Light field(LF)imaging has attracted attention because of its ability to solve computer vision problems.In this paper we briefly review the research progress in computer vision in recent years.For most factors that af...Light field(LF)imaging has attracted attention because of its ability to solve computer vision problems.In this paper we briefly review the research progress in computer vision in recent years.For most factors that affect computer vision development,the richness and accuracy of visual information acquisition are decisive.LF imaging technology has made great contributions to computer vision because it uses cameras or microlens arrays to record the position and direction information of light rays,acquiring complete three-dimensional(3D)scene information.LF imaging technology improves the accuracy of depth estimation,image segmentation,blending,fusion,and 3D reconstruction.LF has also been innovatively applied to iris and face recognition,identification of materials and fake pedestrians,acquisition of epipolar plane images,shape recovery,and LF microscopy.Here,we further summarize the existing problems and the development trends of LF imaging in computer vision,including the establishment and evaluation of the LF dataset,applications under high dynamic range(HDR)conditions,LF image enhancement,virtual reality,3D display,and 3D movies,military optical camouflage technology,image recognition at micro-scale,image processing method based on HDR,and the optimal relationship between spatial resolution and four-dimensional(4D)LF information acquisition.LF imaging has achieved great success in various studies.Over the past 25 years,more than 180 publications have reported the capability of LF imaging in solving computer vision problems.We summarize these reports to make it easier for researchers to search the detailed methods for specific solutions.展开更多
AIM: To further improve the endoscopic detection of intestinal mucosa alterations due to celiac disease(CD).METHODS: We assessed a hybrid approach based on the integration of expert knowledge into the computerbased cl...AIM: To further improve the endoscopic detection of intestinal mucosa alterations due to celiac disease(CD).METHODS: We assessed a hybrid approach based on the integration of expert knowledge into the computerbased classification pipeline. A total of 2835 endoscopic images from the duodenum were recorded in 290 children using the modified immersion technique(MIT). These children underwent routine upper endoscopy for suspected CD or non-celiac upper abdominal symptoms between August 2008 and December 2014. Blinded to the clinical data and biopsy results, three medical experts visually classified each image as normal mucosa(Marsh-0) or villous atrophy(Marsh-3). The experts' decisions were further integrated into state-of-the-arttexture recognition systems. Using the biopsy results as the reference standard, the classification accuracies of this hybrid approach were compared to the experts' diagnoses in 27 different settings.RESULTS: Compared to the experts' diagnoses, in 24 of 27 classification settings(consisting of three imaging modalities, three endoscopists and three classification approaches), the best overall classification accuracies were obtained with the new hybrid approach. In 17 of 24 classification settings, the improvements achieved with the hybrid approach were statistically significant(P < 0.05). Using the hybrid approach classification accuracies between 94% and 100% were obtained. Whereas the improvements are only moderate in the case of the most experienced expert, the results of the less experienced expert could be improved significantly in 17 out of 18 classification settings. Furthermore, the lowest classification accuracy, based on the combination of one database and one specific expert, could be improved from 80% to 95%(P < 0.001).CONCLUSION: The overall classification performance of medical experts, especially less experienced experts, can be boosted significantly by integrating expert knowledge into computer-aided diagnosis systems.展开更多
Infrared thermography has been widely applied in real industrial inspection of aerospace,energy management systems,engines,and electric systems.However,two-dimensional imaging modality limits its development.Here,a te...Infrared thermography has been widely applied in real industrial inspection of aerospace,energy management systems,engines,and electric systems.However,two-dimensional imaging modality limits its development.Here,a technique named frequency multiplexed photothermal correlation tomography(FM-PCT)was developed to enable non-destructive and contactless cross-sectional imaging for manufactured material evaluation and characterization.By combining advantages of photothermal tomography and pulsed thermography,FM-PCT facilitates the generation of three-dimensional thermal images through temporal superposition(stacking)of two-dimensional images from sequential subsurface depths.FM-PCT image processing involves pulsed excitation signals to which frequency delay and matched filtering techniques are applied.Major features of FM-PCT are high-resolution three-dimensional tomographic imaging under low camera frame-rate conditions with self-correcting capability for diffusion(blurring)correction of subsurface images due to cross-correlation processing of individual frequencies in the Fourier decomposition spectrum of the excitation pulse.Furthermore,FM-PCT extends truncated-correlation photothermal coherence tomography from chirp and pulsed signals to more general linear heating sources.Lock-in thermography and x-ray computed tomography validation demonstrate that 3D FM-PCT imaging accurately reveals subsurface discontinuities/defects in solids despite the diffusive nature of thermal-wave imaging.展开更多
We present a new method for automatically forecasting the occurrence of solar flares based on photospheric magnetic measurements. The method is a cascading combination of an ordinal logistic regression model and a sup...We present a new method for automatically forecasting the occurrence of solar flares based on photospheric magnetic measurements. The method is a cascading combination of an ordinal logistic regression model and a support vector machine classifier. The predictive variables are three photospheric magnetic parameters, i.e., the total unsigned magnetic flux, length of the strong-gradient magnetic polarity inversion line, and total magnetic energy dissipation. The output is true or false for the occurrence of a certain level of flares within 24 hours. Experimental results, from a sample of 230 active regions between 1996 and 2005, show the accuracies of a 24- hour flare forecast to be 0.86, 0.72, 0.65 and 0.84 respectively for the four different levels. Comparison shows an improvement in the accuracy of X-class flare forecasting.展开更多
