检索结果-南通市图书馆

Semisupervised learning-based depth estimation with semantic inference guidance

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第5期65卷 1098-1106页

作者： ZHANG Yan FAN XiaoPeng ZHAO DeBin Department of Computer Science and Technology Harbin Institute of TechnologyHarbin150001China

depth estimation is a fundamental computer vision problem that infers three-dimensional(3D)structures from a given *** it is an ill-posed problem,to fit the projection function from the given scene to the 3D structure,traditional methods generally require mass amounts of annotated *** pixel-level annotation is quite labor consuming,especially when addressing reflective surfaces such as mirrors or *** widespread application of deep learning further intensifies the demand for large amounts of annotated ***,it is urgent and necessary to propose a framework that is able to reduce the requirement on the amount of *** this paper,we propose a novel semisupervised learning framework to infer the 3D structure from the given ***,semantic information is employed to make the depth inference more ***,we make both the depth estimation and semantic segmentation coarse-to-fine frameworks;thus,the depth estimation can be gradually guided by semantic *** compare our model with state-of-the-art *** experimental results demonstrate that our method is better than many supervised learning-based methods,which proves the effectiveness of the proposed method.

关键词： depth estimation semisupervised learning semantic information neural networks

depth estimation system suitable for hardware design

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai University(English Edition) 2011年第4期15卷 325-330页

作者：李贺建左一帆杨高波安平王建伟滕国伟 Key Laboratory of Advanced (Shanghai University) Display and System Application Ministry of EducationShanghai 200072P.R.China College of Computer and Communication Hunan UniversityChangsha 410082P.R.China School of Communication and Information Engineering Shanghai UniversityShanghai 200072P.R.China

depth estimation is an active research area with the developing of stereo vision in recent years. It is one of the key technologies to resolve the large data of stereo vision communication. Now depth estimation still has some problems, such as occlusion, fuzzy edge, real-time processing, etc. Many algorithms have been proposed base on software, however the performance of the computer configurations limits the software processing speed. The other resolution is hardware design and the great developments of the digital signal processor （DSP）, and application specific integrated circuit （ASIC） and field programmable gate array （FPGA） provide the opportunity of flexible applications. In this work, by analyzing the procedures of depth estimation, the proper algorithms which can be used in hardware design to execute real-time depth estimation are proposed. The different methods of calibration, matching and post-processing are analyzed based on the hardware design requirements. At last some tests for the algorithm have been analyzed. The results show that the algorithms proposed for hardware design can provide credited depth map for further view synthesis and are suitable for hardware design.

关键词： 3-D TV (3DTV) depth estimation hardware design rank transform census transform

On Robust Cross-view Consistency in Self-supervised Monocular depth estimation

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第3期21卷 495-513页

作者： Haimei Zhao Jing Zhang Zhuo Chen Bo Yuan Dacheng Tao School of Computer Science University of SydneySydney2008Australia Shenzhen International Graduate School Tsinghua UniversityShenzhen518055China School of Information Technology&Electrical Engineering University of QueenslandBrisbane4072Australia

Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric consistency and 3D point cloud consistency. However, they are very vulnerable to illumination variance, occlusions, texture-less regions, as well as moving objects, making them not robust enough to deal with various scenes. To address this challenge, we study two kinds of robust cross-view consistency in this paper. Firstly, the spatial offset field between adjacent frames is obtained by reconstructing the reference frame from its neighbors via deformable alignment, which is used to align the temporal depth features via a depth feature alignment (DFA) loss. Secondly, the 3D point clouds of each reference frame and its nearby frames are calculated and transformed into voxel space, where the point density in each voxel is calculated and aligned via a voxel density alignment (VDA) loss. In this way, we exploit the temporal coherence in both depth feature space and 3D voxel space for SS-MDE, shifting the “point-to-point” alignment paradigm to the “region-to-region” one. Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques. Extensive ablation study and analysis validate the effectiveness of the proposed losses, especially in challenging scenes. The code and models are available at https://***/sunnyHelen/RCVC-depth.

关键词： 3D vision depth estimation cross-view consistency self-supervised learning monocular perception

Semi-Global depth estimation Algorithm for Mobile 3-D Video Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2012年第2期17卷 128-135页

作者： Qiong Liu Hongjiang Xiao Department of Automation Tsinghua UniversityBeijing 100084China Department of Electronics and Information Engineering Huazhong University of Science and TechnologyWuhan 430074China Academy of Broadcasting Planning SARFT Beijing 100866China

Three-dimensional （3-D） video applications, such as 3-D cinema, 3DTV, ana Free Viewpomt Video （FVV） are attracting more attention both from the industry and in the literature. High accuracy of depth video is a fundamental prerequisite for most 3-D applications. However, accurate depth requires computationally intensive global optimization. This high computational complexity is one of the bottlenecks to applying depth generation to 3-D applications, especially for mobile networks since mobile terminals usually have limited computing ability. This paper presents a semi-global depth estimation algorithm based on temporal consis- tency, where the depth propagation is used to generate initial depth values for the computationally intensive global optimization. The accuracy of initial depth is improved by detecting and eliminating the depth propagation outliers before the global optimization. Integrating the initial values without outliers into the global optimization reduces the computational complexity while maintaining the depth accuracy. Tests demonstrate that the algorithm reduces the total computational time by 54%-65% while the quality of the virtual views is essentially equivalent to the benchmark.

