摘要
针对卷积神经网络在多卷积层叠加造成的图像内小尺度目标丢失和类别边界模糊问题,提出一种基于多尺度特征融合和边界优化的阶梯型图像语义分割网络结构。该网络以提升网络模型的准确率为目标,对Deeplab V3+网络中空间池化金字塔模块进行优化,使用针对视觉任务的新激活函数Funnel ReLU(FReLU)替换原有非线性激活函数获取精度补偿,增添优化分支构建阶梯型网络,通过对各类别边界的精确预测提升整体图像分割准确率,减少预测结果中类内误识别和小尺度目标丢失问题。在Cityscapes数据集上的实验结果表明,改进后的网络各类别平均交并比指标均取得明显提升。
About the problem that multiple convolution layers used on convolutional neural networks can cause the loss of small-scale targets in the image and the blurring of category boundaries.A stepped image semantic segmentation network structure based on multi-scale feature fusion and boundary optimization is proposed.The network aims to improve the accuracy of the network model,the spatial pooling pyramid module in the Deeplab V3+network is optimized,and using the new activation function Funnel ReLU(FReLU)for the vision task to replace the original nonlinear activation function,which obtains accuracy compensation.Adding the optimization branch to build a ladder network and accurately predicting the boundaries of each category are used to improve the overall image segmentation accuracy and reduce the problem of the misrecognition within the category and the loss of small-scale targets in the prediction results.The experimental result on the Cityscapes dataset shows that the mean intersection over the improved network union has been significantly improved.
作者
李鑫
张红英
刘汉玉
LI Xin;ZHANG Hongying;LIU Hanyu(School of Information Engineering,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China;Robot Technology Used for Special Environment Key Laboratory of Sichuan Province,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China)
出处
《计算机工程与应用》
CSCD
北大核心
2022年第21期250-257,共8页
Computer Engineering and Applications
基金
国家部委科工局项目。
关键词
语义分割
卷积神经网络
边界优化
Deeplab
V3+
精度补偿
semantic segmentation
convolutional neural network
boundary optimization
Deeplab V3+
accuracy compensation