A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a...A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a multi-block SSD mechanism,which consists of three steps,is designed.First,the original input images are segmented into several overlapped patches.Second,each patch is separately fed into an SSD to detect the objects.Third,the patches are merged together through two stages.In the first stage,the truncated object of the sub-layer detection result is spliced.In the second stage,a sub-layer suppression and filtering algorithm applying the concept of non-maximum suppression is utilized to remove the overlapped boxes of sub-layers.The boxes that are not detected in the main-layer are retained.In addition,no sufficient labeled training samples of railway circumstance are available,thereby hindering the deployment of SSD.A two-stage training strategy leveraging to transfer learning is adopted to solve this issue.The deep learning model is preliminarily trained using labeled data of numerous auxiliaries,and then it is refined using only a few samples of railway scene.A railway spot in China,which is easily damaged by landslides,is investigated as a case study.Experimental results show that the proposed multi-block SSD method produces an overall accuracy of 96.6%and obtains an improvement of up to 9.2%compared with the traditional SSD.展开更多
High intensity focused ultrasound(HIFU)therapy is an effective method in clinical treatment of tumors,in order to explore the bio-heat conduction mechanism of in multi-layer media by concave spherical transducer,tempe...High intensity focused ultrasound(HIFU)therapy is an effective method in clinical treatment of tumors,in order to explore the bio-heat conduction mechanism of in multi-layer media by concave spherical transducer,temperature field induced by this kind of transducer in multi-layer media will be simulated through solving Pennes equation with finite difference method,and the influence of initial sound pressure,absorption coefficient,and thickness of different layers of biological tissue as well as thermal conductivity parameter on sound focus and temperature distribution will be analyzed,respectively.The results show that the temperature in focus area increases faster while the initial sound pressure and thermal conductivity increase.The absorption coefficient is smaller,the ultrasound intensity in the focus area is bigger,and the size of the focus area is increasing.When the thicknesses of different layers of tissue change,the focus position changes slightly,but the sound intensity of the focus area will change obviously.The temperature in focus area will rise quickly before reaching a threshold,and then the temperature will keep in the threshold range.展开更多
With the rapid development of global information and the increasing dependence on network for people, network security problems are becoming more and more serious. By analyzing the existing security assessment methods...With the rapid development of global information and the increasing dependence on network for people, network security problems are becoming more and more serious. By analyzing the existing security assessment methods, we propose a network security situation evaluation system based on modified D-S evidence theory is proposed. Firstly, we give a modified D-S evidence theory to improve the reliability and rationality of the fusion result and apply the theory to correlation analysis. Secondly, the attack successful support is accurately calculated by matching internal factors with external threats. Multi-module evaluation is established to comprehensively evaluate the situation of network security. Finally we use an example of actual network datasets to validate the network security situation evaluation system. The simulation result shows that the system can not only reduce the rate of false positives and false alarms, but also effectively help analysts comprehensively to understand the situation of network security.展开更多
Due to the encephalic tissues are highly irregular, three-dimensional （3D） modeling of brain always leads to compli- cated computing. In this paper, we explore an efficient method for brain surface reconstruction fr...Due to the encephalic tissues are highly irregular, three-dimensional （3D） modeling of brain always leads to compli- cated computing. In this paper, we explore an efficient method for brain surface reconstruction from magnetic reso- nance （MR） images of head, which is helpful to surgery planning and tumor localization. A heuristic algorithm is pro- posed foi＂ surface triangle mesh generation with preserved features, and the diagonal length is regarded as the heuristic information to optimize the shape of triangle. The experimental results show that our approach not only reduces the computational complexity, but also completes 3D visualization with good quality.展开更多
Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neur...Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network(CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field(CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.展开更多
It is novel to apply three-dimensional(3D)light field imaging technology to recognize two-dimensional(2D)fake pedestrians.In this paper,we propose a parallel support vector machine(SVM)method based on 3D light field i...It is novel to apply three-dimensional(3D)light field imaging technology to recognize two-dimensional(2D)fake pedestrians.In this paper,we propose a parallel support vector machine(SVM)method based on 3D light field imaging(light field camera)and machine learning techniques.A light field(LF)camera with robust sensors,which is able to record rich 3D information,is used as hardware equipment.Histogram of oriented gradient(HOG)feature extraction algorithm and SVM classification method are used to recognize the real and 2D fake pedestrians efficiently.Besides,we carry out an experiment on our improved LF pedestrian dataset.The experimental results of parameter optimization study show that in the case of 400 training samples(200 positive samples and 200 negative samples),120 to 420 testing samples,and an HOG cellsize as 8×8,the best recognition accuracy with polynomial kernel function is improved by more than 2%compared with the previous method.The best accuracy is 99.17%.Otherwise,the recognition accuracy of more than 98.00%will be obtained even under other experimental conditions.展开更多
