计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 63-69.doi: 10.11896/j.issn.1002-137X.2018.08.011
张新明1,2, 程金凤1, 康强1, 王霞1
LIU Yang, QI Chun, YANG Jing-yi
摘要: 文中提出一种羽毛球比赛的2D视频转换到3D视频的算法。在这类视频中,前景是最受关注的部分,准确地从背景中提取出前景对象是获取深度图的关键。文中采用一种改进的图割算法来获取前景,并根据场景结构构建背景深度模型,获取背景深度图;在背景深度图的基础上,根据前景与镜头之间的距离关系为前景对象进行深度赋值,从而得到前景深度图。然后,融合背景深度图和前景深度图,得到完整的深度图。最后,通过基于深度图像的虚拟视点绘制技术DIBR来获取用于3D显示的立体图像对。实验结果表明,最终生成的立体图像对具有较好的3D效果。
中图分类号:
[1] PATIL S,CHARLES P.Review on 2D to 3D image and video conversion methods[C]∥Proceedings of the International Conference on Computing Communication Control and Automation.Paris,France,2015:728-732. [2]EIGEN D,PUHRSCH C.Depth map prediction from a singleimage using a multi-scale deep network[J].Computer Science,arXiv:1406.2283.2014:2366-2374. [3]DOMINIC J M.Recent trends in 2D to 3D conversion:A Survey[J].International Journal for Research in Applied Science and Engineering Technology,2014,2:388-395. [4]JU K,LI Y,XIONG H.Depth propagation with tensor voting for 2D-to-3D video conversion[C]∥Proceedings of the International Conference on Acoustics,Speech and Signal Processing.Shanghai,China,2016:1696-1700. [5]TSAI T H,FAN C S.Monocular vision-based depth map extraction method for 2D to 3D video conversion[J].EURASIP Journal on Image and Video Processing,2016,2016(1):1-12. [6]JUNG C,CAI J.Superpixel matching-based depth propagation for 2D-to-3D conversion with joint bilateral filtering[C]∥Proceedings of the International Conference on Image Processing.Quebec,Canada,2015:3515-3519. [7]YAN X,YANG Y,ER G,et al.Depth map generation for 2D-to-3D conversion by limited user inputs and depth propagation[C]∥Proceedings of the 3dtv Conference:the True Vision-Capture,Transmission and Display of 3d Video.Antalya,Turkey,2011:1-4. [8]FAN Y C,CHEN P W,CHEN W S.Low computing complexity architecture design of 2D-to-3D image converter[C]∥Procee-dings of the IEEE International Conference on Consumer Electronics.Taiwan,2014:99-100. [9]HAN K,HONG K.Geometric and texture cue based depth-map estimation for 2D to 3D image conversion[C]∥Proceedings of the IEEE International Conference on Consumer Electronics.Berlin,2011:651-652. [10]CHEN Y C,WU Y C,LIU C H,et al.Depth map generation based on depth from focus[C]∥Electronic Devices,Systems and Applications.IEEE,2010:59-63. [11]LIN J,JI X,XU W,et al.Absolute depth estimation from a single defocused image[J].IEEE Transactions on Image Proces-sing,2013,22(11):4545-4550. [12]YONG J J,BAIK A,PARK D.A novel 2D-to-3D conversion technique based on relative height-depth cue[J].Proc Spie,2009,7237:72371U-72371U-8. [13]LAI Y K,LAI Y F,CHEN Y C.An Effective Hybrid Depth-Generation Algorithm for 2D-to-3D Conversion in 3D Displays[J].Journal of Display Technology,2013,9(3):154-161. [14]SAXENA A,SCHULTE J,NG A Y.Depth estimation using monocular and stereo cues[C]∥Proceedings of the International Joint Conference on Artifical Intelligence.Hyderabad,India,2007:2197-2203. [15]MOHAGHEGH H,SAMAVI S,KARIMI N,et al.Depth eatimation from single images using modified stacked generalization[C]∥Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing.Shanghai,China,2016:1621-1625. [16]KONRAD J,WANG M,ISHWAR P,et al.Learning-Based,Automatic 2D-to-3D image and video