http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : ( Tiantian Qiu ) (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Single Low-Light Ghost-Free Image Enhancement via Deep Retinex Model
( Yan Liu ),( Bingxue Lv ),( Jingwen Wang ),( Wei Huang ),( Tiantian Qiu ),( Yunzhong Chen ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.5
Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.
-
Seismic behavior of steel tube reinforced concrete bridge columns
Tian Tian,Wenliang Qiu,Zhe Zhang 국제구조공학회 2018 Steel and Composite Structures, An International J Vol.28 No.1
This paper reports an experimental study that was accomplished to assess the seismic behavior of steel tube reinforced concrete bridge columns (SBCs). The motivation of this study was to verify a supposition that the core steel tube may be terminated at a rational position in the column to minimize the material cost while maintaining the seismic behavior of this composite column. Four SBC specimens were tested under combined constant axial load and cyclic reversed lateral loads. The unique variable in the test matrix was the core steel tube embedment length, which ranged from 1/3 to 3/3 of the column effective height. It is observed that SBCs showed two distinctly different failure patterns, namely brittle shear failure and ductile flexural failure. Tests results indicate that the hysteretic responses of SBCs were susceptible to the core steel tube embedment length. With the increase of this structural parameter, the lateral strength of SBC was progressively improved; the deformability and ductility, however, exhibited a tendency of first increase and then decrease. It is also found that in addition to maintained the rate of stiffness degradation and cumulative energy dissipation basically unchanged, both the ductility and deformability of SBC were significantly improved when the core steel tube was terminated at the mid-height of the column, and these were the most unexpected benefits accompanied with material cost reduction.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