Focusing on data imbalance and intraclass variation,an improved pedestrian detection with a cascade of complex peer AdaBoost classifiers is proposed.The series of the AdaBoost classifiers are learned greedily,along wi...Focusing on data imbalance and intraclass variation,an improved pedestrian detection with a cascade of complex peer AdaBoost classifiers is proposed.The series of the AdaBoost classifiers are learned greedily,along with negative example mining.The complexity of classifiers in the cascade is not limited,so more negative examples are used for training.Furthermore,the cascade becomes an ensemble of strong peer classifiers,which treats intraclass variation.To locally train the AdaBoost classifiers with a high detection rate,a refining strategy is used to discard the hardest negative training examples rather than decreasing their thresholds.Using the aggregate channel feature(ACF),the method achieves miss rates of 35%and 14%on the Caltech pedestrian benchmark and Inria pedestrian dataset,respectively,which are lower than that of increasingly complex AdaBoost classifiers,i.e.,44%and 17%,respectively.Using deep features extracted by the region proposal network(RPN),the method achieves a miss rate of 10.06%on the Caltech pedestrian benchmark,which is also lower than 10.53%from the increasingly complex cascade.This study shows that the proposed method can use more negative examples to train the pedestrian detector.It outperforms the existing cascade of increasingly complex classifiers.展开更多
Unsupervised image-to-image translation is a challenging task for computer vision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only f...Unsupervised image-to-image translation is a challenging task for computer vision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only focused on image-level translation but ignored image features processing, which led to a certain semantics loss, such as the changes of the background of the generated image, partial transformation, and so on. In this work, we propose a method of image-to-image translation based on generative adversarial nets(GANs). We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image. Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image. At the same time, as expanding the convolution receptive field, the quality of the generated image is enhanced. Quantitative experiment shows that our method significantly outperforms previous works. Especially on images with obvious foreground, our model shows an impressive improvement.展开更多
This paper presents an image denoising method based on bilateral filtering and non-local means. The non-local region texture or structure of the image has the characteristics of repetition, which can be used to effect...This paper presents an image denoising method based on bilateral filtering and non-local means. The non-local region texture or structure of the image has the characteristics of repetition, which can be used to effectively preserve the edge and detail of the image. And compared with classical methods, bilateral filtering method has a better performance in denosing for the reason that the weight includes the geometric closeness factor and the intensity similarity factor. We combine the geometric closeness factor with the weight of non-local means, and construct a new weight. Experimental results show that the modified algorithm can achieve better performance. And it can protect the image detail and structure information better.展开更多
Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely ex...Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3 D shape. To address these challenges, we propose a semantics-aware transformer(SATF) for 3 D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue(RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the Shape Net dataset show that our SATF outperforms the state-of-the-art methods.展开更多
In this paper, a refractive index(RI) sensor based on the twin-core photonic crystal fiber(TC-PCF) is presented. Introducing the rectangular array in the core area makes the PCF possible to obtain high birefringence a...In this paper, a refractive index(RI) sensor based on the twin-core photonic crystal fiber(TC-PCF) is presented. Introducing the rectangular array in the core area makes the PCF possible to obtain high birefringence and low confinement loss over the wavelength range from 0.6 μm to 1.7 μm. Therefore, the core region can enhance the interaction between the core mode and the filling material. We studied theoretically the evolution characteristics of the birefringence and operating wavelength corresponding to the strongest polarization point under the condition of filling the rectangular array with RI matching fluid range from 1.33 to 1.41. Simulation results reveal that the proposed TC-PCF has opposite evolutions of change rates between the B and wavelength, and the maximum RI sensing sensitivities of 1.809× 10-2 B/RIU and 8 700 nm/RIU at low and high RI infill are obtained respectively, which means that the TC-PCF features of dual-parameter demodulation for the RI sensing can maintain a high refractive index sensing sensitivity within a large scope of RI ranging from 1.33 to 1.41. Compared with the results of single-parameter demodulation, it is an optimized method to improve the sensitivity of low refractive index sensors, which has great application potency in the field of biochemical sensing and detection.展开更多
This paper proposes a robust auto-focus(AF) measure based on inner energy. In general, the inner energy of noise pixels is close to zero because the magnitude of gradient and the direction of the noise pixels are rand...This paper proposes a robust auto-focus(AF) measure based on inner energy. In general, the inner energy of noise pixels is close to zero because the magnitude of gradient and the direction of the noise pixels are random. Therefore, the inner energy can effectively eliminate the influence of noise on image quality assessment. But the gradients of near edge points are consistent with those of edge points, so the inner energy of edge pixels is relatively large, and the detail information of the image can be highlighted. Experimental results indicate that compared with traditional methods, the proposed method has higher accuracy, fewer local peaks, stronger robustness and better practicability. In particular, the evaluation results are close to the subjective evaluation of the human eyes. These results illustrate that the proposed method can be applied in automatic focusing.展开更多
