摘要
深度学习的发展加快了图像语义分割的研究。目前,最有效的图像语义分割研究方法大部分都是基于全卷积神经网络(FCNN),尽管现有的语义分割方法能有效地对图像进行整体分割,但对于图像中的重叠遮挡物体不能清晰地识别出边缘信息,也不能有效地融合图像高低层的特征信息。针对以上问题,在采用FCNN来解决图像语义分割问题的基础上,利用超像素分割对物体边缘的特殊优势作为辅助优化,对粗糙分割结果进行优化。同时在FCNN中利用空洞卷积设计了一个联合局部跨阶段的多尺度特征融合模块,其能有效地利用图像的空间信息。此外还在网络的上采样模块中加入跳跃连接结构,用来增强网络的学习能力,在训练过程中采用2个损失函数来保证网络稳定收敛和提升网络的性能,图像语义分割网络在公开的数据集PASCALVOC2012上进行训练测试。实验结果表明,该改进算法在像素精度和分割准确率方面均有提升,且具有较强的鲁棒性。
The advancement of deep learning has boosted the research on image semantic segmentation.At present,most effective methods for this research are based on the fully convolutional neural networks.Although the existing semantic segmentation methods can effectively segment the image as a whole,they cannot clearly identify the edge information of the overlapped objects in the image,and cannot effectively fuse the high-and low-layer feature information of the image.To address the above problems,superpixel segmentation was employed as an auxiliary optimization to optimize the segmentation results of object edges based on the fully convolutional neural network.At the same time,the design of a joint cross-stage partial multiscale feature fusion module can enable the utilization of image spatial information.In addition,a skip structure was added to the upsampling module to enhance the learning ability of the network,and two loss functions were adopted to ensure network convergence and improve network performance.The network was trained and tested on the public datasets PASCAL VOC 2012.Compared with other image semantic segmentation methods,the proposed network can improve the accuracies in pixel and segmentation,and displays strong robustness.
作者
官申珂
林晓
郑晓妹
朱媛媛
马利庄
GUAN Shen-ke;LIN Xiao;ZHENG Xiao-mei;ZHU Yuan-yuan;MA Li-zhuang(College of Information,Mechanical and Electrical Engineering,Shanghai Normal University,Shanghai 200234,China;College of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)
出处
《图学学报》
CSCD
北大核心
2021年第3期406-413,共8页
Journal of Graphics
基金
国家自然科学基金项目(61872242)。
关键词
全卷积神经网络
多尺度特征融合
超像素分割
fully convolutional neural network
multiscale feature fusion
superpixel segmentation
