In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or ove...In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or overlooked. While deep learning techniques have been employed to segment teeth in panoramic X-ray images, accurate segmentation of individual teeth remains an underexplored area. In this study, we propose an end-to-end deep learning method that effectively addresses this challenge by employing an improved combinatorial loss function to separate the boundaries of adjacent teeth, enabling precise segmentation of individual teeth in panoramic X-ray images. We validate the feasibility of our approach using a challenging dataset. By training our segmentation network on 115 panoramic X-ray images, we achieve an intersection over union (IoU) of 86.56% for tooth segmentation and an accuracy of 65.52% in tooth counting on 87 test set images. Experimental results demonstrate the significant improvement of our proposed method in single tooth segmentation compared to existing methods.展开更多
In response to the challenges posed by insufficient real-time performance and suboptimal matching accuracy of traditional feature matching algorithms within automotive panoramic surround view systems,this paper has pr...In response to the challenges posed by insufficient real-time performance and suboptimal matching accuracy of traditional feature matching algorithms within automotive panoramic surround view systems,this paper has proposed a high-performance dimension reduction parallel matching algorithm that integrates Principal Component Analysis(PCA)and Dual-Heap Filtering(DHF).The algorithm employs PCA to map the feature points into the lower-dimensional space and employs the square of Euclidean distance for feature matching,which significantly reduces computational complexity.To ensure the accuracy of feature matching,the algorithm utilizes Dual-Heap Filtering to filter and refine matched point pairs.To further enhance matching speed and make optimal use of computational resources,the algorithm introduces a multi-core parallel matching strategy,greatly elevating the efficiency of feature matching.Compared to Scale-Invariant Feature Transform(SIFT)and Speeded Up Robust Features(SURF),the proposed algorithm reduces matching time by 77%to 80%and concurrently enhances matching accuracy by 5%to 15%.Experimental results demonstrate that the proposed algorithmexhibits outstanding real-time matching performance and accuracy,effectivelymeeting the feature-matching requirements of automotive panoramic surround view systems.展开更多
In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strat...In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strategy for extracting road cracks.This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images.The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously.A convolutional neural network is utilized to extract cracks from the panoramic sequence image.The extracted sequence image is then aligned with the laser point cloud,enabling the assignment of RGB information to the vehicle-mounted three dimensional(3D)point cloud and location information to the two dimensional(2D)panoramic image.Additionally,a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud.The three-dimensional data pertaining to the cracks can be acquired.The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks.The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks.This approach exhibits superior accuracy when compared to conventional methods.Moreover,it facilitates rapid and accurate identification and localization of road cracks,thereby playing a crucial role in ensuring road maintenance and traffic safety.Consequently,this technique finds extensive application in the domains of intelligent transportation and urbanization development.The technology exhibits significant promise for use in the domains of intelligent transportation and city development.展开更多
In this paper,we propose a novel approach to visualizing global geographical information:a panoramic sphere in an immersive environment.The whole geographical surface can be observed through the rotating of heads as t...In this paper,we propose a novel approach to visualizing global geographical information:a panoramic sphere in an immersive environment.The whole geographical surface can be observed through the rotating of heads as the viewpoint of the panoramic sphere is inside the sphere.We compared three approaches to visualizing the earth for rendering the geographical information in a virtual reality environment.On the tasks of terrestrial and marine geographical information,we compare the visualization effects on a)a globe,b)a flat map and c)a panoramic sphere.Terrestrial geographical information tasks include the area comparison and direction determination.Marine geographical information tasks contain the visualization of sea surface temperature and sea surface currents.For terrestrial geographical information tasks,the experimental results show that the panoramic sphere outperforms the globe and the flat map,with a higher average accuracy and a shorter time.On marine geographical information task,the panoramic sphere visualization is also superior to the flat map and the globe in an immersive environment for the sea surface temperature data and the sea surface current fields.In all three visualization experiments,the panoramic sphere is most preferred by the participants,particularly for global,transcontinental and transoceanic needs.展开更多
