结合超像素分割的多尺度特征融合图像语义分割算法

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...

A semantic segmentation algorithm using multi-scale feature fusionwith combination of superpixel segmentation

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 existingsemantic segmentation methods can effectively segment the image as a whole, they cannot clearly identify the edgeinformation of the overlapped objects in the image, and cannot effectively fuse the high- and low-layer featureinformation of the image. To address the above problems, superpixel segmentation was employed as an auxiliaryoptimization to optimize the segmentation results of object edges based on the fully convolutional neural network. Atthe same time, the design of a joint cross-stage partial multiscale feature fusion module can enable the utilization ofimage 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 networkperformance. The network was trained and tested on the public datasets PASCAL VOC 2012. Compared with otherimage semantic segmentation methods, the proposed network can improve the accuracies in pixel and segmentation,and displays strong robustness.