Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611895
Anas Abuzaina, Thamer S. Alathari, M. Nixon, J. Carter
We present a new approach to extracting moving spheres from a sequence of 3D point clouds. The new 3D velocity Hough Transform (3DVHT) incorporates motion parameters in addition to structural parameters in an evidence gathering process to accurately detect moving spheres at any given point cloud from the sequence. We demonstrate its capability to detect spheres which are obscured within the sequence of point clouds, which conventional approaches cannot achieve. We apply our algorithm on real and synthetic data and demonstrate the ability of detecting fully occluded spheres by exploiting inter-frame correlation within the 3D point cloud sequence.
{"title":"Detecting moving spheres in 3D point clouds via the 3D velocity Hough Transform","authors":"Anas Abuzaina, Thamer S. Alathari, M. Nixon, J. Carter","doi":"10.1109/IVMSPW.2013.6611895","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611895","url":null,"abstract":"We present a new approach to extracting moving spheres from a sequence of 3D point clouds. The new 3D velocity Hough Transform (3DVHT) incorporates motion parameters in addition to structural parameters in an evidence gathering process to accurately detect moving spheres at any given point cloud from the sequence. We demonstrate its capability to detect spheres which are obscured within the sequence of point clouds, which conventional approaches cannot achieve. We apply our algorithm on real and synthetic data and demonstrate the ability of detecting fully occluded spheres by exploiting inter-frame correlation within the 3D point cloud sequence.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128239876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611937
Alexandros Doumanoglou, S. Asteriadis, D. Alexiadis, D. Zarpalas, P. Daras
Hereby, a new publicly available 3D reconstruction-oriented dataset is presented. It consists of multi-view range scans of small-sized objects using a turntable. Range scans were captured using a Microsoft Kinect sensor, as well as an accurate laser scanner (Vivid VI-700 Non-contact 3D Digitizer), whose reconstructions can serve as ground-truth data. The construction of this dataset was motivated by the lack of a relevant Kinect dataset, despite the fact that Kinect has attracted the attention of many researchers and home enthusiasts. Thus, the core idea behind the construction of this dataset, is to allow the validation of 3D surface reconstruction methodologies for point sets extracted using Kinect sensors. The dataset consists of multi-view range scans of 59 objects, along with the necessary calibration information that can be used for experimentation in the field of 3D reconstruction from Kinect depth data. Two well-known 3D reconstruction methods were selected and applied on the dataset, in order to demonstrate its applicability in the 3D reconstruction field, as well as the challenges that arise. Additionally, the appropriate 3D reconstruction evaluation methodology is presented. Finally, as the dataset comes in classes of similar objects, it can also be used for classification purposes, using the provided 2.5D/3D features.
{"title":"A dataset of Kinect-based 3D scans","authors":"Alexandros Doumanoglou, S. Asteriadis, D. Alexiadis, D. Zarpalas, P. Daras","doi":"10.1109/IVMSPW.2013.6611937","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611937","url":null,"abstract":"Hereby, a new publicly available 3D reconstruction-oriented dataset is presented. It consists of multi-view range scans of small-sized objects using a turntable. Range scans were captured using a Microsoft Kinect sensor, as well as an accurate laser scanner (Vivid VI-700 Non-contact 3D Digitizer), whose reconstructions can serve as ground-truth data. The construction of this dataset was motivated by the lack of a relevant Kinect dataset, despite the fact that Kinect has attracted the attention of many researchers and home enthusiasts. Thus, the core idea behind the construction of this dataset, is to allow the validation of 3D surface reconstruction methodologies for point sets extracted using Kinect sensors. The dataset consists of multi-view range scans of 59 objects, along with the necessary calibration information that can be used for experimentation in the field of 3D reconstruction from Kinect depth data. Two well-known 3D reconstruction methods were selected and applied on the dataset, in order to demonstrate its applicability in the 3D reconstruction field, as well as the challenges that arise. Additionally, the appropriate 3D reconstruction evaluation methodology is presented. Finally, as the dataset comes in classes of similar objects, it can also be used for classification purposes, using the provided 2.5D/3D features.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129629536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611910
O. Ikeda
In photometric stereo two of the common problems are inter-reflections and non-Lambertian reflection. The former locally blurs the images, resulting in a locally distorted shape, where the effects may be more significant as the object structure is more complicated. The latter, on the other hand, gives global distortions and it may be represented by directional diffuse reflection. In this paper, we present an image processing method to reduce the effects of inter-reflections for directional diffuse reflection object. The method is described mathematically, and experimental results are given to examine the method.
