Background:Irregular heartbeats can have serious health implications if left undetected and untreated for an extended period of time.Methods:This study leverages machine learning(ML)techniques to classify electrocardi...Background:Irregular heartbeats can have serious health implications if left undetected and untreated for an extended period of time.Methods:This study leverages machine learning(ML)techniques to classify electrocardiogram(ECG)heartbeats,comparing traditional feature-based ML methods with innovative image-based approaches.The dataset underwent rigorous preprocessing,including down-sampling,frequency filtering,beat segmentation,and normalization.Two methodologies were explored:(1)handcrafted feature extraction,utilizing metrics like heart rate variability and RR distances with LightGBM classifiers,and(2)image transformation of ECG signals using Gramian Angular Field(GAF),Markov Transition Field(MTF),and Recurrence Plot(RP),enabling multimodal input for convolutional neural networks(CNNs).The Synthetic Minority Oversampling Technique(SMOTE)addressed data imbalance,significantly improving minority-class metrics.Results:The handcrafted feature approach achieved notable performance,with LightGBM excelling in precision and recall.Image-based classification further enhanced outcomes,with a custom Inception-based CNN,attaining an 85%F1 score and 97%accuracy using combined GAF,MTF,and RP transformations.Statistical analyses confirmed the significance of these improvements.Conclusion:This work highlights the potential of ML for cardiac irregularities detection,demonstrating that combining advanced preprocessing,feature engineering,and state-of-the-art neural networks can improve classification accuracy.These findings contribute to advancing AI-driven diagnostic tools,offering promising implications for cardiovascular healthcare.展开更多
This paper addresses a coordinated control problem for Spacecraft Formation Flying(SFF). The distributed followers are required to track and synchronize with the leader spacecraft.By using the feature points in the tw...This paper addresses a coordinated control problem for Spacecraft Formation Flying(SFF). The distributed followers are required to track and synchronize with the leader spacecraft.By using the feature points in the two-dimensional image space, an integrated 6-degree-of-freedom dynamic model is formulated for spacecraft relative motion. Without sophisticated threedimensional reconstruction, image features are directly utilized for the controller design. The proposed image-based controller can drive the follower spacecraft in the desired configuration with respect to the leader when the real-time captured images match their reference counterparts. To improve the precision of the formation configuration, the proposed controller employs a coordinated term to reduce the relative distance errors between followers. The uncertainties in the system dynamics are handled by integrating the adaptive technique into the controller, which increases the robustness of the SFF system. The closed-loop system stability is analyzed using the Lyapunov method and algebraic graph theory. A numerical simulation for a given SFF scenario is performed to evaluate the performance of the controller.展开更多
In this paper, an efficient sparse representation-based method is presented for detecting surface defects. The proposed method uses the sparse degree of coefficient in the redundant dictionary for checking whether the...In this paper, an efficient sparse representation-based method is presented for detecting surface defects. The proposed method uses the sparse degree of coefficient in the redundant dictionary for checking whether the test image is defective or not, and the binary representation of the defective images is obtained, according to the global coefficient feature. Owing to the requirements for the efficiency and detecting quality, the block proximal gradient operator is introduced to speed up the online dictionary learning. Considering the correlation among the testing samples, prior knowledge is applied in the orthogonal-matching-pursuit sparse representation algorithm to improve the speed of sparse coding. Experimental results demonstrate that the proposed detection method can effectively detect and extract the defects of the surface images, and has broad applicability.展开更多
Cervical cancer is the one of the most common cancer in female patients inThailand. Radiotherapy has the role for the treatment of cervical cancer by postoperative, radical and palliative treatments. For radical radio...Cervical cancer is the one of the most common cancer in female patients inThailand. Radiotherapy has the role for the treatment of cervical cancer by postoperative, radical and palliative treatments. For radical radiotherapy, the combination of external beam radiation therapy and brachytherapy will be used to increase the tumor dose to curative goal. With the new development of medical images (Computed tomography (CT), Magnetic Resonance Imaging (MRI) or Ultrasonography (US)), the treatment with brachytherapy will be developed from point-based to volume-based concepts. Many studies reported the benefit of image-based brachytherapy over conventional brachytherapy and clinical benefit of using image-based brachytherapy in the treatment of cervical cancer.展开更多
Image-based rendering is important both in the field of computer graphics and computer vision,and it is also widely used in virtual reality technology.For more than two decades,people have done a lot of work on the re...Image-based rendering is important both in the field of computer graphics and computer vision,and it is also widely used in virtual reality technology.For more than two decades,people have done a lot of work on the research of image-based rendering,and these methods can be divided into two categories according to whether the geometric information of the scene is utilized.According to this classification,we introduce some classical methods and representative methods proposed in recent years.We also compare and analyze the basic principles,advantages and disadvantages of different methods.Finally,some suggestions are given for research directions on image-based rendering techniques in the future.展开更多
