With the development of computer vision technology,panoramic image stitching has been widely used in fields such as scene reconstruction.A single traditional image cannot fully capture the panoramic view of the iconic...With the development of computer vision technology,panoramic image stitching has been widely used in fields such as scene reconstruction.A single traditional image cannot fully capture the panoramic view of the iconic East Gate of the South Campus of Shaanxi University of Technology.Therefore,this project aims to technically fuse multiple partial images into a complete panoramic image,enabling comprehensive recording and visual presentation of the architectural landscapes and spatial environments in this area.This report first introduces the technical background and application scenarios,clarifying the necessity of panoramic image stitching in campus landscape recording.It then elaborates on the core objectives and practical values,highlighting the role of technical solutions in improving image quality.Technically,a modular system design based on OpenCV is adopted,including modules such as image preprocessing,feature extraction and matching,image registration,fusion,and post-processing.Specifically,the SIFT algorithm is applied for feature extraction,KNN combined with ratio testing is used for feature matching,image registration is achieved by calculating the homography matrix,the fusion process utilizes multiband blending and Laplacian pyramid,and post-processing includes operations such as black area filling and CLAHE contrast enhancement.The experiment was conducted in a specific hardware and software environment using five overlapping images.After preprocessing,stitching,detail enhancement,and black edge repair,a panoramic image was successfully generated.The results show that the panoramic image fully presents the relevant scenery,with concealed seams,balanced exposure differences,and strong hierarchical details.This report provides a systematic description of the project’s technical implementation and achievement application.展开更多
The proliferation of low-altitude economic activities has precipitated a significant expansion in the application domains of Unmanned Aerial Vehicle(UAV),transcending the constraints of singular platform operation.Mul...The proliferation of low-altitude economic activities has precipitated a significant expansion in the application domains of Unmanned Aerial Vehicle(UAV),transcending the constraints of singular platform operation.Multi-UAV cooperative online remote sensing image stitching involves several challenges,including image blurriness and deformation caused by platform vibrations,as well as managing vast amounts of data and addressing transmission delays.This paper introduces a real-time system for multi-UAV video stitching that integrates hardware acceleration,pose-guided ROI filtering,and temporal consistency constraints.Data from the onboard GPS and Inertial Measurement Unit(IMU)are used to estimate the overlap between two aerial images.Subsequently,the Graphics Processing Unit(GPU)within an edge computing platform is tasked with swiftly detecting SIFT features within the overlapping image sectors.Feature point matching is performed using a position-guided matching algorithm to compute the homography matrix.The results demonstrate that the RK3588-based edge computing platform exhibits rapid image decoding and stitching capabilities,with an average stitching latency of 36.43ms.Furthermore,this study developed a ground-based human-machine interaction system to present stitched video streams in realtime,thereby improving the operational efficiency and visual quality of multi-UAV aerial surveillance.展开更多
Optical microscopes are essential tools for scientific research,but traditional microscopes are restricted to capturing only two-dimensional(2D)texture information,lacking comprehensive three-dimensional(3D)morphology...Optical microscopes are essential tools for scientific research,but traditional microscopes are restricted to capturing only two-dimensional(2D)texture information,lacking comprehensive three-dimensional(3D)morphology capabilities.Additionally,traditional microscopes are inherently constrained by the limited space-bandwidth product of optical systems,resulting in restricted depth of field(DOF)and field of view(FOV).Attempts to expand DOF and FOV typically come at the cost of diminished resolution.In this paper,we propose a texture-driven FOV stitching algorithm specifically designed for extended depth-of-field(EDOF)microscopy,allowing for the integration of 2D texture and 3D depth data to achieve high-resolution,high-throughput multimodal imaging.Experimental results demonstrate an 11-fold enhancement in DOF and an 8-fold expansion in FOV compared to traditional microscopes,while maintaining axial resolution after FOV extension.展开更多