关键词： 3-D video depth estimation temporal propagation graph cuts

Light field depth estimation:A comprehensive survey from principles to future

在线全文

学校读者我要写书评

暂无评论

High-Confidence Computing 2024年第1期4卷 92-107页

作者： Tun Wang Hao Sheng Rongshan Chen Da Yang Zhenglong Cui Sizhe Wang Ruixuan Cong Mingyuan Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Zhongfa Aviation Institute Beihang UniversityHangzhou 311115China Faculty of Applied Sciences Macao Polytechnic UniversityMacao 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Light Field(LF)depth estimation is an important research direction in the area of computer vision and computational photography,which aims to infer the depth information of different objects in threedimensional scenes by capturing LF *** this new era of significance,this article introduces a survey of the key concepts,methods,novel applications,and future trends in this *** summarize the LF depth estimation methods,which are usually based on the interaction of radiance from rays in all directions of the LF data,such as epipolar-plane,multi-view geometry,focal stack,and deep *** analyze the many challenges facing each of these approaches,including complex algorithms,large amounts of computation,and speed *** addition,this survey summarizes most of the currently available methods,conducts some comparative experiments,discusses the results,and investigates the novel directions in LF depth estimation.

关键词： Light field depth estimation Deep learning Sub-aperture image Epipolar-plane image

depth estimation from a Single Image Based on Cauchy Distribution Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2021年第3期9卷 133-142页

作者： Ying Ming College of Politics National Defense University of PLA Shanghai China

Most approaches to estimate a scene’s 3D depth from a single image often model the point spread function (PSF) as a 2D Gaussian function. However, those methods are suffered from some noises, and difficult to get a high quality of depth recovery. We presented a simple yet effective approach to estimate exactly the amount of spatially varying defocus blur at edges, based on a Cauchy distribution model for the PSF. The raw image was re-blurred twice using two known Cauchy distribution kernels, and the defocus blur amount at edges could be derived from the gradient ratio between the two re-blurred images. By propagating the blur amount at edge locations to the entire image using the matting interpolation, a full depth map was then recovered. Experimental results on several real images demonstrated both feasibility and effectiveness of our method, being a non-Gaussian model for DSF, in providing a better estimation of the defocus map from a single un-calibrated defocused image. These results also showed that our method was robust to image noises, inaccurate edge location and interferences of neighboring edges. It could generate more accurate scene depth maps than the most of existing methods using a Gaussian based DSF model.

关键词： depth estimation depth From Defocus Defocus Blur Gaussian Gradient Cauchy Distribution Point Spread Function (PSF)

Fault depth estimation using support vector classifier and features selection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Applied Geophysics 2013年第1期10卷 88-96,119页

作者： Mohammad Ehsan Hekmatian Vahid E. Ardestani Mohammad Ali Riahi Ayyub Memar Koucheh Bagh Jalal Amini Faculty of Basic Sciences of Science and Research Branch Islamic Azad University Nuclear Fuel Cycle Research School of Nuclear Science & Technology Research Institute (NSTRI) Institute of Geophysics University of Tehran Faculty of Engineering University of Tehran

depth estimation of subsurface faults is one of the problems in gravity interpretation. We tried using the support vector classifier （SVC） method in the estimation. Using forward and nonlinear inverse techniques, detecting the depth of subsurface faults with related error is possible but it is necessary to have an initial guess for the depth and this initial guess usually comes from non-gravity data. We introduce SVC in this paper as one of the tools for estimating the depth of subsurface faults using gravity data. We can suppose that each subsurface fault depth is a class and that SVC is a classification algorithm. To better use the SVC algorithm, we select proper depth estimation features using a proper features selection （FS） algorithm. In this research, we produce a training set consisting of synthetic gravity profiles created by subsurface faults at different depths to train the SVC code to estimate the depth of real subsurface faults. Then we test our trained SVC code by a testing set consisting of other synthetic gravity profiles created by subsurface faults at different depths. We also tested our trained SVC code using real data.

关键词： depth estimation subsurface fault support vector classifier feature featuresselection

Dense depth estimation with Absolute Scale

在线全文

学校读者我要写书评

暂无评论

Dense Depth Estimation with Absolute Scale

Deep Multi-scale Convolutional Neural Network Method for depth estimation from a Single Image

第37届中国控制会议

作者： Xing Jin Zhiwen Yao Jingjing Zhang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Considering the difficulties in estimating depth from single image, in this paper, we propose a method to obtain the absolute scale depth map by combining the convolution neural network and depth filter. We compute relative transformation between consecutive frames by direct tracking features, which are extracted from RGB images and whose depthes are predicted by deep network, and then optimize relative motion by searching for a better feature alignment in epipolar line, and finally update every pixel depth of the reference frame by depth filter. We evaluate the proposed method on the open dataset comparison against the state of the art in depth estimation to evaluate our method.

关键词： depth estimation Pose estimation depth Filter

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Deep Multi-scale Convolutional Neural Network Method for Dep...