西北工业大学计算机视觉与计算摄像学研究组
中文 | English
: 西北工业大学长安校区
       计算机学院楼216室
:

项目

双平面光场局部不变性特征提取与匹配方法研究 [正在进行...]

主持人: 肖照林 | 项目批准号: 61871319 | 资助部门: 国家自然科学基金 | 起止时间: 2019-01-01/2022-12-31 | 项目类型:面上项目

基于光场成像的儿童社交行为理解研究 [正在进行...]

主持人: 王雪 | 项目批准号: 61801396 | 资助部门: 国家自然科学基金 | 起止时间: 2019-01-01/2021-12-31 | 项目类型:青年基金

相关论文

Region-based depth feature descriptor for saliency detection on light field [PDF] [BIB]

Xue Wang, Yingying Dong, Qi Zhang, Qing Wang
Multimedia Tools and Applications, 2020, Early Access (2020-05)

4D Light Field Segmentation from Light Field Super-pixel Hypergraph Representation [PDF] [BIB]

Xianqiang Lv, Xue Wang, Qing Wang, Jingyi Yu
IEEE Transactions on Visualization and Computer Graphics, 2020, Early Access (2020-03)

Accurate 3D Reconstruction from Circular Light Field Using CNN-LSTM [PDF] [BIB]

Zhengxi Song, Hao Zhu, Qi Wu, Xue Wang, Hongdong Li, Qing Wang
IEEE Int. Conf. on Multimedia and Expo (ICME), London, UK, 2020 (2020-05)

DGAN: Disentangled Representation Learning for Anisotropic BRDF Reconstruction [PDF] [BIB]

Zhongyun Hu, Xue Wang, Qing Wang
IEEE ICASSP, Barcelona, Spain, pp. 4397-4401, 2020. (2020-02)

Light Field SLAM Based on Ray-space Projection Model [PDF] [BIB]

Yaning Li, Qi Zhang, Xue Wang, Qing Wang
Photonics Asia 2019, Hangzhou, China (2019-11)

Light Field Planar Homography and Its Application [PDF] [BIB]

Qi Zhang, Xue Wang, Qing Wang
Photonics Asia 2019, Hangzhou, China (2019-11)

多视光场计算理论与关键技术研究 [正在进行...]

主持人: 王庆 | 项目批准号: 61531014 | 资助部门: 国家自然科学基金委 | 起止时间: 2016-01-01/2020-12-31 | 项目类型:重点项目

以多视光场数据关联性为研究对象,构建多视光场理论与模型,提出光场相机参数标定方法参数估计误差分析精确度度量方法,突破多视光场深度估计、光场超分辨率重建,光场编辑及三维重建等关键技术,研制多视光场数据获取系统,完成全景光场合成光场高分辨率立体视频生成两个典型应用验证。

相关论文

Region-based depth feature descriptor for saliency detection on light field [PDF] [BIB]

Xue Wang, Yingying Dong, Qi Zhang, Qing Wang
Multimedia Tools and Applications, 2020, Early Access (2020-05)

4D Light Field Segmentation from Light Field Super-pixel Hypergraph Representation [PDF] [BIB]

Xianqiang Lv, Xue Wang, Qing Wang, Jingyi Yu
IEEE Transactions on Visualization and Computer Graphics, 2020, Early Access (2020-03)

Accurate 3D Reconstruction from Circular Light Field Using CNN-LSTM [PDF] [BIB]

Zhengxi Song, Hao Zhu, Qi Wu, Xue Wang, Hongdong Li, Qing Wang
IEEE Int. Conf. on Multimedia and Expo (ICME), London, UK, 2020 (2020-05)

DGAN: Disentangled Representation Learning for Anisotropic BRDF Reconstruction [PDF] [BIB]

Zhongyun Hu, Xue Wang, Qing Wang
IEEE ICASSP, Barcelona, Spain, pp. 4397-4401, 2020. (2020-02)

Revisiting Spatio-Angular Trade-off in Light Field Cameras and Extended Applications in Super-Resolution [PDF] [BIB]