We investigate the evolution of cooperation with evolutionary public goods games based on finite populations, where four pure strategies： cooperators, defectors, punishers and loners who are unwilling to participate ...We investigate the evolution of cooperation with evolutionary public goods games based on finite populations, where four pure strategies： cooperators, defectors, punishers and loners who are unwilling to participate are considered. By adopting approximate best response dynamics, we show that the magnitude of rationality not only quantitatively explains the experiment results in [Nature （London） 425 （2003） 390], but also it will heavily influence the evolution of cooperation. Compared with previous results of infinite populations, which result in two equilibriums, we show that there merely exists a special equilibrium cooperation. In addition, we characterize that loner＇s and the relevant high value of bounded rationality will sustain payoff plays an active role in the maintenance of cooperation, which will only be warranted for the low and moderate values of loner＇s payoff. It thus indicates the effects of rationality and loner＇s payoff will influence the cooperation. Finally, we highlight the important result that the introduction of voluntary participation and punishment will facilitate cooperation greatly.展开更多
To deeply understand the emergence of cooperation in natural,social and economical systems,we present an improved fitness evaluation mechanism with memory in spatial prisoner's dilemma game on regular lattices.In ...To deeply understand the emergence of cooperation in natural,social and economical systems,we present an improved fitness evaluation mechanism with memory in spatial prisoner's dilemma game on regular lattices.In our model,the individual fitness is not only determined by the payoff in the current game round,but also by the payoffs in previous round bins.A tunable parameter,termed as the memory strength(μ),which lies between 0 and 1,is introduced into the model to regulate the ratio of payoffs of current and previous game rounds in the individual fitness calculation.When μ = 0,our model is reduced to the standard prisoner's dilemma game;while μ = 1 represents the case in which the payoff is totally determined by the initial strategies and thus it is far from the realistic ones.Extensive numerical simulations indicate that the memory effect can substantially promote the evolution of cooperation.For μ < 1,the stronger the memory effect,the higher the cooperation level,but μ = 1 leads to a pathological state of cooperation,but can partially enhance the cooperation in the very large temptation parameter.The current results are of great significance for us to account for the role of memory effect during the evolution of cooperation among selfish players.展开更多
After reviewing three different definitions of mode field diameter of single-mode fibers, coupled efficiency calculation methods associated with lateral offset, longitude separation and wavelength, the effects produce...After reviewing three different definitions of mode field diameter of single-mode fibers, coupled efficiency calculation methods associated with lateral offset, longitude separation and wavelength, the effects produced by them, and the influences of splicing defects were discussed in detail. The regularities of the effects were studied according to the first order derivation of couple efficiency formula, and a simplified formula for couple efficiency calculation was presented under the circumstance of slight misalignment, with respect to wavelength, 2, and in a good agreement with the theoretical model. The simplified formula provides a new but simple approach to evaluate wavelength dependent couple efficiency of single-mode fibers. Theoretical analyses and numerical calculations show that, when those defects exist, the wavelength produces additional effects on the couple loss that growth of wavelength causes an increase on the couple efficiency for the lateral offset or longitude separation whereas lessens the couple efficiency due to angular misalignment or mode fields mismatching, and that the wavelength degrades the couple efficiency distinctly when λ≥2.5 μm whereas it distorts the couple slightly in range of λ≤2λ≤2 μm.展开更多
Arecanut disease identification is a challenging problem in the field of image processing.In this work,we present a new combination of multi-gradient-direction and deep con-volutional neural networks for arecanut dise...Arecanut disease identification is a challenging problem in the field of image processing.In this work,we present a new combination of multi-gradient-direction and deep con-volutional neural networks for arecanut disease identification,namely,rot,split and rot-split.Due to the effect of the disease,there are chances of losing vital details in the images.To enhance the fine details in the images affected by diseases,we explore multi-Sobel directional masks for convolving with the input image,which results in enhanced images.The proposed method extracts arecanut as foreground from the enhanced images using Otsu thresholding.Further,the features are extracted for foreground information for disease identification by exploring the ResNet architecture.The advantage of the proposed approach is that it identifies the diseased images from the healthy arecanut images.Experimental results on the dataset of four classes(healthy,rot,split and rot-split)show that the proposed model is superior in terms of classification rate.展开更多
基金Project supported by the National Natural Science Foundation of China(Nos.61906133,62020106004,and 92048301)。
文摘Light field(LF)imaging has attracted attention because of its ability to solve computer vision problems.In this paper we briefly review the research progress in computer vision in recent years.For most factors that affect computer vision development,the richness and accuracy of visual information acquisition are decisive.LF imaging technology has made great contributions to computer vision because it uses cameras or microlens arrays to record the position and direction information of light rays,acquiring complete three-dimensional(3D)scene information.LF imaging technology improves the accuracy of depth estimation,image segmentation,blending,fusion,and 3D reconstruction.LF has also been innovatively applied to iris and face recognition,identification of materials and fake pedestrians,acquisition of epipolar plane images,shape recovery,and LF microscopy.Here,we further summarize the existing problems and the development trends of LF imaging in computer vision,including the establishment and evaluation of the LF dataset,applications under high dynamic range(HDR)conditions,LF image enhancement,virtual reality,3D display,and 3D movies,military optical camouflage technology,image recognition at micro-scale,image processing method based on HDR,and the optimal relationship between spatial resolution and four-dimensional(4D)LF information acquisition.LF imaging has achieved great success in various studies.Over the past 25 years,more than 180 publications have reported the capability of LF imaging in solving computer vision problems.We summarize these reports to make it easier for researchers to search the detailed methods for specific solutions.
