自适应分割的视频点云多模式帧间编码方法  

An Adaptive Segmentation Based Multi-mode Inter-frame Coding Method for Video Point Cloud

作　　者：陈建[1,2] 廖燕俊 王适 郑明魁[1,2] 苏立超 CHEN Jian;LIAO Yan-Jun;WANG Kuo;ZHENG Ming-Kui;SU Li-Chao(School of Advanced Manufacturing,Fuzhou University,Quanzhou 362251;College of Physics and Information Engineering,Fuzhou University,Fuzhou 350116;College of Computer and Data Science/College of Software,Fuzhou University,Fuzhou 350116)

机构地区：[1]福州大学先进制造学院,泉州362251 [2]福州大学物理与信息工程学院,福州350116 [3]福州大学计算机与大数据学院/软件学院,福州350116

出　　处：《自动化学报》2023年第8期1707-1722,共16页Acta Automatica Sinica

基　　金：国家自然科学基金(62001117,61902071);福建省自然科学基金(2020J01466);中国福建光电信息科学与技术创新实验室(闽都创新实验室)(2021ZR151);超低延时视频编码芯片及其产业化(2020年福建省教育厅产学研专项)资助。

摘　　要：基于视频的点云压缩(Video based point cloud compression, V-PCC)为压缩动态点云提供了高效的解决方案,但V-PCC从三维到二维的投影使得三维帧间运动的相关性被破坏,降低了帧间编码性能.针对这一问题,提出一种基于V-PCC改进的自适应分割的视频点云多模式帧间编码方法,并依此设计了一种新型动态点云帧间编码框架.首先,为实现更精准的块预测,提出区域自适应分割的块匹配方法以寻找最佳匹配块;其次,为进一步提高帧间编码性能,提出基于联合属性率失真优化(Rate distortion optimization, RDO)的多模式帧间编码方法,以更好地提高预测精度和降低码率消耗.实验结果表明,提出的改进算法相较于V-PCC实现了-22.57%的BD-BR (Bjontegaard delta bit rate)增益.该算法特别适用于视频监控和视频会议等帧间变化不大的动态点云场景.Video based point cloud compression(V-PCC)provides an efficient solution for compressing dynamic point clouds,but the projection of V-PCC from 3D to 2D destroys the correlation of 3D inter-frame motion and reduces the performance of inter-frame coding.To solve this problem,we proposes an adaptive segmentation based multi-mode inter-frame coding method for video point cloud to improve V-PCC,and designs a new dynamic point cloud inter-frame encoding framework.Firstly,in order to achieve more accurate block prediction,a block matching method based on adaptive regional segmentation is proposed to find the best matching block;Secondly,in order to further improve the performance of inter coding,a multi-mode inter-frame coding method based on joint attribute rate distortion optimization(RDO)is proposed to increase the prediction accuracy and reduce the bit rate consumption.Experimental results show that the improved algorithm proposed in this paper achieves−22.57%Bjontegaard delta bit rate(BD-BR)gain compared with V-PCC.The algorithm is especially suitable for dynamic point cloud scenes with little change between frames,such as video surveillance and video conference.

关 键 词：点云压缩 基于视频的点云压缩 三维帧间编码 点云分割 率失真优化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]