{"title":"Compensation for inter-reflection and control of reflection coefficient for directional diffuse object in photometric stereo","authors":"O. Ikeda","doi":"10.1109/IVMSPW.2013.6611910","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611910","url":null,"abstract":"In photometric stereo two of the common problems are inter-reflections and non-Lambertian reflection. The former locally blurs the images, resulting in a locally distorted shape, where the effects may be more significant as the object structure is more complicated. The latter, on the other hand, gives global distortions and it may be represented by directional diffuse reflection. In this paper, we present an image processing method to reduce the effects of inter-reflections for directional diffuse reflection object. The method is described mathematically, and experimental results are given to examine the method.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130107624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611939
D. Alexiadis, D. Zarpalas, P. Daras
Multi-party 3D Tele-Immersive (TI) environments, supporting realistic interaction among distant users, is the future of tele-conferencing. Real-time, full-body 3D reconstruction, an important task for TI applications, is addressed in this paper. A volumetric method for the reconstruction of watertight models of moving humans is presented, along with details for appropriate texture-mapping to enhance the visual quality. The reconstruction uses the input from multiple consumer depth cameras and specifically Kinect sensors. The presented results verify the effectiveness of the proposed methodologies, with respect to the visual quality and frame rates.
{"title":"Real-time, realistic full-body 3D reconstruction and texture mapping from multiple Kinects","authors":"D. Alexiadis, D. Zarpalas, P. Daras","doi":"10.1109/IVMSPW.2013.6611939","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611939","url":null,"abstract":"Multi-party 3D Tele-Immersive (TI) environments, supporting realistic interaction among distant users, is the future of tele-conferencing. Real-time, full-body 3D reconstruction, an important task for TI applications, is addressed in this paper. A volumetric method for the reconstruction of watertight models of moving humans is presented, along with details for appropriate texture-mapping to enhance the visual quality. The reconstruction uses the input from multiple consumer depth cameras and specifically Kinect sensors. The presented results verify the effectiveness of the proposed methodologies, with respect to the visual quality and frame rates.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116073607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611898
B. Guthier, J. Kiess, S. Kopf, W. Effelsberg
In this paper, we present a novel technique for seam carving of stereoscopic video. It removes seams of pixels in areas that are most likely not noticed by the viewer. When applying seam carving to stereoscopic video rather than monoscopic still images, new challenges arise. The detected seams must be consistent between the left and the right view, so that no depth information is destroyed. When removing seams in two consecutive frames, temporal consistency between the removed seams must be established to avoid flicker in the resulting video. By making certain assumptions, the available depth information can be harnessed to improve the quality achieved by seam carving. Assuming that closer pixels are more important, the algorithm can focus on removing distant pixels first. Furthermore, we assume that coherent pixels belonging to the same object have similar depth. By avoiding to cut through edges in the depth map, we can thus avoid cutting through object boundaries.
{"title":"Seam carving for stereoscopic video","authors":"B. Guthier, J. Kiess, S. Kopf, W. Effelsberg","doi":"10.1109/IVMSPW.2013.6611898","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611898","url":null,"abstract":"In this paper, we present a novel technique for seam carving of stereoscopic video. It removes seams of pixels in areas that are most likely not noticed by the viewer. When applying seam carving to stereoscopic video rather than monoscopic still images, new challenges arise. The detected seams must be consistent between the left and the right view, so that no depth information is destroyed. When removing seams in two consecutive frames, temporal consistency between the removed seams must be established to avoid flicker in the resulting video. By making certain assumptions, the available depth information can be harnessed to improve the quality achieved by seam carving. Assuming that closer pixels are more important, the algorithm can focus on removing distant pixels first. Furthermore, we assume that coherent pixels belonging to the same object have similar depth. By avoiding to cut through edges in the depth map, we can thus avoid cutting through object boundaries.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132477814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611902
Yaoxue Xing, Yao Zhao, Chunyu Lin, H. Bai, Chao Yao
In this paper, the spatial correlation and temporal consistency are jointly employed in depth down/up-sampling to achieve efficient depth coding. Given that the temporal consistency of the depth maps, a direct down-sampling method that the pixels at different positions are sampled between the adjacent frames is applied. After down-sampling, High Efficiency Video Coding (HEVC) is adopted to encode and decode the down-sampled depth maps for its good compression efficiency. Then, the proposed up-sampling algorithm which considers the spatial correlation among the neighbor pixels in one depth map and the temporal consistency between the adjacent depth frames, as well as the correlation between the depth map and its corresponding texture image is utilized to get a good quality depth map with full resolution. Experimental results show that the proposed algorithm improves both depth map coding performance and synthesized quality.
