基于多尺度特征提取和全连接条件随机场的图像语义分割方法

Image Semantic Segmentation Based on Multi-Scale Feature Extraction and Fully Connected Conditional Random Fields

针对图像语义分割中图像的上下文信息利用不充分、边缘分割不清等问题,提出一种基于多尺度特征提取与全连接条件随机场的网络模型。分别以多尺度形式将RGB图像和深度图像输入网络,利用卷积神经网络提取图像特征;将深度信息作为补充信息添加到RGB特征图,得到语义粗分割结果;采用全连接条件随机场优化语义粗分割结果,最终得到语义精细分割结果。实验结果表明,所提方法提高了图像语义分割的精度,优化了图像语义分割的边缘,具有实际应用价值。

Aiming at the problems of insufficient usage of context information and unclear image edge segmentation in image semantic segmentation, a network model based on multi-scale feature extraction and fully connected conditional random fields is proposed. RGB and depth images are input into the network in a multi-scale form, and their features are extracted by a Convolutional neural network. Depth information is added to supplement the RGB feature map and obtain a rough semantic segmentation, which is optimized by the fully connected conditional random fields. Finally, fine semantic segmentation results are obtained. This proposed method improves the precision of semantic segmentation and optimizes the image edge segmentation, which has a practical application.