Coding Scheme for Compressive Sensing Depth Video Based on Adaptive Bits Allocation
WANG Kang1, LAN Xuguang1, LI Xiangwei2
1.Institute of Artificial Intelligence and Robotics, Xi′an Jiaotong University, Xi′an 710049 2.Xi′an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi′an 710049
Abstract By utilizing the compressive sensing in the depth video, the compressive sensing depth video(CSDV) is obtained. However, the redundancy of CSDV is still huge. A coding scheme for compressive sensing depth video(CSDV) based on Gaussian mixture models(GMM) and object edges is proposed. Firstly, the compressive sensing(CS) is utilized to compress 8 depth frames to acquire a CSDV frame in the temporal direction. A whole CSDV frame is divided into a set of non-overlap patches, and object edges in the patches are detected by Canny operator to reduce the computational complexity of quantization. Then, variable bits for different patches are allocated based on the percentages of non-zero pixels in every patch. The GMM is employed to model the CSDV frame patches and design product vector quantizers to quantize CSDV frames.
Fund:Supported by Key Projects of Tri-Co-Robots Plan of National Natural Science Foundation of China(No.91748208), National Natural Science Foundation of China(No.61573268), National Key R&D Program of China(2016YFB1000903)
Corresponding Authors:
LAN Xuguang(Corresponding author), Ph.D., professor. His research interests include computer vision, deep learning and pattern recognition.
About author:: WANG Kang, master student. His research interests include compressive sensing and depth video;LI Xiangwei, Ph.D., researcher. His research interests include image/video proce-ssing, compressive sensing and scalable video coding.
[1] SARKIS M, DIEPOLD K. Depth Map Compression via Compressed Sensing // Proc of the 16th IEEE International Conference on Image Processing. Washington, USA: IEEE, 2009: 737-740. [2] OH B T, LEE J, PARK D. Depth Map Coding Based on Synthesized View Distortion Function. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(7): 1344-1352. [3] LIU H X, SONG B, TIAN F, et al. Joint Sampling Rate and Bit-depth Optimization in Compressive Video Sampling. IEEE Transactions on Multimedia, 2014, 16(6): 1549-1562. [4] SHEN G, KIM W S, ORTEGA A, et al. Edge-Aware Intra Prediction for Depth-Map Coding // Proc of the 17th IEEE International Conference on Image Processing. Washington, USA: IEEE, 2010: 3393-3396. [5] OH K J, VETRO A, HO Y S. Depth Coding Using a Boundary Reconstruction Filter for 3-D Video Systems. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(3): 350-359. [6] MORVAN Y, DE WITH P H N, FARIN D. Platelet-Based Coding of Depth Maps for the Transmission of Multiview Images. Procee-dings of SPIE, 2006. DOI: 10.1117/12.642666. [7] MULLER K, MERKLE P, TECH G, et al. 3D Video Coding with Depth Modeling Modes and View Synthesis Optimization[C/OL]. [2017-12-20]. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6411814. [8] 王相海,付明哲,宋传鸣.三维小波八叉体分裂视频编码算法.模式识别与人工智能, 2015, 28(8): 702-709. (WANG X H, FU M Z, SONG C M. 3D Wavelet Octcube Split Video Coding Algorithm. Pattern Recognition and Artificial Intelligence, 2015, 28(8), 702-709.) [9] CANDÈS E J. Compressive Sampling // Proc of the International Congress of Mathematicians. Berlin, Germany: Springer, 2006, III: 1433-1452. [10] CANDÈS E J, WAKIN M B. An Introduction to Compressive Sampling. IEEE Signal Processing Magazine, 2008, 25(2): 21-30. [11] DONOHO D L. Compressed Sensing. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306. [12] YANG J B, YUAN X, LIAO X J, et al. Video Compressive Sensing Using Gaussian Mixture Models. IEEE Transactions on Image Processing, 2014, 23(11): 4863-4878. [13] YANG J B, YUAN X, LIAO X J, et al. Gaussian Mixture Model for Video Compressive Sensing // Proc of the 20th IEEE International Conference on Image Processing. Washington, USA: IEEE, 2013: 19-23. [14] 赵泉华,张洪云,赵雪梅,等.邻域约束高斯混合模型的模糊聚类图像分割.模式识别与人工智能, 2017, 30(3): 214-223. (ZHAO Q H, ZHANG H Y, ZHAO X M, et al. Fuzzy Clustering Image Segmentation Based on Neighborhood Constrained Gaussian Mixture Model. Pattern Recognition and Artificial Intelligence, 2017, 30(3): 214-223.) [15] LI X W, LAN X G, YANG M, et al. Efficient Compressive Sen-sing Video Compression Method Based on Gaussian Mixture Models // Proc of the International Conference on Visual Communications and Image Processing. Washington, USA: IEEE, 2016. DOI: 10.1109/VCIP.2016.7805535. [16] LI X W, LAN X G, YANG M, et al. Efficient Lossy Compression for Compressive Sensing Acquisition of Images in Compressive Sensing Imaging Systems. Sensors, 2014, 14(12): 23398-23418. [17] LI X W, LAN X G, YANG M, et al. A New Compressive Sensing Video Coding Framework Based on Gaussian Mixture Model. Signal Processing: Image Communication, 2017, 55: 66-79. [18] YANG J B, LIAO X J, CHEN M H, et al. Compressive Sensing of Signals from a GMM with Sparse Precision Matrices // Proc of the 27th International Conference on Neural Information Processing Systems. Berlin, Germany: Springer, 2014, II: 3194-3202. [19] SUBRAMANIAM A D, RAO B D. PDF Optimized Parametric Vector Quantization of Speech Line Spectral Frequencies. IEEE Transactions on Speech and Audio Processing, 2003, 11(2): 130-142. [20] GERSHO A, GRAY R M. Vector Quantization and Signal Compression. Berlin, Germany: Springer Science & Business Media, 2012.
2018, Vol. 31 
