GPU和格子玻尔兹曼方法联合加速的水平集模型及其在图像分割中的应用  

GPU accelerated level set model solving by lattice boltzmann method with application to image segmentation

作　　者：石文君 王登位[2,3] 刘万锁 蒋大钢 SHI Wen-Jun;WANG Deng-Wei;LIU Wan-Suo;JIANG Da-Gang(Aviation Maintenance School for NCO,Air Force Engineering University,Xinyang 464000,China;School of Aeronautics and Astronautics,University of Electronic Science and Technology of China,Chengdu 611731,China;Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province,Chengdu 611731,China)

机构地区：[1]空军工程大学航空机务士官学校,河南信阳464000 [2]航空航天学院,电子科技大学,四川成都611731 [3]飞行器集群智能感知与协同控制四川省重点实验室,四川成都611731

出　　处：《红外与毫米波学报》2021年第1期108-121,共14页Journal of Infrared and Millimeter Waves

基　　金：the National Natural Science Foundation of China(61501097);the Chinese Fundamental Research Funds for the Central Universities(ZYGX2016J157,ZYGX2018J079,ZYGX2019J080)。

摘　　要：面向图像分割应用,提出了一种新颖的GPU加速水平集模型,将来自于不同模型的全局及局部拟合能量有机地整合一起,并且可以自适应地调整全局项的加权系数。无论初始轮廓位于图像中的任何位置,模型都可以有效地分割出具有强度非同质性图像中的前景目标。在数值实现环节,采用格子玻尔兹曼方法的策略来打破传统求解方法对于时间步长参数的限制条件。另外,借助NVIDIA GPU来高效地组织格子玻尔兹曼方法的数值解算过程,以充分利用格子玻尔兹曼方法所具有的并行特性。在合成及真实图像数据上的实验结果验证了所提方法的有效性。另外,还对影响分割结果的数个关键因素进行了深入的分析。A novel Graphics Processing Units(GPU)accelerated level set model which organically combines the global fitting energy and the local fitting energy from different models and the weighting coefficient of the global fitting term can be adaptively adjusted,is proposed to image segmentation.The proposed model can efficiently segment images with intensity inhomogeneity regardless of where the initial contour lies in the image.In its numerical implementation,an efficient numerical scheme called Lattice Boltzmann Method(LBM)is used to break the restrictions on time step.In addition,the proposed LBM is implemented by using a NVIDIA GPU to fully utilize the characteristics of LBM method with high parallelism.The extensive and promising experimental results from synthetic and real images demonstrate the effectiveness and efficiency of the proposed method.In addition,the factors that can have a key impact on segmentation performance are also analyzed in depth.

关 键 词：强度非同质性 水平集方法 分割 格子玻尔兹曼方法 图形处理单元. 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]