Semantic annotation for complex video street views based on 2D-3D multi-feature fusion and aggregated boosting decision forests

网站地图 | English | 公务邮箱

About the library

Background
History
Leadership
Organization

Opening Hours
Collections
Help Via Email

Electronic Information Resources

Semantic annotation for complex video street views based on 2D-3D multi-feature fusion and aggregated boosting decision forests

详细信息查看全文

作者：Xun Wang^a ; ^{wx@zjgsu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Guoli Yan^a ; ^{1327237426@qq.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Huiyan Wang^a ; ^{cederic@zjgsu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jianhai Fu^a ; ^{15138469880@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jing Hua^a ; ^b ; ^{jinghua@wayne.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jingqi Wang^c ; ^{wangjingqi555@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yutao Yang^a ; ^{1121082097@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Guofeng Zhang^d ; ^{zhangguofeng@cad.zju.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Hujun Bao^d ; ^{bao@cad.zju.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
关键词：Semantic annotation ; Superpixel segmentation ; 2D&ndash ; 3D feature fusion ; ABDF model
刊名：Pattern Recognition
出版年：2017
出版时间：February 2017
年：2017
卷：62
期：Complete
页码：189-201
全文大小：4820 K

文摘

class="label">•: 2D and 3D superpixel features for object representation.
class="label">•: A modified aggregated boosting decision forest for fast and accurate classification.
class="label">•: Only a small amount of samples for building classification model.
class="label">•: An effective tool for accurate and efficient semantic annotation of complex street views.
class="label">•: Better performance in accuracy, robustness and computation efficiency.

NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.