A novel automatic seamless stitching method is presented. Compared to the traditional method, it can speed the processing and minimize the utilization of human resources to produce global lunar map. Meanwhile, a new g...A novel automatic seamless stitching method is presented. Compared to the traditional method, it can speed the processing and minimize the utilization of human resources to produce global lunar map. Meanwhile, a new global image map of the Moon with spatial resolution of -120 m has been completed by the proposed method from Chang＇E-1 CCD image data.展开更多
The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 luna...The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 lunar mission is proposed. Combining with the image registration technique and the characteristics of Chang＇E CCD images, the fast method proposed not only can overcome the contradiction of the high spatial resolution of the CCD images and the low positioning accuracy of the location coordinates, but also can speed up the processing and minimize the utilization of human resources to produce lunar mosaic map. Meanwhile, a new lunar map from 70oN to 70oS with spatial resolution of less than 10 m has been completed by the proposed method. Its average relative location accuracy of the adjacent orbits CCD image data is less than 3 pixels.展开更多
A multi layer gridless area router is reported.Based on corner stitching,this router adopts tile expansion to explore path for each net.A heuristic method that penalizes nodes deviating from the destination is devise...A multi layer gridless area router is reported.Based on corner stitching,this router adopts tile expansion to explore path for each net.A heuristic method that penalizes nodes deviating from the destination is devised to accelerate the algorithm.Besides,an enhanced interval tree is used to manage the intermediate data structure.In order to improve the completion rate of routing,a new gridless rip up and rerouting algorithm is proposed.The experimental results indicate that the completion rate is improved after the rip up and reroute process and the speed of this algorithm is satisfactory.展开更多
According to the bio-characteristics of the lower and upper cavity surfaces of dental restoration, a stitching approach is proposed based on a virtual zipper working mechanism and a minimization of the surface total c...According to the bio-characteristics of the lower and upper cavity surfaces of dental restoration, a stitching approach is proposed based on a virtual zipper working mechanism and a minimization of the surface total curvature energy, which is used to resolve the stitching problems existing during computer-aided design for dental restorations. First, the two boundaries corresponding to the lower and upper surfaces are triangulated based on the zipper working mechanism to generate the initial stitching surface patch, of which the edges are distributed uniformly between the boundaries. Secondly, the initial stitching surface patch is subdivided and deformed to reconstruct an optimized surface patch according to the bio-characteristics of the teeth. The optimized surface patch is minimally distinguishable from the surrounding mesh in smoothness and density, and it can stitch the upper and lower cavity surfaces naturally. The experimental results show that the dental restorations obtained by the proposed method can satisfy both the shape aesthetic and the fitting accuracy, and meet the requirements of clinical oral medicine.展开更多
为实现深井钻孔内壁形态的高质量全景可视化,克服传统图像拼接方法在自动化水平、拼接质量及处理效率方面的局限,提出了一种融合YOLOv11s(You Only Look Once)与结构相似性(Structural Similarity Index Method)的智能图像拼接方法。研...为实现深井钻孔内壁形态的高质量全景可视化,克服传统图像拼接方法在自动化水平、拼接质量及处理效率方面的局限,提出了一种融合YOLOv11s(You Only Look Once)与结构相似性(Structural Similarity Index Method)的智能图像拼接方法。研究旨在突破现有技术对人工干预依赖性强、易产生接缝、亮度不均及视觉伪影等瓶颈,提升钻孔内壁图像拼接的精度、连续性与整体效率,为后续钻孔质量评估与爆破设计参数优化提供高保真、高一致性的视觉数据支持。在技术方法上,引入轻量化YOLOv11s目标检测网络,充分利用其深层特征提取能力与多尺度检测优势,精准识别钻孔图像中的圆形边界,自动提取圆心坐标与半径参数,有效克服因镜头畸变、光照不均或局部遮挡引起的定位偏差;随后,基于精确的几何参数进行极坐标变换,将环形内壁区域逐帧展开为矩形图像,保留原始纹理信息的同时构建空间有序的展开图集。在此基础上,创新性地融合SSIM结构相似性度量与滑动窗口匹配策略,通过系统分析相邻展开图像在重叠区域内的亮度、对比度与结构一致性,自适应搜索最优配准位置,实现高效、无缝的图像拼接,最终生成完整内壁环状全景图。试验结果表明,该方法在处理240张图像时,拼接耗时仅为34.98 s,同样实验条件下,相较于传统SIFT特征点匹配方法所需的271.35 s,该方法耗时更短且拼接结果具有更高的视觉连贯性与几何保真度,抑制了接缝错位、亮度跳变和纹理重复等常见问题。创新在于提出了一种自动化拼接流程,融合YOLOv11s与SSIM算法,提升了拼接效率与视觉质量。展开更多
