计算机科学
分割
人工智能
棱锥(几何)
水准点(测量)
卷积神经网络
模式识别(心理学)
图像分割
卷积(计算机科学)
钥匙(锁)
特征(语言学)
领域(数学分析)
机器学习
基于分割的对象分类
人工神经网络
尺度空间分割
光学
物理
语言学
数学分析
哲学
计算机安全
数学
地理
大地测量学
作者
Xiaolong Liu,Zhidong Deng,Yuhan Yang
标识
DOI:10.1007/s10462-018-9641-3
摘要
Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, up-sample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.
科研通智能强力驱动
Strongly Powered by AbleSci AI