[논문]Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion

Lee, Sihaeng; Lee, Janghyeon; Kim, Doyeon; Kim, Junmo

doi:10.1109/access.2020.2990212

[해외논문] Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion 원문보기

IEEE access : practical research, open solutions, v.8, 2020년, pp.79801 - 79810

Lee, Sihaeng (Korea Advanced Institute of Science and Technology, Division of Future Vehicle, Daejeon, South Korea) , Lee, Janghyeon (Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Daejeon, South Korea) , Kim, Doyeon (Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Daejeon, South Korea) , Kim, Junmo (Korea Advanced Institute of Science and Technology, Division of Future Vehicle, Daejeon, South Korea)

Abstract ▼ AI-Helper

It is challenging to apply depth maps generated from sparse laser scan data to computer vision tasks, such as robot vision and autonomous driving, because of the sparsity and noise in the data. To overcome this problem, depth completion tasks have been proposed to produce a dense depth map from sparse LiDAR data and a single RGB image. In this study, we developed a deep convolutional architecture with cross guidance for multi-modal feature fusion to compensate for the lack of representation power of their modality. Two encoders, which are part of the proposed architecture, receive different modalities as inputs. They interact with each other by exchanging information in each stage through the attention mechanism during encoding. We also propose a residual atrous spatial pyramid block, comprising multiple dilated convolutions with different dilation rates, which are used to derive highly significant features. The experimental results of the KITTI depth completion benchmark dataset demonstrate that the proposed architecture shows higher performance than that of the other models trained in a two-dimensional space without pre-training or fine-tuning other datasets.

참고문헌 (39)

10.1109/CVPR.2016.470
10.1109/CVPR.2016.350
Proc Int Conf Med Image Comput Comput -Assist Intervent U-Net: Convolutional networks for biomedical image segmentation ronneberger 0 234
10.1109/CVPR.2017.634
10.1007/978-3-030-01249-6_34
10.1109/CVPR.2017.683
10.1109/3DV.2018.00017
10.1109/ICCV.2015.123
Proc Adv Neural Inf Process Syst (NIPS) PyTorch: An imperative style, high-performance deep learning library paszke 2019 8024
Russakovsky, Olga, Deng, Jia, Su, Hao, Krause, Jonathan, Satheesh, Sanjeev, Ma, Sean, Huang, Zhiheng, Karpathy, Andrej, Khosla, Aditya, Bernstein, Michael, Berg, Alexander C., Fei-Fei, Li. ImageNet Large Scale Visual Recognition Challenge. International journal of computer vision, vol.115, no.3, 211-252.

상세보기
10.1109/CVPR.2017.75
10.1109/CVPR.2019.00326
10.1109/CVPR.2018.00745
Proc Adv Neural Inf Process Syst (NIPS) Spatial transformer networks jaderberg 2015 2017
Proc Adv Neural Inf Process Syst (NIPS) Attention is all you need vaswani 2017 5998
10.1109/CVPR.2018.00813
10.1007/978-3-030-01234-2_1
Proc Int Conf Mach Learn (ICML) Show, attend and tell: Neural image caption generation with visual attention xu 2015 2048
10.1007/978-3-030-01270-0_7
Eldesokey, Abdelrahman, Felsberg, Michael, Khan, Fahad Shahbaz. Confidence Propagation through CNNs for Guided Sparse Depth Regression. IEEE transactions on pattern analysis and machine intelligence, vol.42, no.10, 2423-2436.

상세보기
10.1109/CVPR.2019.00347
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.. Gradient-based learning applied to document recognition. Proceedings of the IEEE, vol.86, no.11, 2278-2324.

상세보기
10.1109/ICCV.2019.00290
Proc Adv Neural Inf Process Syst (NIPS) Imagenet classification with deep convolutional neural networks krizhevsky 2012 1097
10.1109/CVPR.2016.90
10.1109/ICCV.2019.01012
Proc Int Conf Learn Represent (ICLR) Very deep convolutional networks for large-scale image recognition simonyan 2015 1
Chen, Liang-Chieh, Papandreou, George, Kokkinos, Iasonas, Murphy, Kevin, Yuille, Alan L.. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE transactions on pattern analysis and machine intelligence, vol.40, no.4, 834-848.

상세보기
10.1109/CVPR.2015.7298594
10.1109/3DV.2017.00012
Proc Int Conf Learn Represent (ICLR) Multi-scale context aggregation by dilated convolutions yu 2016 1
Geiger, A, Lenz, P, Stiller, C, Urtasun, R. Vision meets robotics: The KITTI dataset. The International journal of robotics research, vol.32, no.11, 1231-1237.

상세보기
10.1109/ICRA.2019.8793637
10.1007/978-3-030-01449-0_38
10.23919/MVA.2019.8757939
10.1109/CRV.2018.00013
10.1109/CVPRW.2012.6238916
10.1109/CVPR.2019.00343
10.1109/CISP.2014.7003768

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 보기

AccessON 원문보기

원문 URL 링크

DOI : 10.1109/ACCESS.2020.2990212 [무료]
IEEE : 저널 > 논문 [무료]
AccessON : 저널

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

오픈액세스(OA) 유형

GOLD

오픈액세스 학술지에 출판된 논문

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증