%0 Journal Article
%T 基于快速区域建议网络的图像多目标分割算法<br>A new method for muti-objects image segmentation based on faster region proposal networks
%A 黄劲潮
%J 山东大学学报（工学版）
%D 2018
%R 10.6040/j.issn.1672-3961.0.2017.592
%X 摘要： 针对传统方法在语义分割中存在大量冗余、结果重叠,造成图像分割算法的结果正确率、鲁棒性较差等问题,提出一种基于快速区域建议网络的图像多目标分割算法。使用选择性搜索(selective search, SS)算法给出初始候选框;采用快速区域建议网络从初始候选框中分类出初始分割框;使用图割算法(GrabCut)从初始分割框中分割出多目标。为了验证本研究算法,采用ImageNet上预训练的VGG16模型,分别使用COCO数据集和CityScapes数据集的训练数据对VGG16模型微调,使用测试数据进行语义分割和多目标图像分割。与YOLO(you only look once,)算法相比,本算法在两个数据集上的平均正确率分别提高了2.16%和1.55%。GrabCut算法在快速区域建议网络的初始分割框上,对多目标的分割更精确,鲁棒性更强。本研究构建的算法通过区域建议网络的得分筛选多目标分割的候选框,保留高得分的候选框来提升图像多目标分割的精度,在多目标的模式识别场合中拥有广泛前景。<br>Abstract: Aim at the shortage of a large amount of redundancy and overlaps of conventional semantic segmentation algorithm, these shortages caused the image segmentation results getting lower accuracy and robust. A new algorithm of multi-objects image segmentation based on faster region proposal networks was proposed. A selective search algorithm was used to get the initial proposal boxes; a faster region proposal network was used to get initial image segmentation boxes. In order to validate our proposed algorithm, the VGG16 models that pre-trained on ImageNet was used on this problem. By using COCO dataset and Cityscapes dataset, the model was well fine-tuned. The test dataset was used for testing semantic segmentation and image segmentation. Compared with YOLO algorithm, the experimental results showed that our proposed algorithm increased mAP of 2.16% and 1.55%. The initial image segmentation boxes by faster region proposal networks were best fitted by GrabCut, multi-objects segmentation results were more accurate and robust. Our proposed algorithm got higher accuracy by sacrifice little time consumption, which got more application scenes in multi-object patterns recognition
%K GrabCut算法
%K selective search算法
%K 图像分割
%K 多目标分割
%K 快速区域建议网络
%K &lt
%K br&gt
%K GrabCut algorithm
%K faster region proposal network(Faster RPN)
%K selective search algorithm
%K muti-objects segmentation
%K image segmentation
%U http://gxbwk.njournal.sdu.edu.cn/CN/10.6040/j.issn.1672-3961.0.2017.592