An aluminum matrix syntactic foam, incorporated with hollow-structured fly ash particles, was fabricated by pressure infiltration technique. X-ray micro-computed tomography was used to characterize its heterogeneous m...An aluminum matrix syntactic foam, incorporated with hollow-structured fly ash particles, was fabricated by pressure infiltration technique. X-ray micro-computed tomography was used to characterize its heterogeneous microstructure three dimensionally （3D）. The quantification of some microstructure features, such as content and size distribution of hollow fly ash particles, was acquired in 3D. The tomographic data were exploited as a rapid method to generate a microstructurally accurate and robust 3D meshed model. The thermal transport behavior has been modeled using a commercial finite-element code to conduct steady state analyses. Simulation of the thermal conductivity showed good correlation with experimental result.展开更多
The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide ...The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide much faster convergence than SPGD; however, the limited actuator stroke of the deformable mirror （DM） often prohibits the sensing of higher-order modes or renders a closed-loop correction inapplicable. Based on a comparative analysis of SPGD and the DM-modal-based algorithm, a hybrid approach involving both algorithms is proposed for extended image-based WSAO, and is demonstrated in this experiment. The hybrid approach can achieve similar correction results to pure SPGD, but with a dramatically decreased iteration number.展开更多
Hayabusa2 is an asteroid sample return mission carried out by the Japan Aerospace Exploration Agency.The spacecraft was launched in 2014 and arrived at the target asteroid Ryugu on June 27,2018.During the 1.5-year pro...Hayabusa2 is an asteroid sample return mission carried out by the Japan Aerospace Exploration Agency.The spacecraft was launched in 2014 and arrived at the target asteroid Ryugu on June 27,2018.During the 1.5-year proximity phase,several critical operations(including two landing/sampling operations)were successfully performed.They were based on autonomous image-based descent and landing techniques.This paper describes an imagebased autonomous navigation scheme of the Hayabusa2 mission using artificial landmarks named target markers(TMs).Its basic algorithm,and the in-flight results of the first touchdown and its rehearsal,are shown.展开更多
This paper proposes a numerical three-dimensional(3D)mesoscopic approach based on the discrete element method combined with X-ray computed tomography(XCT)images to characterize the dynamic impact behavior of heterogen...This paper proposes a numerical three-dimensional(3D)mesoscopic approach based on the discrete element method combined with X-ray computed tomography(XCT)images to characterize the dynamic impact behavior of heterogeneous coal-rock(HCR).The dynamic impact loading in three directions was modelled to investigate the effects of the 3D meso-structure on the failure patterns and fracture mechanism,with different impact velocities.The XCT image-based discrete element model of HCR was calibrated through appropriate standard uniaxial compression tests.Numerical simulations were carried out to investigate how the breakage behaviors are affected by different loading directions with different impact velocities.The loading direction,input energy,and spatial distribution of the mineral phase had a remarkable influence on the failure patterns and load-carrying capacities.The shape of the gangue phase and the approximate location of the gangue interfaces are key parameters to consider when investigating the failure patterns and fracture mechanism of heterogeneous rock materials.The damage and fracture tended to propagate from the surfaces to the HCR interior.The gangue phase area contacting the loading wall,growth direction of the strong gangue interfaces,and loading directions greatly influenced the failure patterns of the heterogeneous rock materials.展开更多
An extension to texture mapping is given in this paper for improving theefficiency of image-based rendering. For a depth image with an orthogonal displacement at eachpixel, it is decomposed by the displacement into a ...An extension to texture mapping is given in this paper for improving theefficiency of image-based rendering. For a depth image with an orthogonal displacement at eachpixel, it is decomposed by the displacement into a series of layered textures (LTs) with each onehaving the same displacement for all its texels. Meanwhile, some texels of the layered textures areinterpolated for obtaining a continuous 3D approximation of the model represented in the depthimage. Thus, the plane-to-plane texture mapping can be used to map these layered textures to producenovel views and the advantages can be obtained as follows: accelerating the rendering speed,supporting the 3D surface details and view motion parallax, and avoiding the expensive task ofhole-filling in the rendering stage. Experimental results show the new method can producehigh-quality images and run faster than many famous image-based rendering techniques.展开更多
In this paper, we investigate the problem of determining regions in 3D scene visible to some given viewpoints when obstacles are present in the scene. We assume that the obstacles are composed of some opaque objects w...In this paper, we investigate the problem of determining regions in 3D scene visible to some given viewpoints when obstacles are present in the scene. We assume that the obstacles are composed of some opaque objects with closed surfaces. The problem is formulated in an implicit framework where the obstacles are represented by a level set function. The visible and invisible regions of the given viewpoints are determined through an efficient implicit ray tracing technique. As an extension of our approach, we apply the multiview visibility estimation to an image-based modeling technique. The unknown scene geometry and multiview visibility information are incorporated into a variational energy functional. By minimizing the energy functional, the true scene geometry as well as the accurate visibility information of the multiple views can be recovered from a number of scene images. This makes it feasible to handle the visibility problem of multiple views by our approach when the true scene geometry is unknown.展开更多