基金Supported by the Austrian Science Fund(FWF),No.KLI 429-B13 to Vécsei A
文摘AIM: To further improve the endoscopic detection of intestinal mucosa alterations due to celiac disease(CD).METHODS: We assessed a hybrid approach based on the integration of expert knowledge into the computerbased classification pipeline. A total of 2835 endoscopic images from the duodenum were recorded in 290 children using the modified immersion technique(MIT). These children underwent routine upper endoscopy for suspected CD or non-celiac upper abdominal symptoms between August 2008 and December 2014. Blinded to the clinical data and biopsy results, three medical experts visually classified each image as normal mucosa(Marsh-0) or villous atrophy(Marsh-3). The experts' decisions were further integrated into state-of-the-arttexture recognition systems. Using the biopsy results as the reference standard, the classification accuracies of this hybrid approach were compared to the experts' diagnoses in 27 different settings.RESULTS: Compared to the experts' diagnoses, in 24 of 27 classification settings(consisting of three imaging modalities, three endoscopists and three classification approaches), the best overall classification accuracies were obtained with the new hybrid approach. In 17 of 24 classification settings, the improvements achieved with the hybrid approach were statistically significant(P < 0.05). Using the hybrid approach classification accuracies between 94% and 100% were obtained. Whereas the improvements are only moderate in the case of the most experienced expert, the results of the less experienced expert could be improved significantly in 17 out of 18 classification settings. Furthermore, the lowest classification accuracy, based on the combination of one database and one specific expert, could be improved from 80% to 95%(P < 0.001).CONCLUSION: The overall classification performance of medical experts, especially less experienced experts, can be boosted significantly by integrating expert knowledge into computer-aided diagnosis systems.
基金the National Key Research and Development Program of China(2023YFE0197800)the Natural Sciences and Engineering Research Council of Canada(NSERC)through the CREATE-oN DuTy!Program(496439-2017)+5 种基金the Canada Research Chair in Multi-polar Infrared Vision(MIVIM)the Canada Foundation for Innovationthe Natural Sciences and Engineering Research Council(NSERC)Discovery Grants Program(RGPIN-2020-04595)the Canada Foundation for Innovation(CFI)Research Chairs Program(950-230876)the New Frontiers in Research Fund—Exploration(NFRFE-2019-00647)the CFI-JELF program(38794)。
文摘Infrared thermography has been widely applied in real industrial inspection of aerospace,energy management systems,engines,and electric systems.However,two-dimensional imaging modality limits its development.Here,a technique named frequency multiplexed photothermal correlation tomography(FM-PCT)was developed to enable non-destructive and contactless cross-sectional imaging for manufactured material evaluation and characterization.By combining advantages of photothermal tomography and pulsed thermography,FM-PCT facilitates the generation of three-dimensional thermal images through temporal superposition(stacking)of two-dimensional images from sequential subsurface depths.FM-PCT image processing involves pulsed excitation signals to which frequency delay and matched filtering techniques are applied.Major features of FM-PCT are high-resolution three-dimensional tomographic imaging under low camera frame-rate conditions with self-correcting capability for diffusion(blurring)correction of subsurface images due to cross-correlation processing of individual frequencies in the Fourier decomposition spectrum of the excitation pulse.Furthermore,FM-PCT extends truncated-correlation photothermal coherence tomography from chirp and pulsed signals to more general linear heating sources.Lock-in thermography and x-ray computed tomography validation demonstrate that 3D FM-PCT imaging accurately reveals subsurface discontinuities/defects in solids despite the diffusive nature of thermal-wave imaging.
