Image semantic segmentation algorithm based on a multi-expert system

计算机科学 分割 人工智能 联营 帕斯卡(单位) 模式识别(心理学) 棱锥(几何) 卷积神经网络 图像分割 尺度空间分割 基于分割的对象分类 特征(语言学) 机器学习 数学 语言学 哲学 几何学 程序设计语言
作者
Sugang Ma,Zhao Ziyi,Zhiqiang Hou,Xiaobao Yang
出处
期刊:Journal of Electronic Imaging [SPIE]
卷期号:32 (03) 被引量:1
标识
DOI:10.1117/1.jei.32.3.033024
摘要

Deeplab series semantic segmentation algorithms extract target semantic features using deep layers of a convolutional neural network, resulting in target features lacking detailed information, such as edges and shapes extracted by shallow layers. Deeplabv3plus uses atrous convolution to obtain feature maps, which lose some image information. All of the above have an impact on segmentation performance improvement. In response to these issues, which reduce segmentation performance, we propose an image semantic segmentation algorithm based on a multi-expert system that builds multiple expert models based on the Deeplabv3plus network architecture. For the target image, each expert model makes independent judgments, and the segmentation results are obtained through the ensemble learning of these expert models. Expert model 1 employs the proposed attention-based atrous spatial pyramid pooling (C-ASPP) module to capture richer global semantic information via a parallel attention mechanism and ASSP module. Expert model 2 designs a feature fusion-based decoder that uses a feature fusion approach to obtain detailed information. Expert model 3 introduces a loss function in the Deeplabv3plus network for supervised detailed information loss. The final segmentation results are generated by adjudicating the results derived by the different expert models, which improves the segmentation performance by compensating for the loss of detailed information and enhancing the semantic features. Evaluated on the commonly used semantic segmentation datasets PASCAL VOC 2012 and CamVid, the algorithm's mIoU reached 82.42% and 69.18%, respectively, which were 2.46% and 1.82% higher than Deeplabv3plus, proving the better segmentation performance of the algorithm.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
愉快的新波完成签到,获得积分10
1秒前
3秒前
3秒前
3秒前
3秒前
完美世界应助zlttt采纳,获得10
5秒前
momo发布了新的文献求助10
7秒前
漫山完成签到,获得积分10
7秒前
量子星尘发布了新的文献求助10
7秒前
8秒前
9秒前
10秒前
阿斗发布了新的文献求助10
11秒前
11秒前
踏实的火龙果完成签到 ,获得积分20
11秒前
健忘白完成签到,获得积分10
13秒前
ding应助liang采纳,获得30
14秒前
厉害tt完成签到,获得积分10
14秒前
14秒前
ding应助momo采纳,获得10
14秒前
在水一方应助吧啦吧啦采纳,获得10
14秒前
踏实的火龙果关注了科研通微信公众号
15秒前
维尼发布了新的文献求助20
16秒前
文档发布了新的文献求助10
16秒前
Rondab应助千余采纳,获得10
20秒前
20秒前
taowang发布了新的文献求助30
20秒前
一支笔画天下完成签到 ,获得积分10
20秒前
21秒前
CL完成签到 ,获得积分10
22秒前
hnlgdx完成签到,获得积分20
22秒前
Dotson发布了新的文献求助20
22秒前
出门见喜发布了新的文献求助10
24秒前
丁老三完成签到 ,获得积分10
25秒前
gky完成签到,获得积分10
26秒前
28秒前
嘻哈完成签到,获得积分10
29秒前
火力全开发布了新的文献求助10
30秒前
taowang完成签到,获得积分10
34秒前
地表飞猪应助科研通管家采纳,获得10
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989297
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253893
捐赠科研通 3270097
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809158