In this paper, we present a hybrid representation of image-based models combining the textured planes and the hierarchical points. Taking a set of depth images as input, our method starts from classifying input pixels...In this paper, we present a hybrid representation of image-based models combining the textured planes and the hierarchical points. Taking a set of depth images as input, our method starts from classifying input pixels into two categories, indicating the planar and non-planar surfaces respectively. For the planar surfaces, the geometric coefficients are reconstructed to form the uniformly sampled textures. For nearly planar surfaces, some textured planes, called lumiproxies, are constructed to represent the equivalent visual appearance. The Hough transform is used to find the positions of these textured planes, and optic flow measures are used to determine their textures. For remaining pixels corresponding to the non-planar geometries, the point primitive is applied, reorganized as the OBB-tree structure. Then, texture mapping and point splatting are employed together to render the novel views, with the hardware acceleration.展开更多
The most important goal of virtual reality is to create a virtual world by computers where users are allowed to view the environment and control the virtual objects interactively. naditionally virtual reality systems ...The most important goal of virtual reality is to create a virtual world by computers where users are allowed to view the environment and control the virtual objects interactively. naditionally virtual reality systems use 3D computer graphics to model and render a virtual environment in real time. However, this approach usually requires laborious modeling and expensive special-purpose rendering hardware. Image-based rendering is a new approach in composing a virtual environment in which a set of panoramic images is used to compose the virtual environment and walking in the space is accomplished by 'hopping' to different panoramic points. This paper introduces an experimeatal image-based VR system. The techniques utilized in the system, in particular the authoring and interactive control tools of the system, are described in detail.展开更多
The effective thermal conductivity of heterogeneous or composite materials is an essential physical parameter of materials selection and design for specific functions in science and engineering. The effective thermal ...The effective thermal conductivity of heterogeneous or composite materials is an essential physical parameter of materials selection and design for specific functions in science and engineering. The effective thermal conductivity is heavily relied on the fraction and spatial distribution of each phase. In this work, image- based finite element method （FEM） was used to calculate the effective thermal conductivity of porous ceramics with different pore structures. Compared with former theoretical models such as effective media theory （EMT） equation and parallel model, image-based FEM can be applied to a large variety of material systems with a relatively steady deviation. The deviation of image-based FEM computation mainly comes from the difference between the two dimensional （2D） image and the three dimensional （3D） structure of the real system, and an experiment was carried out to confirm this assumption. Factors influencing 2D and 3D effective thermal conductivities were studied by FEM to illustrate the accuracy and application conditions of image-based FEM.展开更多
1. Background The virtual reality （VR） technology is now at the frontier of modern information science. VR is based on computer graphics, computer vision, and other fresh air topics in today＇s computer technology....1. Background The virtual reality （VR） technology is now at the frontier of modern information science. VR is based on computer graphics, computer vision, and other fresh air topics in today＇s computer technology. Nowadays the VR technology has been applied successfully in variety of fields such as military simulation, industry, medical training and visualization, environment protection and entertainment.展开更多
Correctly tracking the evolution of spatial heterogeneity of local degree of saturation(Sr)in unsaturated soils is essential to explain the seepage phenomenon,which is crucial to assessing slope stability.Several meth...Correctly tracking the evolution of spatial heterogeneity of local degree of saturation(Sr)in unsaturated soils is essential to explain the seepage phenomenon,which is crucial to assessing slope stability.Several methods exist for quantifying the heterogeneity of local S_(r).However,a comprehensive comparison of these methods in terms of accuracy,relative advantages,and disadvantages is currently lacking.This paper presents a comparative analysis of local Sr obtained at multiple scales,ranging from the element scale to the slice,representative element volume(REV),pore,and voxel scales.The spatial heterogeneity of Sr in an unsaturated glass beads specimen at different matric suctions was visualised and quantified by multiscale X-ray micro-focus computed tomography image-based analysis methods.Local Sr obtained at different scales displayed a comparable trend along the sample depth,yet the REV-scale method showed a much scattered and discontinuous distribution.In contrast,the pore-scale method detected a distinct two-clustered,bimodal distribution of S_(r).The pore-scale method has the highest integrated resolution,as it has the highest spatial resolution(i.e.number of data points)and provides more information(i.e.number of extractable physical parameters).This method thus provides a more effective approach for tracking the spatial heterogeneity of S_(r).Based on this method,pore-scale water retention curves were determined,offering new quantitative means to characterise pore water heterogeneity and explainwater drainage processes such as hysteresis at the pore scale.展开更多