文摘With the development of computer vision technology,panoramic image stitching has been widely used in fields such as scene reconstruction.A single traditional image cannot fully capture the panoramic view of the iconic East Gate of the South Campus of Shaanxi University of Technology.Therefore,this project aims to technically fuse multiple partial images into a complete panoramic image,enabling comprehensive recording and visual presentation of the architectural landscapes and spatial environments in this area.This report first introduces the technical background and application scenarios,clarifying the necessity of panoramic image stitching in campus landscape recording.It then elaborates on the core objectives and practical values,highlighting the role of technical solutions in improving image quality.Technically,a modular system design based on OpenCV is adopted,including modules such as image preprocessing,feature extraction and matching,image registration,fusion,and post-processing.Specifically,the SIFT algorithm is applied for feature extraction,KNN combined with ratio testing is used for feature matching,image registration is achieved by calculating the homography matrix,the fusion process utilizes multiband blending and Laplacian pyramid,and post-processing includes operations such as black area filling and CLAHE contrast enhancement.The experiment was conducted in a specific hardware and software environment using five overlapping images.After preprocessing,stitching,detail enhancement,and black edge repair,a panoramic image was successfully generated.The results show that the panoramic image fully presents the relevant scenery,with concealed seams,balanced exposure differences,and strong hierarchical details.This report provides a systematic description of the project’s technical implementation and achievement application.
基金funded by Graduate innovation program of National University of Defense Technology,grant number:XJZH2024016.
文摘The proliferation of low-altitude economic activities has precipitated a significant expansion in the application domains of Unmanned Aerial Vehicle(UAV),transcending the constraints of singular platform operation.Multi-UAV cooperative online remote sensing image stitching involves several challenges,including image blurriness and deformation caused by platform vibrations,as well as managing vast amounts of data and addressing transmission delays.This paper introduces a real-time system for multi-UAV video stitching that integrates hardware acceleration,pose-guided ROI filtering,and temporal consistency constraints.Data from the onboard GPS and Inertial Measurement Unit(IMU)are used to estimate the overlap between two aerial images.Subsequently,the Graphics Processing Unit(GPU)within an edge computing platform is tasked with swiftly detecting SIFT features within the overlapping image sectors.Feature point matching is performed using a position-guided matching algorithm to compute the homography matrix.The results demonstrate that the RK3588-based edge computing platform exhibits rapid image decoding and stitching capabilities,with an average stitching latency of 36.43ms.Furthermore,this study developed a ground-based human-machine interaction system to present stitched video streams in realtime,thereby improving the operational efficiency and visual quality of multi-UAV aerial surveillance.
基金supported by Science Foundation of Donghai Lab-oratory(No.DH-2022KF01001).
文摘Optical microscopes are essential tools for scientific research,but traditional microscopes are restricted to capturing only two-dimensional(2D)texture information,lacking comprehensive three-dimensional(3D)morphology capabilities.Additionally,traditional microscopes are inherently constrained by the limited space-bandwidth product of optical systems,resulting in restricted depth of field(DOF)and field of view(FOV).Attempts to expand DOF and FOV typically come at the cost of diminished resolution.In this paper,we propose a texture-driven FOV stitching algorithm specifically designed for extended depth-of-field(EDOF)microscopy,allowing for the integration of 2D texture and 3D depth data to achieve high-resolution,high-throughput multimodal imaging.Experimental results demonstrate an 11-fold enhancement in DOF and an 8-fold expansion in FOV compared to traditional microscopes,while maintaining axial resolution after FOV extension.
基金supported by the Science and Technology Development Fund of Macao (Nos. 004/2011/A1 and 015/2010/A)the National High Technology Research and Development Program (No. 2010AA122202)
文摘A novel automatic seamless stitching method is presented. Compared to the traditional method, it can speed the processing and minimize the utilization of human resources to produce global lunar map. Meanwhile, a new global image map of the Moon with spatial resolution of -120 m has been completed by the proposed method from Chang＇E-1 CCD image data.