Hao Zhu, Mantang Guo, Hongdong Li, Qing Wang, Antonio Robles-Kelly
IEEE Transactions on Visualization and Computer Graphics, 2020 (2019-12)

Full View Optical Flow Estimation Leveraged from Light Field Superpixel [PDF] [BIB]

Hao Zhu, Xiaoming Sun, Qi Zhang, Qing Wang, Antonio Robles-Kelly, Hongdong Li, Shaodi You
IEEE Transactions on Computational Imaging, 6(1):12-23, 2020. (2020-01)

4D Light Field Superpixel and Segmentation [PDF] [BIB]

Hao Zhu, Qi Zhang, Qing Wang, Hongdong Li
IEEE Transactions on Image Processing, 29(1):85-99, 2020. (2020-01)

Ray-Space Projection Model for Light Field Camera [PDF] [BIB]

Qi Zhang, Jinbo Ling, Qing Wang, Jingyi Yu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, pp. 10121-10129 (2019-06)

A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras [PDF] [BIB]

Qi Zhang, Chunping Zhang, Jinbo Ling, Qing Wang, Jingyi Yu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(11):2539-2552, 2019. (2019-11)

Common Self-polar Triangle of Concentric Conics for Light Field Camera Calibration [PDF] [BIB]

Qi Zhang, Qing Wang
2018 Asian Conf. on Computer Vision (ACCV), Perth, Australia (2018-11)

Dense Light Field Reconstruction from Sparse Sampling Using Residual Network [PDF] [BIB]

Mantang Guo, Hao Zhu, Guoqing Zhou, Qing Wang
2018 Asian Conf. on Computer Vision (ACCV), Perth, Australia (2018-11)

Motion-based Temporal Alignment of Independently Moving Cameras [PDF] [BIB]

Xue Wang, Jianbo Shi, Hyun Soo Park, Qing Wang
IEEE Transactions on Circuits and Systems for Video Technology, 27(11):2344-2354, 2017 (2017-11)

High Angular Resolution Light Field Reconstruction with Coded-Aperture Mask [PDF] [BIB]

Wanxin Qu, Guoqing Zhou, Hao Zhu, Zhaolin Xiao, Qing Wang, Rene Vidal
IEEE Int. Conf. on Image Processing (ICIP), Beijing, China, pp.3036-3040 (2017-09)

Extending the FOV from Disparity and Color Consistencies in Multiview Light Fields [PDF] [BIB]

Zhao Ren, Qi Zhang, Hao Zhu, Qing Wang
IEEE Int. Conf. on Image Processing (ICIP), Beijing, China, pp.1157-1161 (2017-09)

Seeing Beyond Foreground Occlusion: A Joint Framework for SAP Based Scene Depth and Appearance Reconstruction [PDF] [BIB]

Zhaolin Xiao, Lipeng Si, Guoqing Zhou
IEEE Journal of Selected Topics in Signal Processing, 11(7):979-991, 2017 (2017-10)

Light Field Imaging: Models, Calibrations, Reconstructions, and Applications [PDF] [BIB]

Hao Zhu, Qing Wang, Jingyi Yu
Frontiers of Information Technology & Electronic Engineering, 18(9):1236-1249, 2017 (2017-09)

Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Field [PDF] [BIB]

Hao Zhu, Qing Wang, Jingyi Yu
IEEE Journal of Selected Topics in Signal Processing, 11(7):965-978, 2017 (2017-10)

Robust Outlier Removal Using Penalized Linear Regression in Multiview Geometry [PDF] [BIB]

Guoqing Zhou, Qing Wang, Zhaolin Xiao
Neurocomputing, 267:455-465, 2017 (2017-08)

4D Light Field Superpixel and Segmentation [PDF] [BIB]

Hao Zhu, Qi Zhang, Qing Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, pp. 6709-6717 (2017-07)

Aliasing Detection and Reduction Scheme on Angularly Undersampled Light Fields [PDF] [BIB]

Zhaolin Xiao, Qing Wang, Guoqing Zhou, Jingyi Yu
IEEE Transactions on Image Processing, 26(5): 2103-2115, 2017 (2017-05)