Pavement distress detection plays a pivotal role in ensuring roadway safety,serviceability,and cost-effective infrastructure management.With rapid advancements in intelligent transportation systems,computer vision,and...Pavement distress detection plays a pivotal role in ensuring roadway safety,serviceability,and cost-effective infrastructure management.With rapid advancements in intelligent transportation systems,computer vision,and sensing technologies,non-contact detection approaches based on images and point clouds have become increasingly prominent due to their efficiency,objectivity,and scalability.This review systematically examines both image-based and point cloud-based methodologies,structured along the complete detection pipeline encompassing data acquisition,preprocessing,distress extraction,and geometric quantification.Image-based techniques rely on visual cues,such as texture,color,and edge continuity,to identify surface-level anomalies efficiently,benefiting from mature deep learning frameworks for classification,object detection,and pixel-level segmentation.In contrast,point cloud-based methods capture rich three-dimensional geometric and structural information,enabling detailed modeling of crack depth,rutting deformation,and surface irregularities.Although each modality can independently achieve satisfactory performance,their complementary strengths have driven a growing trend toward hybrid frameworks,combining image-based rapid screening with point cloud-based precision modeling,to enhance detection accuracy,robustness,and adaptability across varying conditions.Furthermore,this paper highlights persistent challenges,including multimodal data fusion,high equipment and labeling costs,computational complexity,and the need for standardized benchmarks.By synthesizing current progress and identifying key technical bottlenecks,this review provides a comprehensive foundation and forward-looking perspective for developing intelligent,efficient,and scalable pavement distress detection systems.展开更多
Wheat powdery mildew caused by Blumeria graminis f.sp.tritici(Bgt)is an important disease worldwide.Detection of latent infection of leaves by the pathogen in late autumn is valuable for estimating the inoculum potent...Wheat powdery mildew caused by Blumeria graminis f.sp.tritici(Bgt)is an important disease worldwide.Detection of latent infection of leaves by the pathogen in late autumn is valuable for estimating the inoculum potential to assess disease risks in the spring.We developed a new tool for rapid detection and quantification of latent infection of seedlings by the pathogen.The method was based on recombinase polymerase amplification(RPA)coupled with an end-point detection via lateral flow device(LFD).The limit of detection is 100 agμL^(-1)of Bgt DNA,without noticeable interference from either other common wheat pathogens or wheat material(Triticum aestivum).It was evaluated on wheat seedlings for this accuracy and sensitivity in detecting latent infection of Bgt.We further extended this RPALFD assay to estimate the level of latent infection by Bgt based on imaging analysis.There was a strong correlation between the image-based and real-time PCR assay estimates of Bgt DNA.The present results suggested that this new tool can provide rapid and accurate quantification of Bgt in latently infected leaves and can be further development as an on-site monitoring tool.展开更多
Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in t...Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in the gastric cancer field based on its efficient computational power and learning capacities,such as imagebased diagnosis and prognosis prediction.AI-assisted diagnosis includes pathology,endoscopy,and computerized tomography,while researchers in the prognosis circle focus on recurrence,metastasis,and survival prediction.In this review,a comprehensive literature search was performed on articles published up to April 2020 from the databases of PubMed,Embase,Web of Science,and the Cochrane Library.Thereby the current status of AI-applications was systematically summarized in gastric cancer.Moreover,future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.展开更多
Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However...Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.展开更多
文摘Background:Irregular heartbeats can have serious health implications if left undetected and untreated for an extended period of time.Methods:This study leverages machine learning(ML)techniques to classify electrocardiogram(ECG)heartbeats,comparing traditional feature-based ML methods with innovative image-based approaches.The dataset underwent rigorous preprocessing,including down-sampling,frequency filtering,beat segmentation,and normalization.Two methodologies were explored:(1)handcrafted feature extraction,utilizing metrics like heart rate variability and RR distances with LightGBM classifiers,and(2)image transformation of ECG signals using Gramian Angular Field(GAF),Markov Transition Field(MTF),and Recurrence Plot(RP),enabling multimodal input for convolutional neural networks(CNNs).The Synthetic Minority Oversampling Technique(SMOTE)addressed data imbalance,significantly improving minority-class metrics.Results:The handcrafted feature approach achieved notable performance,with LightGBM excelling in precision and recall.Image-based classification further enhanced outcomes,with a custom Inception-based CNN,attaining an 85%F1 score and 97%accuracy using combined GAF,MTF,and RP transformations.Statistical analyses confirmed the significance of these improvements.Conclusion:This work highlights the potential of ML for cardiac irregularities detection,demonstrating that combining advanced preprocessing,feature engineering,and state-of-the-art neural networks can improve classification accuracy.These findings contribute to advancing AI-driven diagnostic tools,offering promising implications for cardiovascular healthcare.