基金supported by NSF under grants ATM-071 6950,ATM-0745744NASA under grant NNXO-8 AQ90G
文摘We present a new method for automatically forecasting the occurrence of solar flares based on photospheric magnetic measurements. The method is a cascading combination of an ordinal logistic regression model and a support vector machine classifier. The predictive variables are three photospheric magnetic parameters, i.e., the total unsigned magnetic flux, length of the strong-gradient magnetic polarity inversion line, and total magnetic energy dissipation. The output is true or false for the occurrence of a certain level of flares within 24 hours. Experimental results, from a sample of 230 active regions between 1996 and 2005, show the accuracies of a 24- hour flare forecast to be 0.86, 0.72, 0.65 and 0.84 respectively for the four different levels. Comparison shows an improvement in the accuracy of X-class flare forecasting.
基金supported by Beijing Natural Science Foundation,China(No.4182020)Open Fund of State Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,China(No.17E01)Key Laboratory for Health Monitoring and Control of Large Structures,Shijiazhuang,China(No.KLLSHMC1901)。
文摘A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a multi-block SSD mechanism,which consists of three steps,is designed.First,the original input images are segmented into several overlapped patches.Second,each patch is separately fed into an SSD to detect the objects.Third,the patches are merged together through two stages.In the first stage,the truncated object of the sub-layer detection result is spliced.In the second stage,a sub-layer suppression and filtering algorithm applying the concept of non-maximum suppression is utilized to remove the overlapped boxes of sub-layers.The boxes that are not detected in the main-layer are retained.In addition,no sufficient labeled training samples of railway circumstance are available,thereby hindering the deployment of SSD.A two-stage training strategy leveraging to transfer learning is adopted to solve this issue.The deep learning model is preliminarily trained using labeled data of numerous auxiliaries,and then it is refined using only a few samples of railway scene.A railway spot in China,which is easily damaged by landslides,is investigated as a case study.Experimental results show that the proposed multi-block SSD method produces an overall accuracy of 96.6%and obtains an improvement of up to 9.2%compared with the traditional SSD.
基金Project(11174077)supported by the National Natural Science Foundation of ChinaProject(11JJ3079)supported by the Hunan Provincial Natural Science Foundation of ChinaProjects(12C0237,11C0844)supported by the Science Research Program of Education Department of Hunan Province,China
文摘High intensity focused ultrasound(HIFU)therapy is an effective method in clinical treatment of tumors,in order to explore the bio-heat conduction mechanism of in multi-layer media by concave spherical transducer,temperature field induced by this kind of transducer in multi-layer media will be simulated through solving Pennes equation with finite difference method,and the influence of initial sound pressure,absorption coefficient,and thickness of different layers of biological tissue as well as thermal conductivity parameter on sound focus and temperature distribution will be analyzed,respectively.The results show that the temperature in focus area increases faster while the initial sound pressure and thermal conductivity increase.The absorption coefficient is smaller,the ultrasound intensity in the focus area is bigger,and the size of the focus area is increasing.When the thicknesses of different layers of tissue change,the focus position changes slightly,but the sound intensity of the focus area will change obviously.The temperature in focus area will rise quickly before reaching a threshold,and then the temperature will keep in the threshold range.
基金Supported by the Foundation of Tianjin for Science and Technology Innovation(10FDZDGX00400,11ZCKFGX00900)Key Project of Educational Reform Foundation of Tianjin Municipal Education Commission(C03-0809)
文摘With the rapid development of global information and the increasing dependence on network for people, network security problems are becoming more and more serious. By analyzing the existing security assessment methods, we propose a network security situation evaluation system based on modified D-S evidence theory is proposed. Firstly, we give a modified D-S evidence theory to improve the reliability and rationality of the fusion result and apply the theory to correlation analysis. Secondly, the attack successful support is accurately calculated by matching internal factors with external threats. Multi-module evaluation is established to comprehensively evaluate the situation of network security. Finally we use an example of actual network datasets to validate the network security situation evaluation system. The simulation result shows that the system can not only reduce the rate of false positives and false alarms, but also effectively help analysts comprehensively to understand the situation of network security.
基金supported by the National Natural Science Foundation of China(No.61202169)
文摘Due to the encephalic tissues are highly irregular, three-dimensional （3D） modeling of brain always leads to compli- cated computing. In this paper, we explore an efficient method for brain surface reconstruction from magnetic reso- nance （MR） images of head, which is helpful to surgery planning and tumor localization. A heuristic algorithm is pro- posed foi＂ surface triangle mesh generation with preserved features, and the diagonal length is regarded as the heuristic information to optimize the shape of triangle. The experimental results show that our approach not only reduces the computational complexity, but also completes 3D visualization with good quality.
基金supported by the National Natural Science Foundation of China(Nos.U1509207,61325019,61472278,61403281 and 61572357)the Key Project of Natural Science Foundation of Tianjin(No.14JCZDJC31700)
文摘Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network(CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field(CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.
