Filters








50,221 Hits in 3.9 sec

Fast and Robust Registration of Aerial Images and LiDAR data Based on Structrual Features and 3D Phase Correlation [article]

Bai Zhu, Yuanxin Ye, Chao Yang, Liang Zhou, Huiyu Liu, Yungang Cao
2020 arXiv   pre-print
To tackle the problem, this paper proposes an automatic registration method based on structural features and three-dimension (3D) phase correlation.  ...  Subsequently, a robust structural feature descriptor is build based on dense gradient features, and the 3D phase correlation is used to detect control points (CPs) between aerial images and LiDAR data  ...  After t, the coarse registration is completed between two local image patches from the aerial and LiDAR intensity images.  ... 
arXiv:2004.09811v1 fatcat:zoy6svzteranvluqo7p7odynky

FAST AND ROBUST REGISTRATION OF AERIAL IMAGES AND LIDAR DATA BASED ON STRUCTURAL FEATURES AND 3D PHASE CORRELATION

B. Zhu, Y. Ye, C. Yang, L. Zhou, H. Liu, Y. Cao
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
To tackle the problem, this paper proposes an automatic registration method based on structural features and three-dimension (3D) phase correlation.  ...  Subsequently, a robust structural feature descriptor is build based on dense gradient features, and the 3D phase correlation is used to detect control points (CPs) between aerial images and LiDAR data  ...  After t, the coarse registration is completed between two local image patches from the aerial and LiDAR intensity images.  ... 
doi:10.5194/isprs-annals-v-2-2020-135-2020 fatcat:fea67tmjvzg7bf36xxgtp5urdq

Multi-scale Adaptive Mask 3D Rigid Registration of Ultrasound and CT Images

Z. Zhijun, S. Jerome, M. K. Soo, B. Yan, C. K. Yeung
2007 Procedings of the British Machine Vision Conference 2007  
The performances of our method are compared with a typical intensity based registration method on phantom and real patient images.  ...  3D Rigid intra-operative image registration is an important technique to provide guidance for pre-operative information from different image modalities.  ...  There are several intensity based multi-modal image registration methods [9, 13, 11, 15] and they work well on registrations between CT and MR images.  ... 
doi:10.5244/c.21.91 dblp:conf/bmvc/ZhangSSBY07 fatcat:s7jeixszvrhl3hl54uz5busjyq

Hybrid Spline-Based Multimodal Registration Using Local Measures for Joint Entropy and Mutual Information [chapter]

Andreas Biesdorf, Stefan Wörz, Hans-Jürgen Kaiser, Christoph Stippich, Karl Rohr
2009 Lecture Notes in Computer Science  
We introduce a new hybrid approach for spline-based elastic registration of multimodal medical images.  ...  The approach uses point landmarks as well as intensity information based on local analytic measures for joint entropy and mutual information.  ...  (a) Original source and target images, (b) after landmark-based registration, (c) after intensity-based registration using JEnew, (d) after intensity-based registration using MInew, (e) after hybrid registration  ... 
doi:10.1007/978-3-642-04268-3_75 fatcat:fvkeb7ft4jazlg2wsyf7orfma4

Registration-based propagation for whole heart segmentation from compounded 3D echocardiography

Xiahai Zhuang, Cheng Yao, YingLiang Ma, David Hawkes, Graeme Penney, Sebastien Ourselin
2010 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
We propose to use the registration-based segmentation framework and adopt a new similarity measure combining local phase, intensity information and local geometry for registration.  ...  However, characteristics of US imaging such as limited field-of-view, artifacts and inconsistent intensity distribution makes automated approaches a challenge.  ...  Hence, intensity-based registration can also be applied to US images using the local phase as feature intensity.  ... 
doi:10.1109/isbi.2010.5490183 dblp:conf/isbi/ZhuangYMHPO10 fatcat:3iyqdkiazbhjrj63azmi7eimtm

Fully Automatic 3D Reconstruction of Histological Images [article]

Ulas Bagci, Li Bai
2009 arXiv   pre-print
To improve the quality of reconstructed 3D volume, first, intensity variations in images are corrected by an intensity standardization process which maps image intensity scale to a standard scale where  ...  Third, in order to improve the quality of the reconstruction process, an automatic best reference slice selection algorithm is developed based on an iterative assessment of image entropy and mean square  ...  Udupa, from Medical Image Processing Group of University of Pennsylvania, for his encouragement and guidance throughout this project.  ... 
arXiv:0907.3215v1 fatcat:nqg3xfuv7ngi5nz2pa4rbkmqwe

Direct Simultaneous Multi-Image Registration [article]

Zhehua Mao, Liang Zhao, Shoudong Huang, Yiting Fan, Alex Pui-Wai Lee
2021 arXiv   pre-print
The algorithm optimizes global poses of local frames directly based on the intensities of images (without extracting features from the images).  ...  This paper presents a novel algorithm that registers a collection of mono-modal 3D images in a simultaneous fashion, named as Direct Simultaneous Registration (DSR).  ...  In this paper, we propose a novel direct simultaneous registration (DSR) method which optimizes global poses of a collection of 3D images directly based on image intensities.  ... 
arXiv:2105.10087v1 fatcat:3ffoqtestvfixio3ynngeyi7ke

Accurate Single Image Multi-modal Camera Pose Estimation [chapter]

Christoph Bodensteiner, Marcus Hebel, Michael Arens
2012 Lecture Notes in Computer Science  
The pose is then accurately refined using an intensity based 2D/3D registration approach.  ...  In this work we propose a novel multi-modal method for single image camera pose estimation with respect to 3D models with intensity information (e.g., LiDAR data with reflectance information).  ...  , (c) best hypothesis supporting feature matches, (d) intensity based local image region alignment, (e) final point correspondences for one local image region.  ... 
doi:10.1007/978-3-642-35740-4_23 fatcat:y2lqjxfzu5f6vfjzm5f47wcmna