Dense Depth-map Estimation and Geometry Inference from Light Fields via Global Optimization [PDF] [BIB]

Lipeng Si, Qing Wang
Asian Conference on Computer Vision (ACCV), Taipei, China, pp.83-98, 2017 (2016-11)

An Efficient Anti-occlusion Depth Estimation Using Generalized EPI Representation in Light Field [PDF] [BIB]

Hao Zhu, Qing Wang
SPIE/COS Photonics Asia. 2016. (2016-10)

Rectifying Projective Distortion in 4D Light Field [PDF] [BIB]

Chunping Zhang, Zhe Ji, Qing Wang
IEEE Int. Conf. on Image Processing (ICIP), 2016 (2016-09)

LFHOG: A Discriminative Descriptor for Live Face Detection from Light Field Image [PDF] [BIB]

Zhe Ji, Hao Zhu, Qing Wang
IEEE Int. Conf. on Image Processing (ICIP), 2016 (2016-09)

光场相机成像模型及参数标定方法综述 [PDF] [BIB]

张春萍, 王庆
中国激光(Chinese Journal of Lasers), 43(6):0609004, 2016 (2016-06)

基于摄像机阵列多深度线索的场景深度估计及优化方法 [已完成]

主持人: 王庆 | 项目批准号: 61272287 | 资助部门: 国家自然科学基金委 | 起止时间: 2013-01-01/2016-12-31 | 项目类型:面上项目

三维场景深度获取一直是计算机视觉领域关注的重点之一,也是该领域众多其他问题,如三维重建、场景分割、视觉导航等相关研究的关键步骤。针对现有单一深度线索进行场景深度估计存在较大误差这一问题,本项目研究利用摄像机阵列多视点采样中所蕴含的多种深度线索来进行深度估计的方法,着重从三个方面探索多深度线索融合下的深度估计与优化方法,包括多深度线索获取、多线索融合的深度估计方法、多线索相互约束的深度估计优化方法。在多深度线索获取方面,项目组首先搭建了摄像机阵列系统的软硬件平台,并对其进行精确标定。本项目分别从对极面图、不同深度的重聚焦图像、共聚焦图像等数据源中提取结构线索、不同深度视差线索以及模糊线索等深度线索。进而,通过对其特性分析可以发现视差线索与模糊线索之间存在互补性。在多深度线索融合的深度估计方法方面,项目组首先研究了光场结构线索,提出了基于全局可控点的结构张量视差估计法。进而,研究组利用模糊线索并引入一种基于分割树的代价聚合算法对深度进行估计。对于自然场景中普遍存在的遮挡问题,研究组提出了光场下场景深度估计的多遮挡模型。最终,研究组在光场理论分析的基础上,提出了将视差线索与聚焦线索相融合的场景深度估计思路,进而提出了基于马尔科夫随机场理论融合视差法与变焦法优势的场景深度计算方法,与基于单一深度线索的场景几何结构恢复方法相比,该类方法具有更优的精度和鲁棒性。在深度估计优化方法方面,研究组给出了多视点图像匹配中的外点去除算法,在凸优化理论基础上,提出了一种基于惩罚线性回归的外点去除算法,有效去除了外点干扰;此外,研究组就遮挡区域深度特性进行研究,并提出一种基于表面相机的立体匹配抗遮挡全局优化方法,能有效处理遮挡部分;针对光场图像的混叠问题,研究组提出了一种基于随机遮挡孔径的角度域图像混叠检测方法,进而提出了基于混叠检测的共聚焦图像抗混叠处理方法,提高了共聚焦图像的生成质量。此外,研究组还开展了多个扩展技术与应用的研究,如多视点视频同步、光场超像素分割、光场局部特征子及其在活体人脸检测的应用等。

在本项目资助下,研究组申请发明专利4项,发表学术论文20篇,其中SCI二区期刊论文2篇,CCF认定的A类会议2篇。培养了青年教师2名并且均获得了自然科学基金青年基金资助,培养了5名博士研究生和10名硕士研究生。