基金supported by the National Natural Science Foundation of China(Nos.61906133,62020106004,92048301 and 61703304)
文摘It is novel to apply three-dimensional(3D)light field imaging technology to recognize two-dimensional(2D)fake pedestrians.In this paper,we propose a parallel support vector machine(SVM)method based on 3D light field imaging(light field camera)and machine learning techniques.A light field(LF)camera with robust sensors,which is able to record rich 3D information,is used as hardware equipment.Histogram of oriented gradient(HOG)feature extraction algorithm and SVM classification method are used to recognize the real and 2D fake pedestrians efficiently.Besides,we carry out an experiment on our improved LF pedestrian dataset.The experimental results of parameter optimization study show that in the case of 400 training samples(200 positive samples and 200 negative samples),120 to 420 testing samples,and an HOG cellsize as 8×8,the best recognition accuracy with polynomial kernel function is improved by more than 2%compared with the previous method.The best accuracy is 99.17%.Otherwise,the recognition accuracy of more than 98.00%will be obtained even under other experimental conditions.
基金Project(2018AAA0102102)supported by the National Science and Technology Major Project,ChinaProject(2017WK2074)supported by the Planned Science and Technology Project of Hunan Province,China+1 种基金Project(B18059)supported by the National 111 Project,ChinaProject(61702559)supported by the National Natural Science Foundation of China。
文摘Focusing on data imbalance and intraclass variation,an improved pedestrian detection with a cascade of complex peer AdaBoost classifiers is proposed.The series of the AdaBoost classifiers are learned greedily,along with negative example mining.The complexity of classifiers in the cascade is not limited,so more negative examples are used for training.Furthermore,the cascade becomes an ensemble of strong peer classifiers,which treats intraclass variation.To locally train the AdaBoost classifiers with a high detection rate,a refining strategy is used to discard the hardest negative training examples rather than decreasing their thresholds.Using the aggregate channel feature(ACF),the method achieves miss rates of 35%and 14%on the Caltech pedestrian benchmark and Inria pedestrian dataset,respectively,which are lower than that of increasingly complex AdaBoost classifiers,i.e.,44%and 17%,respectively.Using deep features extracted by the region proposal network(RPN),the method achieves a miss rate of 10.06%on the Caltech pedestrian benchmark,which is also lower than 10.53%from the increasingly complex cascade.This study shows that the proposed method can use more negative examples to train the pedestrian detector.It outperforms the existing cascade of increasingly complex classifiers.
基金supported in part by the National Natural Science Foundation of China(Nos.61906135,62020106004,92048301 and 61906027)the Tianjin Science and Technology Plan Project(No.20JCQNJC01350)。
文摘Unsupervised image-to-image translation is a challenging task for computer vision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only focused on image-level translation but ignored image features processing, which led to a certain semantics loss, such as the changes of the background of the generated image, partial transformation, and so on. In this work, we propose a method of image-to-image translation based on generative adversarial nets(GANs). We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image. Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image. At the same time, as expanding the convolution receptive field, the quality of the generated image is enhanced. Quantitative experiment shows that our method significantly outperforms previous works. Especially on images with obvious foreground, our model shows an impressive improvement.
基金supported by the Student’s Platform for Innovation and Entrepreneurship Training Program(No.201510060022)
文摘This paper presents an image denoising method based on bilateral filtering and non-local means. The non-local region texture or structure of the image has the characteristics of repetition, which can be used to effectively preserve the edge and detail of the image. And compared with classical methods, bilateral filtering method has a better performance in denosing for the reason that the weight includes the geometric closeness factor and the intensity similarity factor. We combine the geometric closeness factor with the weight of non-local means, and construct a new weight. Experimental results show that the modified algorithm can achieve better performance. And it can protect the image detail and structure information better.
基金supported by the National Key R&D Program of China (No.2018YFB1305200)the National Natural Science Foundation of China (Nos.61906134, 62020106004, 92048301, and 61925201)
文摘Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3 D shape. To address these challenges, we propose a semantics-aware transformer(SATF) for 3 D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue(RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the Shape Net dataset show that our SATF outperforms the state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(Nos.11804250,11904262 and 11704283)the Tianjin Natural Science Foundation(No.18JCQNJC71300)+1 种基金the Tianjin Education Commission Scientific Research Project(No.2018KJ146)the Opening Foundation of Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems(No.2019LODTS004)。
文摘In this paper, a refractive index(RI) sensor based on the twin-core photonic crystal fiber(TC-PCF) is presented. Introducing the rectangular array in the core area makes the PCF possible to obtain high birefringence and low confinement loss over the wavelength range from 0.6 μm to 1.7 μm. Therefore, the core region can enhance the interaction between the core mode and the filling material. We studied theoretically the evolution characteristics of the birefringence and operating wavelength corresponding to the strongest polarization point under the condition of filling the rectangular array with RI matching fluid range from 1.33 to 1.41. Simulation results reveal that the proposed TC-PCF has opposite evolutions of change rates between the B and wavelength, and the maximum RI sensing sensitivities of 1.809× 10-2 B/RIU and 8 700 nm/RIU at low and high RI infill are obtained respectively, which means that the TC-PCF features of dual-parameter demodulation for the RI sensing can maintain a high refractive index sensing sensitivity within a large scope of RI ranging from 1.33 to 1.41. Compared with the results of single-parameter demodulation, it is an optimized method to improve the sensitivity of low refractive index sensors, which has great application potency in the field of biochemical sensing and detection.
