Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance o...Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.展开更多
This research develops an accurate and efficient method for the Perspective-n-Line(Pn L)problem. The developed method addresses and solves Pn L via exploiting the problem’s geometry in a non-linear least squares fash...This research develops an accurate and efficient method for the Perspective-n-Line(Pn L)problem. The developed method addresses and solves Pn L via exploiting the problem’s geometry in a non-linear least squares fashion. Specifically, by representing the rotation matrix with a novel quaternion parameterization, the Pn L problem is first decomposed into four independent subproblems. Then, each subproblem is reformulated as an unconstrained minimization problem, in which the Kronecker product is adopted to write the cost function in a more compact form. Finally, the Groobner basis technique is used to solve the polynomial system derived from the first-order optimality conditions of the cost function. Moreover, a novel strategy is presented to improve the efficiency of the algorithm. It is improved by exploiting structure information embedded in the rotation parameterization to accelerate the computing of coefficient matrix of a cost function. Experiments on synthetic data and real images show that the developed method is comparable to or better than state-of-the-art methods in accuracy, but with reduced computational requirements.展开更多
High-quality 3D reconstruction is an important topic in computer graphics and computer vision with many applications,such as robotics and augmented reality.The advent of consumer RGB-D cameras has made a profound adva...High-quality 3D reconstruction is an important topic in computer graphics and computer vision with many applications,such as robotics and augmented reality.The advent of consumer RGB-D cameras has made a profound advance in indoor scene reconstruction.For the past few years,researchers have spent significant effort to develop algorithms to capture 3D models with RGB-D cameras.As depth images produced by consumer RGB-D cameras are noisy and incomplete when surfaces are shiny,bright,transparent,or far from the camera,obtaining highquality 3D scene models is still a challenge for existing systems.We here review high-quality 3D indoor scene reconstruction methods using consumer RGB-D cameras.In this paper,we make comparisons and analyses from the following aspects:(i)depth processing methods in 3D reconstruction are reviewed in terms of enhancement and completion,(ii)ICP-based,feature-based,and hybrid methods of camera pose estimation methods are reviewed,and(iii)surface reconstruction methods are reviewed in terms of surface fusion,optimization,and completion.The performance of state-of-the-art methods is also compared and analyzed.This survey will be useful for researchers who want to follow best practices in designing new high-quality 3D reconstruction methods.展开更多
Camera Pose Estimating from point and line correspondences is critical in various applications,including robotics,augmented reality,3D reconstruction,and autonomous navigation.Existing methods,such as the Perspective-...Camera Pose Estimating from point and line correspondences is critical in various applications,including robotics,augmented reality,3D reconstruction,and autonomous navigation.Existing methods,such as the Perspective-n-Point(PnP)and Perspective-n-Line(PnL)approaches,offer limited accuracy and robustness in environments with occlusions,noise,or sparse feature data.This paper presents a unified solution,Efficient and Accurate Pose Estimation from Point and Line Correspondences(EAPnPL),combining point-based and linebased constraints to improve pose estimation accuracy and computational efficiency,particularly in low-altitude UAV navigation and obstacle avoidance.The proposed method utilizes quaternion parameterization of the rotation matrix to overcome singularity issues and address challenges in traditional rotation matrix-based formulations.A hybrid optimization framework is developed to integrate both point and line constraints,providing a more robust and stable solution in complex scenarios.The method is evaluated using synthetic and realworld datasets,demonstrating significant improvements in performance over existing techniques.The results indicate that the EAPnPL method enhances accuracy and reduces computational complexity,making it suitable for real-time applications in autonomous UAV systems.This approach offers a promising solution to the limitations of existing camera pose estimation methods,with potential applications in low-altitude navigation,autonomous robotics,and 3D scene reconstruction.展开更多
文摘Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.
基金supported in part by the National Natural Science Foundation of China(Nos.61905112 and 62073161)in part by the China Scholarship Council(Nos.201906830092)in part by the Fundamental Research Funds for the Central University(No.NZ2020005)。
文摘This research develops an accurate and efficient method for the Perspective-n-Line(Pn L)problem. The developed method addresses and solves Pn L via exploiting the problem’s geometry in a non-linear least squares fashion. Specifically, by representing the rotation matrix with a novel quaternion parameterization, the Pn L problem is first decomposed into four independent subproblems. Then, each subproblem is reformulated as an unconstrained minimization problem, in which the Kronecker product is adopted to write the cost function in a more compact form. Finally, the Groobner basis technique is used to solve the polynomial system derived from the first-order optimality conditions of the cost function. Moreover, a novel strategy is presented to improve the efficiency of the algorithm. It is improved by exploiting structure information embedded in the rotation parameterization to accelerate the computing of coefficient matrix of a cost function. Experiments on synthetic data and real images show that the developed method is comparable to or better than state-of-the-art methods in accuracy, but with reduced computational requirements.
基金National Key R&D Program of China under Grant No.2018YFC2000600Open Projects Program of National Laboratory of Pattern Recognition under Grant No.202100009+1 种基金National Natural Science Foundation of China under Grant No.72071018Fundamental Research Funds for Central Universities under Grant No.2021TD006。
文摘High-quality 3D reconstruction is an important topic in computer graphics and computer vision with many applications,such as robotics and augmented reality.The advent of consumer RGB-D cameras has made a profound advance in indoor scene reconstruction.For the past few years,researchers have spent significant effort to develop algorithms to capture 3D models with RGB-D cameras.As depth images produced by consumer RGB-D cameras are noisy and incomplete when surfaces are shiny,bright,transparent,or far from the camera,obtaining highquality 3D scene models is still a challenge for existing systems.We here review high-quality 3D indoor scene reconstruction methods using consumer RGB-D cameras.In this paper,we make comparisons and analyses from the following aspects:(i)depth processing methods in 3D reconstruction are reviewed in terms of enhancement and completion,(ii)ICP-based,feature-based,and hybrid methods of camera pose estimation methods are reviewed,and(iii)surface reconstruction methods are reviewed in terms of surface fusion,optimization,and completion.The performance of state-of-the-art methods is also compared and analyzed.This survey will be useful for researchers who want to follow best practices in designing new high-quality 3D reconstruction methods.
基金funded by the Jiangsu Province Postgraduate Scientific Research and Practice Innovation Program(SJCX240449)projectthe Nanjing University of Information Science and Technology Talent Startup Fund(2022r078).
文摘Camera Pose Estimating from point and line correspondences is critical in various applications,including robotics,augmented reality,3D reconstruction,and autonomous navigation.Existing methods,such as the Perspective-n-Point(PnP)and Perspective-n-Line(PnL)approaches,offer limited accuracy and robustness in environments with occlusions,noise,or sparse feature data.This paper presents a unified solution,Efficient and Accurate Pose Estimation from Point and Line Correspondences(EAPnPL),combining point-based and linebased constraints to improve pose estimation accuracy and computational efficiency,particularly in low-altitude UAV navigation and obstacle avoidance.The proposed method utilizes quaternion parameterization of the rotation matrix to overcome singularity issues and address challenges in traditional rotation matrix-based formulations.A hybrid optimization framework is developed to integrate both point and line constraints,providing a more robust and stable solution in complex scenarios.The method is evaluated using synthetic and realworld datasets,demonstrating significant improvements in performance over existing techniques.The results indicate that the EAPnPL method enhances accuracy and reduces computational complexity,making it suitable for real-time applications in autonomous UAV systems.This approach offers a promising solution to the limitations of existing camera pose estimation methods,with potential applications in low-altitude navigation,autonomous robotics,and 3D scene reconstruction.