文摘This paper addresses a coordinated control problem for Spacecraft Formation Flying(SFF). The distributed followers are required to track and synchronize with the leader spacecraft.By using the feature points in the two-dimensional image space, an integrated 6-degree-of-freedom dynamic model is formulated for spacecraft relative motion. Without sophisticated threedimensional reconstruction, image features are directly utilized for the controller design. The proposed image-based controller can drive the follower spacecraft in the desired configuration with respect to the leader when the real-time captured images match their reference counterparts. To improve the precision of the formation configuration, the proposed controller employs a coordinated term to reduce the relative distance errors between followers. The uncertainties in the system dynamics are handled by integrating the adaptive technique into the controller, which increases the robustness of the SFF system. The closed-loop system stability is analyzed using the Lyapunov method and algebraic graph theory. A numerical simulation for a given SFF scenario is performed to evaluate the performance of the controller.
基金supported by the Zhejiang Provincial Natural Science Foundation of China(No.LZ14F030001)
文摘In this paper, an efficient sparse representation-based method is presented for detecting surface defects. The proposed method uses the sparse degree of coefficient in the redundant dictionary for checking whether the test image is defective or not, and the binary representation of the defective images is obtained, according to the global coefficient feature. Owing to the requirements for the efficiency and detecting quality, the block proximal gradient operator is introduced to speed up the online dictionary learning. Considering the correlation among the testing samples, prior knowledge is applied in the orthogonal-matching-pursuit sparse representation algorithm to improve the speed of sparse coding. Experimental results demonstrate that the proposed detection method can effectively detect and extract the defects of the surface images, and has broad applicability.
文摘Cervical cancer is the one of the most common cancer in female patients inThailand. Radiotherapy has the role for the treatment of cervical cancer by postoperative, radical and palliative treatments. For radical radiotherapy, the combination of external beam radiation therapy and brachytherapy will be used to increase the tumor dose to curative goal. With the new development of medical images (Computed tomography (CT), Magnetic Resonance Imaging (MRI) or Ultrasonography (US)), the treatment with brachytherapy will be developed from point-based to volume-based concepts. Many studies reported the benefit of image-based brachytherapy over conventional brachytherapy and clinical benefit of using image-based brachytherapy in the treatment of cervical cancer.
基金National Natural Science Foundation of China(61632003).
文摘Image-based rendering is important both in the field of computer graphics and computer vision,and it is also widely used in virtual reality technology.For more than two decades,people have done a lot of work on the research of image-based rendering,and these methods can be divided into two categories according to whether the geometric information of the scene is utilized.According to this classification,we introduce some classical methods and representative methods proposed in recent years.We also compare and analyze the basic principles,advantages and disadvantages of different methods.Finally,some suggestions are given for research directions on image-based rendering techniques in the future.
基金Funded by the National Natural Science Foundation of China (No. 51001037)the Fundamental Research Funds for the Central Universities (No. HIT.NSRIF.2013003)
文摘An aluminum matrix syntactic foam, incorporated with hollow-structured fly ash particles, was fabricated by pressure infiltration technique. X-ray micro-computed tomography was used to characterize its heterogeneous microstructure three dimensionally （3D）. The quantification of some microstructure features, such as content and size distribution of hollow fly ash particles, was acquired in 3D. The tomographic data were exploited as a rapid method to generate a microstructurally accurate and robust 3D meshed model. The thermal transport behavior has been modeled using a commercial finite-element code to conduct steady state analyses. Simulation of the thermal conductivity showed good correlation with experimental result.