本文将空间相关性和时间一致性结合到深度上下采样中，实现了高效的深度编码。考虑到深度图的时间一致性，采用直接下采样的方法，在相邻的帧之间采样不同位置的像素。下采样后，采用高效视频编码(High Efficiency Video Coding, HEVC)对下采样深度图进行编码解码，压缩效率高。然后，利用所提出的上采样算法，综合考虑同一深度图中相邻像素之间的空间相关性和相邻深度帧之间的时间一致性，以及深度图与其对应纹理图像之间的相关性，得到高质量的全分辨率深度图。实验结果表明，该算法提高了深度图编码性能和合成质量。
{"title":"Depth down/up-sampling using hybrid correlation for depth coding","authors":"Yaoxue Xing, Yao Zhao, Chunyu Lin, H. Bai, Chao Yao","doi":"10.1109/IVMSPW.2013.6611902","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611902","url":null,"abstract":"In this paper, the spatial correlation and temporal consistency are jointly employed in depth down/up-sampling to achieve efficient depth coding. Given that the temporal consistency of the depth maps, a direct down-sampling method that the pixels at different positions are sampled between the adjacent frames is applied. After down-sampling, High Efficiency Video Coding (HEVC) is adopted to encode and decode the down-sampled depth maps for its good compression efficiency. Then, the proposed up-sampling algorithm which considers the spatial correlation among the neighbor pixels in one depth map and the temporal consistency between the adjacent depth frames, as well as the correlation between the depth map and its corresponding texture image is utilized to get a good quality depth map with full resolution. Experimental results show that the proposed algorithm improves both depth map coding performance and synthesized quality.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124935628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611911
Jaekwang Kim, Jaeho Lee, Seung-Ryong Han, Dowan Kim, Jongsul Min, Changick Kim
In recent years, fusion camera systems that consist of color cameras and Time-of-Flight (TOF) depth sensors have been popularly used due to its depth sensing capability at real-time frame rates. However, captured depth maps are limited in low resolution compared to the corresponding color images due to physical limitation of the TOF depth sensor. Although many algorithms have been proposed, they still yield erroneous results, especially when boundaries of the depth map and the color image are not aligned. We therefore propose a novel kernel regression framework to generate the high quality depth map. Our proposed filter is based on the vector pointing homogeneous pixels that represents the unit vector toward similar neighbors in the local region. The vectors are used to detect misaligned regions between color edges and depth edges. Experimental comparisons with other data fusion techniques prove the superiority of the proposed algorithm.
{"title":"Trilateral filter construction for depth map upsampling","authors":"Jaekwang Kim, Jaeho Lee, Seung-Ryong Han, Dowan Kim, Jongsul Min, Changick Kim","doi":"10.1109/IVMSPW.2013.6611911","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611911","url":null,"abstract":"In recent years, fusion camera systems that consist of color cameras and Time-of-Flight (TOF) depth sensors have been popularly used due to its depth sensing capability at real-time frame rates. However, captured depth maps are limited in low resolution compared to the corresponding color images due to physical limitation of the TOF depth sensor. Although many algorithms have been proposed, they still yield erroneous results, especially when boundaries of the depth map and the color image are not aligned. We therefore propose a novel kernel regression framework to generate the high quality depth map. Our proposed filter is based on the vector pointing homogeneous pixels that represents the unit vector toward similar neighbors in the local region. The vectors are used to detect misaligned regions between color edges and depth edges. Experimental comparisons with other data fusion techniques prove the superiority of the proposed algorithm.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"311 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122495397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611904
Hak Gu Kim, B. Song
This paper presents a new 2D-to-3D conversion method based on structure from motion (SfM) in order to relieve the visual fatigue and simultaneously improve the three-dimensional effect (3D effect). First, we obtain the 3D information such as camera positions and depth values via SfM. Then, we segment an input image, and find the nearest object region. Next, the projective matrix of the nearest object is computed. Finally, the nearest object is warped using the computed projective matrix, and the other regions are properly warped according to their depth values. Experimental results show that the proposed method can synthesize stereo views better than the other methods.