conversion[J].IEEE Tran-sactions on Image Processing,2013,22(9):3485-3496. [17]JI P,WANG L,LI D X,et al.A novel 2D-to-3D conversionmethod based on blocks world[C]∥Proceedings of the IEEE International Conference on Audio,Language and Image Proces-sing.2012:541-543. [18]CHENG C C,LI C T,CHEN L G.A novel 2D-to-3D conversion system using edge information[J].IEEE Transactions on Consumer Electronics,2010,56(3):1739-1745. [19]CHENG C C,LI C T,HUANG P S,et al.A block-based 2D-to-3D conversion system with bilateral filter[C]∥Proceedings of the International Conference on Consumer Electronics.Kyoto,Japan,2009:1-2. [20]FREILING B,SCHUMANN T,LAI Y K,et al.Block baseddepth map estimation algorithm for 2D-to-3D conversion[C]∥Proceedings of the IEEE International Symposium on Consumer Electronics.Hsinchu,Taiwan,2013:53-54. [21]NAM S W,KIM H S,BAN Y J,et al.Real-Time 2D-to-3D conversion for 3DTV using time-coherent depth-map generation method[J].International Journal of Contents,2014,10(3):187-188. [22]TANG M,GORELICK L,VEKSLER O,et al.GrabCut in one cut[C]∥Proceedings of the International Conference on Computer Vision.Sydney,Australia,2013:1-8. [23]YIN S,DONG H,JIANG G,et al.A novel 2D-to-3D video conversion method using time-coherent depth maps[J].Sensors,2015,15(7):15246-15264. [24]ROTHER C,KOLMOGOROV V,BLAKE A.GrabCut:interactive foreground extraction using iterated graph cuts[J].Acm Transactions on Graphics,2004,23(3):309-314. [25]CHEN X,LI J.Summary of Segmentation Algorithm Based on Graph Theory[J].Computer and Digital Engineering,2016,44(10):2043-2047.(in Chinese)陈杏,李军.基于图论的分割算法研究综述[J].计算机与数字工程,2016,44(10):2043-2047. [26]FEHN C.Depth-image-based rendering (DIBR),compression,and transmission for a new approach on 3D-TV[C]∥Procee-dings of SPIE-The International Society for Optical Enginee-ring.2004:93-104. [27]ZHU C,ZHAO Y,YU L,et al.3D-TV System with Depth-Ima-ge-Based Rendering:Architectures,Techniques and Challenges[M].New York:Springer,2013. |
[1] | 侯春萍, 赵春月, 王致芃. 基于自反馈最优子类挖掘的视频异常检测算法 Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining 计算机科学, 2021, 48(7): 199-205. https://doi.org/10.11896/jsjkx.200800146 |
[2] | 宋昱, 孙文赟. 改进非线性结构张量的含噪图像边缘检测 Edge Detection in Images Corrupted with Noise Based on Improved Nonlinear Structure Tensor 计算机科学, 2021, 48(6): 138-144. https://doi.org/10.11896/jsjkx.200600017 |
[3] | 牛康力, 谌雨章, 张龚平, 谭前程, 王绎冲, 罗美琪. 基于深度学习的无人机航拍车流量监测 Vehicle Flow Measuring of UVA Based on Deep Learning 计算机科学, 2021, 48(6A): 275-280. https://doi.org/10.11896/jsjkx.200900149 |
[4] | 洪睿, 康晓东, 李博, 王亚鸽. 一种基于复杂网络的图像形状及纹理描述方法 Image Shape and Texture Description Method Based on Complex Network 计算机科学, 2018, 45(11A): 244-246. |
[5] | 冯飞,刘培学,李丽,陈玉杰. FCM融合改进的GSA算法在医学图像分割中的研究 Study of FCM Fusing ImprovedGravitational Search Algorithm in Medical Image Segmentation 计算机科学, 2018, 45(6A): 252-254. |
[6] | 祝轩, 王磊, 张超, 梅东锋, 薛珈萍, 曹晴雯. 基于连续性约束背景模型减除的运动目标检测 Moving Object Detection Based on Continuous Constraint Background Model Deduction 计算机科学, 2019, 46(6): 311-315. https://doi.org/10.11896/j.issn.1002-137X.2019.06.047 |
[7] | 宋娅菲, 谌雨章, 沈君凤, 曾张帆. 基于改进残差网络的水下图像重建方法 Underwater Image Reconstruction Based on Improved Residual Network 计算机科学, 2020, 47(6A): 500-504. https://doi.org/10.11896/JsJkx.200100084 |
|