基金supported by the Specialized Research Fund for the Doctoral Program of Higher Education(Grant No.20131101120023)the Excellent Young Scholars Research Fund of the Beijing Institute of Technology(Grant No.2012YG0203)
文摘The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide much faster convergence than SPGD; however, the limited actuator stroke of the deformable mirror （DM） often prohibits the sensing of higher-order modes or renders a closed-loop correction inapplicable. Based on a comparative analysis of SPGD and the DM-modal-based algorithm, a hybrid approach involving both algorithms is proposed for extended image-based WSAO, and is demonstrated in this experiment. The hybrid approach can achieve similar correction results to pure SPGD, but with a dramatically decreased iteration number.
文摘Hayabusa2 is an asteroid sample return mission carried out by the Japan Aerospace Exploration Agency.The spacecraft was launched in 2014 and arrived at the target asteroid Ryugu on June 27,2018.During the 1.5-year proximity phase,several critical operations(including two landing/sampling operations)were successfully performed.They were based on autonomous image-based descent and landing techniques.This paper describes an imagebased autonomous navigation scheme of the Hayabusa2 mission using artificial landmarks named target markers(TMs).Its basic algorithm,and the in-flight results of the first touchdown and its rehearsal,are shown.
基金The authors gratefully acknowledge the financial support received from the China Postdoctoral Science Foundation(2018M630676)National Nature Science Foundation of China(Nos.51675521 and 51779224)+1 种基金Zhejiang Basic Public Welfare Research Program(No.LHZ19E090002)and Open Founda-tion of Shandong Province Key Laboratory of Mine Mechanical.Engineering(No.2019KLMM105).
文摘This paper proposes a numerical three-dimensional(3D)mesoscopic approach based on the discrete element method combined with X-ray computed tomography(XCT)images to characterize the dynamic impact behavior of heterogeneous coal-rock(HCR).The dynamic impact loading in three directions was modelled to investigate the effects of the 3D meso-structure on the failure patterns and fracture mechanism,with different impact velocities.The XCT image-based discrete element model of HCR was calibrated through appropriate standard uniaxial compression tests.Numerical simulations were carried out to investigate how the breakage behaviors are affected by different loading directions with different impact velocities.The loading direction,input energy,and spatial distribution of the mineral phase had a remarkable influence on the failure patterns and load-carrying capacities.The shape of the gangue phase and the approximate location of the gangue interfaces are key parameters to consider when investigating the failure patterns and fracture mechanism of heterogeneous rock materials.The damage and fracture tended to propagate from the surfaces to the HCR interior.The gangue phase area contacting the loading wall,growth direction of the strong gangue interfaces,and loading directions greatly influenced the failure patterns of the heterogeneous rock materials.
文摘An extension to texture mapping is given in this paper for improving theefficiency of image-based rendering. For a depth image with an orthogonal displacement at eachpixel, it is decomposed by the displacement into a series of layered textures (LTs) with each onehaving the same displacement for all its texels. Meanwhile, some texels of the layered textures areinterpolated for obtaining a continuous 3D approximation of the model represented in the depthimage. Thus, the plane-to-plane texture mapping can be used to map these layered textures to producenovel views and the advantages can be obtained as follows: accelerating the rendering speed,supporting the 3D surface details and view motion parallax, and avoiding the expensive task ofhole-filling in the rendering stage. Experimental results show the new method can producehigh-quality images and run faster than many famous image-based rendering techniques.
基金supported by the National Natural Science Foundation of China under Grant No.90920009the National High-Tech Research and Development 863 Program of China under Grant No.2009AA01Z323
文摘In this paper, we investigate the problem of determining regions in 3D scene visible to some given viewpoints when obstacles are present in the scene. We assume that the obstacles are composed of some opaque objects with closed surfaces. The problem is formulated in an implicit framework where the obstacles are represented by a level set function. The visible and invisible regions of the given viewpoints are determined through an efficient implicit ray tracing technique. As an extension of our approach, we apply the multiview visibility estimation to an image-based modeling technique. The unknown scene geometry and multiview visibility information are incorporated into a variational energy functional. By minimizing the energy functional, the true scene geometry as well as the accurate visibility information of the multiple views can be recovered from a number of scene images. This makes it feasible to handle the visibility problem of multiple views by our approach when the true scene geometry is unknown.
