检索结果-南通市图书馆

Pipeline scene reconstruction Based on Image Mosaicing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Pipeline Scene Reconstruction Based on Image Mosaicing

Towards Domain-agnostic Depth Completion

第37届中国控制会议

作者： Zishu Gao En Li Lei Yang Zize Liang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences The University of Chinese Academy of Sciences

Robots should be able to perceive the surroundings in the complicated and unknown environment before carrying out further ***,environmental reconstruction is the premise for the robot autonomous *** this paper,a pipeline scene reconstruction method based on image mosaicing is proposed for cylindrical pipeline *** a wide-angle camera,the image sequence of the pipeline environment is *** order to obtain intuitional environmental information around the pipeline,an unwrapped model is proposed to unfold the distorted raw image to corrected flat surface *** utilizing ORB（Oriented FAST and Rotated BRIEF） and weighted smoothing blending algorithm,image mosaicing with sequence frames are performed to realize scene *** experimental results demonstrate that the proposed algorithm can achieve seamless stitching of pipeline image,and the number of keypoints is prominently decreased in comparison to that of FAST operator,while the quality of keypoints is *** with the classical SIFT and SURF operator,the time-consuming of the algorithm is improved about 2.5 times,which is more suitable for real-time environmental reconstruction.

关键词： scene reconstruction image unwrapping ORB image mosaicing

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

Machine Intelligence Research 2024年第4期21卷 652-669页

作者： Guangkai Xu Wei Yin Jianming Zhang Oliver Wang Simon Niklaus Simon Chen Jia-Wang Bian Zhejiang University Hangzhou 310058China DaJiang Technology Shenzhen 518057China Adobe Research California 95110USA University of Oxford Oxford OX12JDUK

Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task *** present a method to complete sparse/semi-dense,noisy,and potentially low-resolution depth maps obtained by various range sensors,including those in modern mobile phones,or by multi-view reconstruction *** method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets,the output of which is used as an input to our *** propose an effective training scheme where we simulate various sparsity patterns in typical task *** addition,we design two new benchmarks to evaluate the generalizability and robustness of depth completion *** simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods,introducing a practical solution to highqualitydepthcapture onamobile device.

关键词： Monocular depth estimation depth completion zero-shot generalization scene reconstruction neural network.

Real-Time Dense reconstruction of Indoor scene

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第9期68卷 3713-3724页

作者： Jinxing Niu Qingsheng Hu Yi Niu Tao Zhang Sunil Kumar Jha Institute of Mechanics North China University of Water Resources and Electric PowerZhengzhou450011China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow100031Poland

Real-time dense reconstruction of indoor scenes is of great research value for the application and development of service robots,augmented reality,cultural relics conservation and other ***-SLAM2 method is one of the excellent open source algorithms in visual SLAM system,which is often used in indoor scene ***,it is time-consuming and can only build sparse scene map by using ORB features to solve camera *** view of the shortcomings of ORB-SLAM2 method,this article proposes an improved ORB-SLAM2 solution,which uses a direct method based on light intensity to solve the camera *** can greatly reduce the amount of computation,the speed is significantly improved by about 5 times compared with the ORB feature method.A parallel thread of map reconstruction is added with surfel model,and depth map and RGB map are fused to build the dense map.A Realsense D415 sensor is used as RGB-D cameras to obtain the three-dimensional(3D)point clouds of an indoor *** calibration and alignment processing,the sensor is applied in the reconstruction experiment of indoor scene with the improved ORB-SLAM2 *** show that the improved ORB-SLAM2 algorithm cause a great improvement in processing speed and reconstructing density of scenes.

关键词： scene reconstruction improved ORB-SLAM2 direct method surfel

Optimized CUDA Implementation to Improve the Performance of Bundle Adjustment Algorithm on GPUs

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 Software Engineering and Applications 2024年第4期17卷 172-201页

作者： Pranay R. Kommera Suresh S. Muknahallipatna John E. McInroy Department of Electrical Engineering and Computer Science University of Wyoming Laramie Wyoming USA

The 3D reconstruction pipeline uses the Bundle Adjustment algorithm to refine the camera and point parameters. The Bundle Adjustment algorithm is a compute-intensive algorithm, and many researchers have improved its performance by implementing the algorithm on GPUs. In the previous research work, “Improving Accuracy and Computational Burden of Bundle Adjustment Algorithm using GPUs,” the authors demonstrated first the Bundle Adjustment algorithmic performance improvement by reducing the mean square error using an additional radial distorting parameter and explicitly computed analytical derivatives and reducing the computational burden of the Bundle Adjustment algorithm using GPUs. The naïve implementation of the CUDA code, a speedup of 10× for the largest dataset of 13,678 cameras, 4,455,747 points, and 28,975,571 projections was achieved. In this paper, we present the optimization of the Bundle Adjustment algorithm CUDA code on GPUs to achieve higher speedup. We propose a new data memory layout for the parameters in the Bundle Adjustment algorithm, resulting in contiguous memory access. We demonstrate that it improves the memory throughput on the GPUs, thereby improving the overall performance. We also demonstrate an increase in the computational throughput of the algorithm by optimizing the CUDA kernels to utilize the GPU resources effectively. A comparative performance study of explicitly computing an algorithm parameter versus using the Jacobians instead is presented. In the previous work, the Bundle Adjustment algorithm failed to converge for certain datasets due to several block matrices of the cameras in the augmented normal equation, resulting in rank-deficient matrices. In this work, we identify the cameras that cause rank-deficient matrices and preprocess the datasets to ensure the convergence of the BA algorithm. Our optimized CUDA implementation achieves convergence of the Bundle Adjustment algorithm in around 22 seconds for the largest dataset compared

关键词： scene reconstruction Bundle Adjustment Levenberg-Marquardt Non-Linear Least Squares Memory Throughput Computational Throughput Contiguous Memory Access CUDA Optimization

Improving Accuracy and Computational Burden of Bundle Adjustment Algorithm Using GPUs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering（科研） 2023年第10期15卷 663-690页

作者： Pranay R. Kommera Suresh S. Muknahallipatna John E. McInroy Department of Electrical Engineering and Computer Science University of Wyoming Laramie Wyoming USA

Bundle adjustment is a camera and point refinement technique in a 3D scene reconstruction pipeline. The camera parameters and the 3D points are refined by minimizing the difference between computed projection and observed projection of the image points formulated as a non-linear least-square problem. Levenberg-Marquardt method is used to solve the non-linear least-square problem. Solving the non-linear least-square problem is computationally expensive, proportional to the number of cameras, points, and projections. In this paper, we implement the Bundle Adjustment (BA) algorithm and analyze techniques to improve algorithmic performance by reducing the mean square error. We investigate using an additional radial distortion camera parameter in the BA algorithm and demonstrate better convergence of the mean square error. We also demonstrate the use of explicitly computed analytical derivatives. In addition, we implement the BA algorithm on GPUs using the CUDA parallel programming model to reduce the computational time burden of the BA algorithm. CUDA Streams, atomic operations, and cuBLAS library in the CUDA programming model are proposed, implemented, and demonstrated to improve the performance of the BA algorithm. Our implementation has demonstrated better convergence of the BA algorithm and achieved a speedup of up to 16× on the use of the BA algorithm on various datasets.

关键词： Bundle Adjustment Levenberg-Marquardt scene reconstruction Radial Dis-tortion Coefficient Explicit Jacobian CUDA Optimization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

从“人、货、场”到“社群、数据、体验”