Rigid Registration [chapter]

Ziv Yaniv
2008 Image-Guided Interventions  
Data types used for registration can be classified as either geometric objects, or image intensity data.  ...  Ultrasound), and three dimensional digitized points obtained in several ways including, contact based digitization with a tracked probe, laser range scanning, and stereo imaging using standard video images  ...  Intensity based methods Intensity based registration arises when the mappings F l and F r in Definition 1.2 map locations to intensity values, image to image registration.  ... 
doi:10.1007/978-0-387-73858-1_6 fatcat:zzm44fgband3jfs3xhn6ugfupm

2D-3D registration with weighted local mutual information in vascular interventions

Cai Meng, Qi Wang, Shaoya Guan, Kai Sun, Bo Liu
2019 IEEE Access  
With the proposed WLMI, the 2D-3D registration experiments are conducted with the synthetic and real DSA images to CTA vessel model.  ...  In this paper, a novel similarity measure, WLMI (Weighted Local Mutual Information), is proposed to perform 2D-3D registration, which uses the patches selected in DSA to find the best match in the DRRs  ...  A. 2D-3D REGISTRATION BASED ON SIMILARITY MEASURES Denote C as the 3D vascular model obtained by CTA segmentation and reconstruction, I DSA as the X-ray image to be registered. 2D-3D registration based  ... 
doi:10.1109/access.2019.2905345 fatcat:f34fzgf56rgsnpcrrmwfud6fpi

Registration of 2D to 3D joint images using phase-based mutual information

Rupin Dalvi, Rafeef Abugharbieh, Mark Pickering, Jennie Scarvell, Paul Smith, Josien P. W. Pluim, Joseph M. Reinhardt
2007 Medical Imaging 2007: Image Processing  
The femur and the tibia in the CT volume were individually registered to the fluoroscopy images using intensity-based MI, gradient-based MI and phase-based MI.  ...  Traditional registration metrics such as intensity-based mutual information (MI) typically work well but often suffer from gross misregistration errors when the image to be registered contains a partial  ...  METHODS Phase-Based Similarity Metric We propose the use of local phase information for the registration of 2D fluoroscopic data to 3D CT volumes.  ... 
doi:10.1117/12.709118 dblp:conf/miip/DalviAPSS07 fatcat:wbw6s2zu2vg4tg37hggvlherti

Single Frame Based Video Geo-Localisation Using Structure Projection

C. Bodensteiner, S. Bullinger, S. Lemaire, M. Arens
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
Li-DAR) in order to generate geo-registered 3D feature maps. These maps enable a simple and fast global appearance based geo-registration of visually overlapping community videos and images.  ...  Community image and video platforms like FlickR and Youtube offer large image collections from different perspectives.  ...  This initial registration is then refined by an intensity based 2D/3D approach. This registration allows for a pixel-wise overlay of a rendered LiDAR view with the input image.  ... 
doi:10.1109/iccvw.2015.136 dblp:conf/iccvw/BodensteinerBLA15 fatcat:43mish6kszfthcgunzwlxcriie

Registration of standardized histological images in feature space

Ulaş Bağci, Li Bai, Joseph M. Reinhardt, Josien P. W. Pluim
2008 Medical Imaging 2008: Image Processing  
In this paper, we propose three novel and important methods for the registration of histological images for 3D reconstruction.  ...  Third, we propose an automatic best reference slice selection algorithm that improves reconstruction quality based on both image entropy and mean square error of the registration process.  ...  Udupa, Image Processing Group of University of Pennsylvania, for his comments and suggestions.  ... 
doi:10.1117/12.770219 dblp:conf/miip/BagciB08 fatcat:qv3dxb6zcnbc5jo5bbujwwyi4m

A practical salient region feature based 3D multi-modality registration method for medical images

Dieter A. Hahn, Gabriele Wolz, Yiyong Sun, Joachim Hornegger, Frank Sauer, Torsten Kuwert, Chenyang Xu, Joseph M. Reinhardt, Josien P. W. Pluim
2006 Medical Imaging 2006: Image Processing  
Our method combines advantageous aspects of both feature-and intensity-based approaches and consists of three steps: an automatic extraction of a set of 3D salient region features on each image, a robust  ...  Results of the developed algorithm are presented for both mono-and multi-modal intra-patient 3D image pairs (CT, PET and SPECT) that have been acquired for change detection, tumor localization, and time  ...  To achieve rotation invariance, the rotation parameters are estimated by a local rigid body registration of the 3D salient feature regions based on their intensity values.  ... 
doi:10.1117/12.653071 dblp:conf/miip/HahnWSHSKX06 fatcat:vfsaetxwxffabexbvigp3be44m

Local tissue-weight-based nonrigid registration of lung images with application to regional ventilation

Youbing Yin, Eric A. Hoffman, Ching-Long Lin, Xiaoping P. Hu, Anne V. Clough
2009 Medical Imaging 2009: Biomedical Applications in Molecular, Structural, and Functional Imaging  
 To understand the etiology of lung pathology (pollutant)  To improve drug delivery methods (therapeutic)  Other applications include  Understanding gas mixing to help improve helium MRI/xenon-CT imaging  ...  Intensity-Based Reg. Hybrid Reg.  ...  Intensity-Based Reg. Hybrid Reg.  ... 
doi:10.1117/12.811715 fatcat:giu7hjexjjdupfxyu7irlqd5za
« Previous Showing results 1 — 15 out of 50,221 results