基金Supported by the National Basic Research 973 Program of China under Grant No.2009CB320802the National High-Tech Research and Development 863 Program of China under Grant No.2008AA01Z301+2 种基金the National Natural Science Foundation of Chinaunder Grant No.60833007the Research Grant from University of Macao,RGC Research Grant (Ref.416007)UGC Direct Grant(No.2050349)
文摘In this paper, we present a hybrid representation of image-based models combining the textured planes and the hierarchical points. Taking a set of depth images as input, our method starts from classifying input pixels into two categories, indicating the planar and non-planar surfaces respectively. For the planar surfaces, the geometric coefficients are reconstructed to form the uniformly sampled textures. For nearly planar surfaces, some textured planes, called lumiproxies, are constructed to represent the equivalent visual appearance. The Hough transform is used to find the positions of these textured planes, and optic flow measures are used to determine their textures. For remaining pixels corresponding to the non-planar geometries, the point primitive is applied, reorganized as the OBB-tree structure. Then, texture mapping and point splatting are employed together to render the novel views, with the hardware acceleration.
文摘The most important goal of virtual reality is to create a virtual world by computers where users are allowed to view the environment and control the virtual objects interactively. naditionally virtual reality systems use 3D computer graphics to model and render a virtual environment in real time. However, this approach usually requires laborious modeling and expensive special-purpose rendering hardware. Image-based rendering is a new approach in composing a virtual environment in which a set of panoramic images is used to compose the virtual environment and walking in the space is accomplished by 'hopping' to different panoramic points. This paper introduces an experimeatal image-based VR system. The techniques utilized in the system, in particular the authoring and interactive control tools of the system, are described in detail.
文摘The effective thermal conductivity of heterogeneous or composite materials is an essential physical parameter of materials selection and design for specific functions in science and engineering. The effective thermal conductivity is heavily relied on the fraction and spatial distribution of each phase. In this work, image- based finite element method （FEM） was used to calculate the effective thermal conductivity of porous ceramics with different pore structures. Compared with former theoretical models such as effective media theory （EMT） equation and parallel model, image-based FEM can be applied to a large variety of material systems with a relatively steady deviation. The deviation of image-based FEM computation mainly comes from the difference between the two dimensional （2D） image and the three dimensional （3D） structure of the real system, and an experiment was carried out to confirm this assumption. Factors influencing 2D and 3D effective thermal conductivities were studied by FEM to illustrate the accuracy and application conditions of image-based FEM.
文摘1. Background The virtual reality （VR） technology is now at the frontier of modern information science. VR is based on computer graphics, computer vision, and other fresh air topics in today＇s computer technology. Nowadays the VR technology has been applied successfully in variety of fields such as military simulation, industry, medical training and visualization, environment protection and entertainment.
基金support provided by the research funds from the Hong Kong Research Grants Council(Grant Nos.16206623,N_HKUST603/22,and C6006-20G).
文摘Correctly tracking the evolution of spatial heterogeneity of local degree of saturation(Sr)in unsaturated soils is essential to explain the seepage phenomenon,which is crucial to assessing slope stability.Several methods exist for quantifying the heterogeneity of local S_(r).However,a comprehensive comparison of these methods in terms of accuracy,relative advantages,and disadvantages is currently lacking.This paper presents a comparative analysis of local Sr obtained at multiple scales,ranging from the element scale to the slice,representative element volume(REV),pore,and voxel scales.The spatial heterogeneity of Sr in an unsaturated glass beads specimen at different matric suctions was visualised and quantified by multiscale X-ray micro-focus computed tomography image-based analysis methods.Local Sr obtained at different scales displayed a comparable trend along the sample depth,yet the REV-scale method showed a much scattered and discontinuous distribution.In contrast,the pore-scale method detected a distinct two-clustered,bimodal distribution of S_(r).The pore-scale method has the highest integrated resolution,as it has the highest spatial resolution(i.e.number of data points)and provides more information(i.e.number of extractable physical parameters).This method thus provides a more effective approach for tracking the spatial heterogeneity of S_(r).Based on this method,pore-scale water retention curves were determined,offering new quantitative means to characterise pore water heterogeneity and explainwater drainage processes such as hysteresis at the pore scale.
