media websites using hierarchical spatial segmentation

Pascal Kelm, Sebastian Schmiedeke, Thomas Sikora
2012 Proceedings of the 5th International Workshop on Location-Based Social Networks - LBSN '12  
The Flickr videos are tagged with the geo-information of the most similar training image within the regions that is previously filtered by the probabilistic model for each test video.  ...  Many of these social media websites such as Flickr, Facebook and Youtube allows the user to manually label their uploaded videos with geo-information using a interface for dragging them into the map.  ...  They find visual nearest neighbours to a single image based on low-level visual image descriptors and propagate the geo-location of the GPS-tagged neighbours.  ... 
doi:10.1145/2442796.2442805 dblp:conf/gis/KelmSS12 fatcat:drmx2yq2aff53prlewhuikzdke

Efficient Calculation of Distance Transform on Discrete Global Grid Systems

Meysam Kazemi, Lakin Wecker, Faramarz Samavati
2022 ISPRS International Journal of Geo-Information  
Computing a distance transform on traditional Geographic Information Systems (GIS) is usually adopted from image processing methods, albeit prone to distortion resulting from flat maps.  ...  computation [18] , image segmentation [19] , and Convolutional Neural Networks [20] , to name a few.  ...  Our system considers line segments of the feature as great-circle arcs, while this is not the case for ArcGIS Pro.  ... 
doi:10.3390/ijgi11060322 doaj:e5417b010769402c9fd95f094d29ef52 fatcat:46yhr4ur75bxpe564ohvlxfjye

An Improved Hybrid Segmentation Method for Remote Sensing Images

Wang, Jiang, Wang, Qi
2019 ISPRS International Journal of Geo-Information  
However, the existing methods ignore the fact that the same parameters must be applied to every segmented geo-object, and fail to consider the homogeneity between adjacent geo-objects.  ...  Image segmentation technology, which can be used to completely partition a remote sensing image into non-overlapping regions in the image space, plays an indispensable role in high-resolution remote sensing  ...  geo-objects used to merge similar segmented geo-objects.  ... 
doi:10.3390/ijgi8120543 fatcat:rxx5ho6ynvcjrgign2r4pkhgma

Deformation Estimation Using Beidou GEO-Satellite-Based Reflectometry

Yongqian Chen, Songhua Yan, Jianya Gong
2021 Remote Sensing  
This paper presents a novel deformation monitoring concept based on GNSS-R utilizing Beidou GEO satellites.  ...  The geometrical properties of the GEO-based bistatic GNSS radar system are explored to build a theoretical connection between deformation quantity and the echo carrier phases.  ...  Conventional methods mainly involve utilizing geodesic leveling, optical remote sensing, or positioning system.  ... 
doi:10.3390/rs13163285 fatcat:epuqfamzhvhhvow7l24st6bte4

What Is the Shape of Geographical Time-Space? A Three-Dimensional Model Made of Curves and Cones

Alain L'Hostis, Farouk Abdou
2021 ISPRS International Journal of Geo-Information  
Slower, short range flights are represented as curved lines above the earth surface with longer length than the geodesic, in order to account for a slower speed.  ...  The novelty of the model resides in the use of cones to describing the terrestrial surface instead of graph faces, and in the use of curves instead of broken segments for edges.  ...  The shortest edges must be drawn as straight lines in the plane, or as geodesic curves on the sphere.  ... 
doi:10.3390/ijgi10050340 fatcat:rvt5mg6g3fdovj3hspnjnac2b4
« Previous Showing results 1 — 15 out of 979 results