{"title":"Automatic object-based 2D-to-3D conversion","authors":"Hak Gu Kim, B. Song","doi":"10.1109/IVMSPW.2013.6611904","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611904","url":null,"abstract":"This paper presents a new 2D-to-3D conversion method based on structure from motion (SfM) in order to relieve the visual fatigue and simultaneously improve the three-dimensional effect (3D effect). First, we obtain the 3D information such as camera positions and depth values via SfM. Then, we segment an input image, and find the nearest object region. Next, the projective matrix of the nearest object is computed. Finally, the nearest object is warped using the computed projective matrix, and the other regions are properly warped according to their depth values. Experimental results show that the proposed method can synthesize stereo views better than the other methods.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125370283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611894
Shinkook Choi, J. Baek
Third-generation CT architectures are approaching fundamental limits. While alternative architectures such as electron beam CT and dual energy CT has been proposed, they have severe tradeoffs in terms of image quality, dose-efficiency, and complexity. In this work, we present the concept of multi-source inverse-geometry CT(MS-IGCT) system which overcomes several limits of current CT architectures, and The 3D reconstruction algorithm and initial experimental results of the MS-IGCT system are also presented.
{"title":"Multi-source inverse geometry CT(MS-IGCT) system: A new concept of 3D CT imaging","authors":"Shinkook Choi, J. Baek","doi":"10.1109/IVMSPW.2013.6611894","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611894","url":null,"abstract":"Third-generation CT architectures are approaching fundamental limits. While alternative architectures such as electron beam CT and dual energy CT has been proposed, they have severe tradeoffs in terms of image quality, dose-efficiency, and complexity. In this work, we present the concept of multi-source inverse-geometry CT(MS-IGCT) system which overcomes several limits of current CT architectures, and The 3D reconstruction algorithm and initial experimental results of the MS-IGCT system are also presented.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114976390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-10DOI: 10.1109/IVMSPW.2013.6611893
Kihyung Kang, Seondeok Hwang, J. Yoon, Dongchoon Hwang, Soobae Moon
In this paper, we propose a shifted ITO electrode structure of a LC barrier for additional sweet spots in the auto-stereoscopic 3D display. The shifted ITO electrode is consisted of vertically inter-digital ITO electrodes both bottom and top electrodes. They are assembled with horizontally shifted by a half pitch. We can drive each electrode according to the viewer position. It gives an effect of varying the viewing zone. By doing this, we can widen the viewing zone with head tracking technique. It can give a viewer some freedom of viewing position with an image of high quality.
{"title":"Autostereoscopic display with a shifted LC barrier structure for a wide viewing zone","authors":"Kihyung Kang, Seondeok Hwang, J. Yoon, Dongchoon Hwang, Soobae Moon","doi":"10.1109/IVMSPW.2013.6611893","DOIUrl":"https://doi.org/10.1109/IVMSPW.2013.6611893","url":null,"abstract":"In this paper, we propose a shifted ITO electrode structure of a LC barrier for additional sweet spots in the auto-stereoscopic 3D display. The shifted ITO electrode is consisted of vertically inter-digital ITO electrodes both bottom and top electrodes. They are assembled with horizontally shifted by a half pitch. We can drive each electrode according to the viewer position. It gives an effect of varying the viewing zone. By doing this, we can widen the viewing zone with head tracking technique. It can give a viewer some freedom of viewing position with an image of high quality.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132994111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：