 

关键词:深度估计;摄像机阵列;多深度线索;全局优化;深度评价模型


相关论文

Motion-based Temporal Alignment of Independently Moving Cameras [PDF] [BIB]

Xue Wang, Jianbo Shi, Hyun Soo Park, Qing Wang
IEEE Transactions on Circuits and Systems for Video Technology, 27(11):2344-2354, 2017 (2017-11)

Aliasing Detection and Reduction Scheme on Angularly Undersampled Light Fields [PDF] [BIB]

Zhaolin Xiao, Qing Wang, Guoqing Zhou, Jingyi Yu
IEEE Transactions on Image Processing, 26(5): 2103-2115, 2017 (2017-05)

基于光场分析的多线索融合深度估计方法 [PDF] [BIB]

杨德刚,肖照林,杨恒,王庆
计算机学报 (Chinese Journal of Computers), 38(12):2437-2449 (2015-12)

Aliasing Detection and Reduction in Plenoptic Imaging [PDF] [BIB]

Zhaolin Xiao, Qing Wang, Guoqing Zhou, Jingyi Yu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA, pp. 3326-3333 (2014-06)

基于随机遮挡孔径的光场图像混叠检测方法 [PDF] [BIB]

肖照林,王庆,杨恒,周果清
自动化学报 (ACTA AUTOMATICA SINICA), 40(2):247-254 (2014-02)

针对光场图像的多尺度抗混叠绘制方法 [PDF] [BIB]

肖照林,王庆,周果清,杨恒
计算机辅助设计与图形学学报 (Journal of CAD and CG), 26(7):1126-1134 (2014-07)

Sparse Representation with Geometric Configuration Constraint for Line Segment Matching [PDF] [BIB]

Qing Wang, Tingwang Chen, Lipeng Si
Neurocomputing, 134(25):100-110, 2014 (2014-01)

Matching Cost Fusion in Dense Depth Recovery for Camera-array via Global Optimization [PDF] [BIB]

Lipeng Si, Qing Wang, Zhaolin Xiao
ICVRV 2014, 180-185 (2014-08)

Figure-Aware Tracking under Occlusion from Monocular Videos [PDF] [BIB]

Xue Wang, Qing Wang
ICVRV 2014, 116-121 (2014-08)

Reconstructing Scene Depth and Appearance behind Foreground Occlusion Using Camera Array [PDF] [BIB]

Zhaolin Xiao, Qing Wang, Lipeng Si, Guoqing Zhou
ICIP 2014, 41-45 (2014-10)

针对摄像机矩阵估计的增强连续禁忌搜索方法 [PDF] [BIB]

周果清,王庆
电子学报 (ACTA ELECTRONICA SINICA), 42(12):2422-2428 (2014-12)

一种视差法与变焦法融合的深度估计方法 [PDF] [BIB]

肖照林,杨恒,周果清,王庆
西北工业大学学报 (2013-02)

A Novel Depth Recovery Approach from Multi-View Stereo Based Focusing [PDF] [BIB]

Zhaolin Xiao, Heng Yang, Qing Wang, Guoqing Zhou
ICVRV 2013, 169-176 (2013-09)

Enhanced Continuous Tabu Search for Parameter Estimation in Multiview Geometry [PDF] [BIB]

Guoqing Zhou, Qing Wang
ICCV 2013, 3240-3247 (2013-12)

光场成像的轴向超分辨率方法研究 [已完成]

主持人: 肖照林 | 项目批准号: 61501370 | 资助部门: 国家自然科学基金委 | 起止时间: 2016-01-01/2018-12-31 | 项目类型:青年科学基金

相关论文

Seeing Beyond Foreground Occlusion: A Joint Framework for SAP Based Scene Depth and Appearance Reconstruction [PDF] [BIB]

Zhaolin Xiao, Lipeng Si, Guoqing Zhou
IEEE Journal of Selected Topics in Signal Processing, 11(7):979-991, 2017 (2017-10)

