中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Omnidirectional Depth Estimation With Hierarchical Deep Network for Multi-Fisheye Navigation Systems

文献类型：期刊论文

作者Su, Xiaojie1; Liu, Shimin1; Li, Rui2
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2023-07-25
页码12
关键词Feature extraction Cameras Estimation Task analysis Navigation Costs Semantics Omnidirectional depth estimation hierarchical deep network multi-fisheye navigation system
ISSN号1524-9050
DOI10.1109/TITS.2023.3294642
通讯作者Li, Rui(rui.li@ia.ac.cn)
英文摘要Multi-fisheye System has the advantages of sufficient overlap and the ability to capture a complete 360 $<^>{\circ}$ scene, which is beneficial for the omnidirectional depth estimation task. However, due to the severe distortion of the fisheye images, it is hard for such systems to extract and match features to predict an accurate depth. In this work, on the basis of a multi-fisheye system, we present a novel end-to-end deep learning architecture for omnidirectional depth estimation: 1) to capture the reliable features of the distorted fisheye image, a multi-scale feature extraction and aggregation module is improved, which can adaptively obtain the global context information to represent the features; 2) to leverage more aligned features, especially those in the overlap between multi-fisheye images, we construct a fusion cost volume to combine similarity and semantic information, which can enhance the feature discriminability; and 3) to refine the omnidirectional depth map efficiently, a cascaded cost regularization architecture is proposed. Instead of several costly 3D convolutions, the 3D BSConv based on intra-kernel correlations is introduced to regularize the cost. The proposed method can incrementally predict the depth map from coarse to fine, and reduce the network computational complexity significantly. The experiments in several public indoor and outdoor synthetic datasets demonstrate that the proposed method outperforms some state-of-the-art methods in terms of a synthesis of accuracy and speed, with fewer model parameters.
资助项目National Key Research and Development Program of China[2022YFE0107300] ; National Natural Science Foundation of China[62003059] ; Chongqing Human Resources and Social Bureau[cx2022064] ; Graduate Research and Innovation Foundation of Chongqing, China[CYS22117]
WOS研究方向Engineering ; Transportation
语种英语
WOS记录号WOS:001040607300001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Chongqing Human Resources and Social Bureau ; Graduate Research and Innovation Foundation of Chongqing, China
源URL[http://ir.ia.ac.cn/handle/173211/53858]  
专题多模态人工智能系统全国重点实验室
通讯作者Li, Rui
作者单位1.Chongqing Univ, Sch Automat, Chongqing 400044, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Su, Xiaojie,Liu, Shimin,Li, Rui. Omnidirectional Depth Estimation With Hierarchical Deep Network for Multi-Fisheye Navigation Systems[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2023:12.
APA Su, Xiaojie,Liu, Shimin,&Li, Rui.(2023).Omnidirectional Depth Estimation With Hierarchical Deep Network for Multi-Fisheye Navigation Systems.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12.
MLA Su, Xiaojie,et al."Omnidirectional Depth Estimation With Hierarchical Deep Network for Multi-Fisheye Navigation Systems".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2023):12.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。