基金supported by the National Natural Science Foundation of China(Nos.U1509207 and 61325019)
文摘This paper proposes a robust auto-focus(AF) measure based on inner energy. In general, the inner energy of noise pixels is close to zero because the magnitude of gradient and the direction of the noise pixels are random. Therefore, the inner energy can effectively eliminate the influence of noise on image quality assessment. But the gradients of near edge points are consistent with those of edge points, so the inner energy of edge pixels is relatively large, and the detail information of the image can be highlighted. Experimental results indicate that compared with traditional methods, the proposed method has higher accuracy, fewer local peaks, stronger robustness and better practicability. In particular, the evaluation results are close to the subjective evaluation of the human eyes. These results illustrate that the proposed method can be applied in automatic focusing.
基金Supported by National Nature Science Foundation under Grant No.60904063the Tianjin municipal Natural Science Foundation under Grant Nos.11JCYBJC06600,11ZCKF6X00900,11ZCKFGX00900
文摘We investigate the evolution of cooperation with evolutionary public goods games based on finite populations, where four pure strategies： cooperators, defectors, punishers and loners who are unwilling to participate are considered. By adopting approximate best response dynamics, we show that the magnitude of rationality not only quantitatively explains the experiment results in [Nature （London） 425 （2003） 390], but also it will heavily influence the evolution of cooperation. Compared with previous results of infinite populations, which result in two equilibriums, we show that there merely exists a special equilibrium cooperation. In addition, we characterize that loner＇s and the relevant high value of bounded rationality will sustain payoff plays an active role in the maintenance of cooperation, which will only be warranted for the low and moderate values of loner＇s payoff. It thus indicates the effects of rationality and loner＇s payoff will influence the cooperation. Finally, we highlight the important result that the introduction of voluntary participation and punishment will facilitate cooperation greatly.
基金Supported by the National Natural Science Foundation of China under Grant Nos. 61203138,60904063Innovation Fund for Technology Based Firms in Tianjin
文摘To deeply understand the emergence of cooperation in natural,social and economical systems,we present an improved fitness evaluation mechanism with memory in spatial prisoner's dilemma game on regular lattices.In our model,the individual fitness is not only determined by the payoff in the current game round,but also by the payoffs in previous round bins.A tunable parameter,termed as the memory strength(μ),which lies between 0 and 1,is introduced into the model to regulate the ratio of payoffs of current and previous game rounds in the individual fitness calculation.When μ = 0,our model is reduced to the standard prisoner's dilemma game;while μ = 1 represents the case in which the payoff is totally determined by the initial strategies and thus it is far from the realistic ones.Extensive numerical simulations indicate that the memory effect can substantially promote the evolution of cooperation.For μ < 1,the stronger the memory effect,the higher the cooperation level,but μ = 1 leads to a pathological state of cooperation,but can partially enhance the cooperation in the very large temptation parameter.The current results are of great significance for us to account for the role of memory effect during the evolution of cooperation among selfish players.
基金Projects（51005074, 91123035） supported by the National Natural Science Foundation of China Project（201021200077） supported by the Frontier Research Program of Central South University, China
文摘After reviewing three different definitions of mode field diameter of single-mode fibers, coupled efficiency calculation methods associated with lateral offset, longitude separation and wavelength, the effects produced by them, and the influences of splicing defects were discussed in detail. The regularities of the effects were studied according to the first order derivation of couple efficiency formula, and a simplified formula for couple efficiency calculation was presented under the circumstance of slight misalignment, with respect to wavelength, 2, and in a good agreement with the theoretical model. The simplified formula provides a new but simple approach to evaluate wavelength dependent couple efficiency of single-mode fibers. Theoretical analyses and numerical calculations show that, when those defects exist, the wavelength produces additional effects on the couple loss that growth of wavelength causes an increase on the couple efficiency for the lateral offset or longitude separation whereas lessens the couple efficiency due to angular misalignment or mode fields mismatching, and that the wavelength degrades the couple efficiency distinctly when λ≥2.5 μm whereas it distorts the couple slightly in range of λ≤2λ≤2 μm.
文摘Arecanut disease identification is a challenging problem in the field of image processing.In this work,we present a new combination of multi-gradient-direction and deep con-volutional neural networks for arecanut disease identification,namely,rot,split and rot-split.Due to the effect of the disease,there are chances of losing vital details in the images.To enhance the fine details in the images affected by diseases,we explore multi-Sobel directional masks for convolving with the input image,which results in enhanced images.The proposed method extracts arecanut as foreground from the enhanced images using Otsu thresholding.Further,the features are extracted for foreground information for disease identification by exploring the ResNet architecture.The advantage of the proposed approach is that it identifies the diseased images from the healthy arecanut images.Experimental results on the dataset of four classes(healthy,rot,split and rot-split)show that the proposed model is superior in terms of classification rate.