Robust Outlier Removal Using Penalized Linear Regression in Multiview Geometry [PDF] [BIB]

Guoqing Zhou, Qing Wang, Zhaolin Xiao
Neurocomputing, 267:455-465, 2017 (2017-08)

Aliasing Detection and Reduction Scheme on Angularly Undersampled Light Fields [PDF] [BIB]

Zhaolin Xiao, Qing Wang, Guoqing Zhou, Jingyi Yu
IEEE Transactions on Image Processing, 26(5): 2103-2115, 2017 (2017-05)

面向自然现象感知应用示范 [已完成]

主持人: 王庆 | 项目批准号: 2012AA011803 | 资助部门: 科技部 | 起止时间: 2012-01-01/2014-12-31 | 项目类型:”863“子课题

高角度分辨率光场数据获取与图像生成方法研究 [已完成]

主持人: 周果清 | 项目批准号: 61401359 | 资助部门: 国家自然科学基金委 | 起止时间: 2015-01-01/2017-12-31 | 项目类型:青年科学基金

相关论文

High Angular Resolution Light Field Reconstruction with Coded-Aperture Mask [PDF] [BIB]

Wanxin Qu, Guoqing Zhou, Hao Zhu, Zhaolin Xiao, Qing Wang, Rene Vidal
IEEE Int. Conf. on Image Processing (ICIP), Beijing, China, pp.3036-3040 (2017-09)

Robust Outlier Removal Using Penalized Linear Regression in Multiview Geometry [PDF] [BIB]

Guoqing Zhou, Qing Wang, Zhaolin Xiao
Neurocomputing, 267:455-465, 2017 (2017-08)

4D Light Field Superpixel and Segmentation [PDF] [BIB]

Hao Zhu, Qi Zhang, Qing Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, pp. 6709-6717 (2017-07)

从共焦图像序列恢复复杂场景几何结构的方法研究 [已完成]

主持人: 杨恒 | 项目批准号: 61103060 | 资助部门: 国家自然科学基金委 | 起止时间: 2013-01-01/2015-12-31 | 项目类型:青年科学基金

基于共聚焦图像序列的动态深度恢复方法研究 [已完成]

主持人: 王庆 | 项目批准号: 20116102110031 | 资助部门: 教育部 | 起止时间: 2012-01-01/2015-12-31 | 项目类型:博士点基金博导类项目

大范围光场获取、实时建模与生成 [已完成]

主持人: 王庆 | 项目批准号: 2009AA01Z332 | 资助部门: 科技部 | 起止时间: 2009-01-01/2010-12-31 | 项目类型:”863“子课题

基于无序多图像的高可靠特征点匹配与最优化方法研究 [已完成]

主持人: 王庆 | 项目批准号: 60873085 | 资助部门: 国家自然科学基金委 | 起止时间: 2009-01-01/2011-12-31 | 项目类型:面上项目

基于时变和无序多图像的4D场景建模和表现技术 [已完成]

主持人: 王庆 | 项目批准号: 2007AA01Z314 | 资助部门: 科技部 | 起止时间: 2007-07-01/2009-12-31 | 项目类型:”863“课题

低质量视频超分辨率重构方法及模型适应性研究 [已完成]

主持人: 王庆 | 项目批准号: NCET-06-0882 | 资助部门: 教育部 | 起止时间: 2007-01-01/2009-12-31 | 项目类型:“新世纪优秀人才”计划项目

相关论文

A Comprehensive Evaluation on Non-deterministic Motion Estimation [PDF] [BIB]

Changzhu Wu, Qing Wang
ICPR 2010, 2333-2336 (2010-08)

Motion Estimation Approach Based on Dual-tree Complex Wavelets [PDF] [BIB]

Changzhu Wu, Qing Wang, Hongxiao Wang
ICPR 2008, 1-4 (2008-12)

基于迭代神经网络的复杂结构模式表示与分类方法研究 [已完成]

主持人: 王庆 | 项目批准号: 60403008 | 资助部门: 国家自然科学基金委 | 起止时间: 2005-01-01/2007-12-31 | 项目类型:面上项目