基于分数阶网络和强化学习的图像实例分割模型  

Image instance segmentation model based on fractional-order network and reinforcement learning

作　　者：李学明[1] 吴国豪 周尚波[1] 林晓然 谢洪斌[3] LI Xueming;WU Guohao;ZHOU Shangbo;LIN Xiaoran;XIE Hongbin(College of Computer Science,Chongqing University,Chongqing 400044,China;School of Information Technology,Hebei University of Economics and Business,Shijiazhuang Hebei 050061,China;Chongqing Key Laboratory of Exogenic Mineralization and Mine Environment(Chongqing Institute of Geology and Mineral Resources),Chongqing 400042,China)

机构地区：[1]重庆大学计算机学院,重庆400044 [2]河北经贸大学信息技术学院,石家庄050061 [3]外生成矿与矿山环境重庆市重点实验室(重庆地质矿产研究院),重庆400042

出　　处：《计算机应用》2022年第2期574-583,共10页journal of Computer Applications

基　　金：河北省高等学校科学技术研究项目(QN2019069);重庆市自然科学基金面上项目(cstc2019jcyj-msxmX0657)。

摘　　要：针对目前的分数阶非线性模型图像特征提取能力不足导致分割精度较低的问题,提出一种基于分数阶网络和强化学习(RL)的图像实例分割模型,用来分割出图像中目标实例的高质量轮廓曲线。该模型共包含两层模块:1)第一层为二维分数阶非线性网络,主要采用混沌同步方法来获取图像中像素点的基础特征,并通过根据像素点间的相似性进行耦合连接的方式获取初步的图像分割结果;2)第二层通过RL思想将图像实例分割建立为一个马尔可夫决策过程(MDP),并利用建模过程中的动作−状态对、奖励函数和策略的设计来获取图像的区域结构和类别信息。最后将第一层获取到的像素特征和初步的图像分割结果与第二层获取到的区域结构和类别信息联合起来进行实例分割。在Pascal VOC2007和Pascal VOC2012数据集上的实验结果表明,这种基于连续决策的图像实例分割模型与传统的分数阶模型相比,平均精度(AP)至少提升了15个百分点,不仅能够获取图像中目标物体的类别信息,而且进一步提升了对图像轮廓细节和细粒度信息的提取能力。Aiming at the low segmentation precision caused by the lack of image feature extraction ability of the existing fractional-order nonlinear models,an instance segmentation model based on fractional-order network and Reinforcement Learning(RL)was proposed to generate high-quality contour curves of target instances in the image.The model consists of two layers of modules:1)the first layer was a two-dimensional fractional-order nonlinear network in which the chaotic synchronization method was mainly utilized to obtain the basic characteristics of the pixels in the image,and the preliminary segmentation result of the image was acquired through the coupling and connection according to the similarity among the pixels;2)the second layer was to establish instance segmentation as a Markov Decision Process(MDP)based on the idea of RL,and the action-state pairs,reward functions and strategies during the modeling process were designed to extract the region structure and category information of the image.Finally,the pixel features and preliminary segmentation result of the image obtained from the first layer were combined with the region structure and category information obtained from the second layer for instance segmentation.Experimental results on datasets Pascal VOC2007 and Pascal VOC2012 show that compared with the existing fractional-order nonlinear models,the proposed model has the Average Precision(AP)improved by at least 15 percentage points,verifying that the sequential decision-based instance segmentation model not only can obtain the class information of the target objects in the image,but also further enhance the ability to extract contour details and fine-grained information of the image.

关 键 词：强化学习 分数阶网络 混沌同步 混沌吸引子 马尔可夫决策过程 像素−动作策略 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]