基金supported in part by the Science and Technology Development Fund of Macao,China (Nos.048/2016/A2,110/2014/A3,091/2013/A3,084/2012/A3,and 048/2012/A2)the National Natural Science Foundation of China (Nos.61170320 and 61272364)the Open Project Program of the State Key Lab of CAD & CG of Zhejiang University (No.A1513)
文摘The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 lunar mission is proposed. Combining with the image registration technique and the characteristics of Chang＇E CCD images, the fast method proposed not only can overcome the contradiction of the high spatial resolution of the CCD images and the low positioning accuracy of the location coordinates, but also can speed up the processing and minimize the utilization of human resources to produce lunar mosaic map. Meanwhile, a new lunar map from 70oN to 70oS with spatial resolution of less than 10 m has been completed by the proposed method. Its average relative location accuracy of the adjacent orbits CCD image data is less than 3 pixels.
文摘A multi layer gridless area router is reported.Based on corner stitching,this router adopts tile expansion to explore path for each net.A heuristic method that penalizes nodes deviating from the destination is devised to accelerate the algorithm.Besides,an enhanced interval tree is used to manage the intermediate data structure.In order to improve the completion rate of routing,a new gridless rip up and rerouting algorithm is proposed.The experimental results indicate that the completion rate is improved after the rip up and reroute process and the speed of this algorithm is satisfactory.
基金The National High Technology Research and Development Program of China(863 Program)(No.2005AA420240)the Key Science and Technology Program of Jiangsu Province (No.BE2005014)
文摘According to the bio-characteristics of the lower and upper cavity surfaces of dental restoration, a stitching approach is proposed based on a virtual zipper working mechanism and a minimization of the surface total curvature energy, which is used to resolve the stitching problems existing during computer-aided design for dental restorations. First, the two boundaries corresponding to the lower and upper surfaces are triangulated based on the zipper working mechanism to generate the initial stitching surface patch, of which the edges are distributed uniformly between the boundaries. Secondly, the initial stitching surface patch is subdivided and deformed to reconstruct an optimized surface patch according to the bio-characteristics of the teeth. The optimized surface patch is minimally distinguishable from the surrounding mesh in smoothness and density, and it can stitch the upper and lower cavity surfaces naturally. The experimental results show that the dental restorations obtained by the proposed method can satisfy both the shape aesthetic and the fitting accuracy, and meet the requirements of clinical oral medicine.
文摘为实现深井钻孔内壁形态的高质量全景可视化,克服传统图像拼接方法在自动化水平、拼接质量及处理效率方面的局限,提出了一种融合YOLOv11s(You Only Look Once)与结构相似性(Structural Similarity Index Method)的智能图像拼接方法。研究旨在突破现有技术对人工干预依赖性强、易产生接缝、亮度不均及视觉伪影等瓶颈,提升钻孔内壁图像拼接的精度、连续性与整体效率,为后续钻孔质量评估与爆破设计参数优化提供高保真、高一致性的视觉数据支持。在技术方法上,引入轻量化YOLOv11s目标检测网络,充分利用其深层特征提取能力与多尺度检测优势,精准识别钻孔图像中的圆形边界,自动提取圆心坐标与半径参数,有效克服因镜头畸变、光照不均或局部遮挡引起的定位偏差;随后,基于精确的几何参数进行极坐标变换,将环形内壁区域逐帧展开为矩形图像,保留原始纹理信息的同时构建空间有序的展开图集。在此基础上,创新性地融合SSIM结构相似性度量与滑动窗口匹配策略,通过系统分析相邻展开图像在重叠区域内的亮度、对比度与结构一致性,自适应搜索最优配准位置,实现高效、无缝的图像拼接,最终生成完整内壁环状全景图。试验结果表明,该方法在处理240张图像时,拼接耗时仅为34.98 s,同样实验条件下,相较于传统SIFT特征点匹配方法所需的271.35 s,该方法耗时更短且拼接结果具有更高的视觉连贯性与几何保真度,抑制了接缝错位、亮度跳变和纹理重复等常见问题。创新在于提出了一种自动化拼接流程,融合YOLOv11s与SSIM算法,提升了拼接效率与视觉质量。
