Processing

Please wait...

Settings

Settings

Goto Application

1. CN108062756 - Image semantic division method based on depth full convolution network and condition random field

Office China
Application Number 201810085381.6
Application Date 29.01.2018
Publication Number 108062756
Publication Date 22.05.2018
Grant Number 108062756
Grant Date 14.04.2020
Publication Kind B
IPC
G06T 7/11
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
11Region-based segmentation
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06T 7/11
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
11Region-based segmentation
G06T 2207/20081
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20081Training; Learning
Applicants CHONGQING UNIVERSITY OF TECHNOLOGY
重庆理工大学
Inventors CUI SHAOGUO
崔少国
WANG YONG
王勇
Agents 重庆信航知识产权代理有限公司 50218
Title
(EN) Image semantic division method based on depth full convolution network and condition random field
(ZH) 基于深度全卷积网络和条件随机场的图像语义分割方法
Abstract
(EN)
The invention provides an image semantic division method based on a depth full convolution network and a condition random field. The image semantic division method comprises the following steps: establishing a depth full convolution semantic division network model; carrying out structured prediction based on a pixel label of a full connection condition random field, and carrying out model training, parameter learning and image semantic division. According to the image semantic division method provided by the invention, expansion convolution and a spatial pyramid pooling module are introduced into the depth full convolution network, and a label predication pattern output by the depth full convolution network is further revised by utilizing the condition random field; the expansion convolution is used for enlarging a receptive field and ensures that the resolution ratio of a feature pattern is not changed; the spatial pyramid pooling module is used for extracting contextual features of different scale regions from a convolution local feature pattern, and a mutual relation between different objects and connection between the objects and features of regions with different scales are provided for the label predication; the full connection condition random field is used for further optimizing the pixel label according to feature similarity of pixel strength and positions, so that a semantic division pattern with a high resolution ratio, an accurate boundary and good space continuity is generated.

(ZH)
本发明提供一种基于深度全卷积网络和条件随机场的图像语义分割方法,包括步骤:深度全卷积语义分割网络模型搭建,基于全连接条件随机场的像素标签结构化预测,模型训练与参数学习和图像语义分割。本申请在深度全卷积网络中引入膨胀卷积和空间金字塔池化模块,并对深度全卷积网络输出的标签预测图使用条件随机场进一步修正,膨胀卷积扩大感受野的同时确保特征图分辨率不变,空间金字塔池化模块从卷积局部特征图提取不同尺度区域上下文特征,为标签预测提供不同对象之间相互关系及对象与不同尺度区域特征之间联系,全连接条件随机场根据像素强度和位置的特征相似性对像素标签进一步优化,从而产生分辨率高、边界精确、空间连续性好的语义分割图。