基金supported in part by the National Natural Science Foundation of China(52378431,52408454)Fundamental Research Funds for the Central Universities,Chang’an University(300102210302,300102210118)+1 种基金111 Project of Sustainable Transportation for Urban Agglomeration in Western China(B20035)the 111 Project of Low Carbon Smart Road Infrastructure Construction and Maintenance Discipline Innovation and Talent Introduction Base of Shaanxi Province.
文摘Pavement distress detection plays a pivotal role in ensuring roadway safety,serviceability,and cost-effective infrastructure management.With rapid advancements in intelligent transportation systems,computer vision,and sensing technologies,non-contact detection approaches based on images and point clouds have become increasingly prominent due to their efficiency,objectivity,and scalability.This review systematically examines both image-based and point cloud-based methodologies,structured along the complete detection pipeline encompassing data acquisition,preprocessing,distress extraction,and geometric quantification.Image-based techniques rely on visual cues,such as texture,color,and edge continuity,to identify surface-level anomalies efficiently,benefiting from mature deep learning frameworks for classification,object detection,and pixel-level segmentation.In contrast,point cloud-based methods capture rich three-dimensional geometric and structural information,enabling detailed modeling of crack depth,rutting deformation,and surface irregularities.Although each modality can independently achieve satisfactory performance,their complementary strengths have driven a growing trend toward hybrid frameworks,combining image-based rapid screening with point cloud-based precision modeling,to enhance detection accuracy,robustness,and adaptability across varying conditions.Furthermore,this paper highlights persistent challenges,including multimodal data fusion,high equipment and labeling costs,computational complexity,and the need for standardized benchmarks.By synthesizing current progress and identifying key technical bottlenecks,this review provides a comprehensive foundation and forward-looking perspective for developing intelligent,efficient,and scalable pavement distress detection systems.
基金supported by the funding from the National Natural Science Foundation of China(32072359)。
文摘Wheat powdery mildew caused by Blumeria graminis f.sp.tritici(Bgt)is an important disease worldwide.Detection of latent infection of leaves by the pathogen in late autumn is valuable for estimating the inoculum potential to assess disease risks in the spring.We developed a new tool for rapid detection and quantification of latent infection of seedlings by the pathogen.The method was based on recombinase polymerase amplification(RPA)coupled with an end-point detection via lateral flow device(LFD).The limit of detection is 100 agμL^(-1)of Bgt DNA,without noticeable interference from either other common wheat pathogens or wheat material(Triticum aestivum).It was evaluated on wheat seedlings for this accuracy and sensitivity in detecting latent infection of Bgt.We further extended this RPALFD assay to estimate the level of latent infection by Bgt based on imaging analysis.There was a strong correlation between the image-based and real-time PCR assay estimates of Bgt DNA.The present results suggested that this new tool can provide rapid and accurate quantification of Bgt in latently infected leaves and can be further development as an on-site monitoring tool.
基金National Key R&D Program of China,No.2017YFC0908300.
文摘Gastric cancer is the fourth leading cause of cancer-related mortality across the globe,with a 5-year survival rate of less than 40%.In recent years,several applications of artificial intelligence(AI)have emerged in the gastric cancer field based on its efficient computational power and learning capacities,such as imagebased diagnosis and prognosis prediction.AI-assisted diagnosis includes pathology,endoscopy,and computerized tomography,while researchers in the prognosis circle focus on recurrence,metastasis,and survival prediction.In this review,a comprehensive literature search was performed on articles published up to April 2020 from the databases of PubMed,Embase,Web of Science,and the Cochrane Library.Thereby the current status of AI-applications was systematically summarized in gastric cancer.Moreover,future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2018R1A2B6007333).
文摘Compressive strength of concrete is a significant factor to assess building structure health and safety.Therefore,various methods have been developed to evaluate the compressive strength of concrete structures.However,previous methods have several challenges in costly,time-consuming,and unsafety.To address these drawbacks,this paper proposed a digital vision based concrete compressive strength evaluating model using deep convolutional neural network(DCNN).The proposed model presented an alternative approach to evaluating the concrete strength and contributed to improving efficiency and accuracy.The model was developed with 4,000 digital images and 61,996 images extracted from video recordings collected from concrete samples.The experimental results indicated a root mean square error(RMSE)value of 3.56(MPa),demonstrating a strong feasibility that the proposed model can be utilized to predict the concrete strength with digital images of their surfaces and advantages to overcome the previous limitations.This experiment contributed to provide the basis that could be extended to future research with image analysis technique and artificial neural network in the diagnosis of concrete building structures.