Background:This study aims to predict the extraction difficulty of mandibular third molars based on panoramic images using transfer learning while employing super-resolution(SR)technology to enhance the feasibility an...Background:This study aims to predict the extraction difficulty of mandibular third molars based on panoramic images using transfer learning while employing super-resolution(SR)technology to enhance the feasibility and validity of the prediction.Methods:We reviewed a total of 608 preoperative mandibular third molar panoramic radiographs from two medical facilities:the First Affiliated Hospital of Zhengzhou University(n=509;456 in the training set and 53 in the test set)and the Henan Provincial Dental Hospital(n=99 in the validation set).We conducted a deep-transfer learning network on high-resolution(HR)panoramic radiographs to improve the longitudinal resolution of the images and obtained the SR images.Subsequently,we constructed models named Model-HR and Model-SR using high-dimensional quantitative features extracted through the Least Absolute Shrinkage and Selection Operator method.The models’performances were evaluated using the receiver operating characteristic curve(ROC).To assess the reliability of the model,we compared the results from the test set with those of three dentists.Results:Model-SR outperformed Model-HR(area under the curve(AUC):0.779,sensitivity:85.5%,specificity:60.9%,and accuracy:79.8%vs.AUC:0.753,sensitivity:73.7%,specificity:73.9%,and accuracy:73.7%)in predicting the difficulty of extracting mandibular third molars.Both Model-HR(AUC=0.821,95%CI 0.687–0.956)and Model-SR(AUC=0.963,95%CI 0.921–0.999)demonstrated superior performance compared to expert dentists(highest AUC=0.799,95%CI 0.671–0.927).Conclusions:Model-SR yielded superior predictive performance in determining the difficulty of extracting mandibular third molars when compared with Model-HR and expert dentists’visual assessments.展开更多
To satisfy the requirements of real-time and high quality mosaics, a bionic compound eye visual system was designed by simulating the visual mechanism of a fly compound eye. Several CCD cameras were used in this syste...To satisfy the requirements of real-time and high quality mosaics, a bionic compound eye visual system was designed by simulating the visual mechanism of a fly compound eye. Several CCD cameras were used in this system to imitate the small eyes of a compound eye. Based on the optical analysis of this system, a direct panoramic image mosaic algorithm was proposed. Several sub-images were collected by the bionic compound eye visual system, and then the system obtained the overlapping proportions of these sub-images and cut the overlap sections of the neighboring images. Thus, a panoramic image with a large field of view was directly mosaicked, which expanded the field and guaranteed the high resolution. The experimental results show that the time consumed by the direct mosaic algorithm is only 2.2% of that by the traditional image mosaic algorithm while guaranteeing mosaic quality. Furthermore, the proposed method effectively solved the problem of misalignment of the mosaic image and eliminated mosaic cracks as a result of the illumination factor and other factors. This method has better real-time properties compared to other methods.展开更多
Abstract： Based on digital signal processor（DSP） and field programmable gate array（FPGA） techniques, the architecture of super large view field（SLVF） panoramic night vision image processing hardware platform wa...Abstract： Based on digital signal processor（DSP） and field programmable gate array（FPGA） techniques, the architecture of super large view field（SLVF） panoramic night vision image processing hardware platform was established. The panoramic unwrapping and correcting algorithm, up to a full 360°, based on coordinate rotation digital computer （CORDIC） and night vision image enhancement algorithm, based on histogram equalization theory and edge detection theory, was presented in this paper, with the purpose of processing night vision dynamic panoramic annular image. The annular image can be unwrapped and corrected to conventional rectangular panorama by the panoramic image processing algorithm, which uses the pipelined CORDIC configuration to realize a trigonometric function generator with high speed and high precision. Histogram equalization algorithm can perfectly enhance the contrast of the night vision image. Edge detection algorithm can be propitious to find and detect small dim dynamic targets in night vision circumstances. After abundant experiment, the al- gorithm for panoramic image processing and night vision image enhancement is successfully implemented in FPGA and DSP. The panoramic night vision image system is a compact device, with no external rotating parts. And the system can reliably and dynamically detect 360＊ SLVF panoramic night vision image.展开更多
Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of ...Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of an embedded ARM system and one array of 16 micro-image sensors. The system achieves the synchronization of captured photos in 10 ms,as well as 10 f /s video capture. The software architecture includes the TCP /IP protocol,video capture procedures in"Poll/Read"or"video streaming"modes,thread pool monitoring in multi-threading mutex,synchronization control with the"event""mutex signal"and"critical region"functions,and a synthetic image algorithm characterized by its portability,modularity,and remote transmission. The panoramic imaging system is expected to be a vision sensor for mobile robotics.展开更多
Introduction Primary liver cancer, the second most common cause of cancer related death worldwide, presents ethnic, etiological, sex, and geographical diversity2 （Figure 1A）. At the histological level, liver cancer ...Introduction Primary liver cancer, the second most common cause of cancer related death worldwide, presents ethnic, etiological, sex, and geographical diversity2 （Figure 1A）. At the histological level, liver cancer includes two major types： hepatocellular carcinoma （HCC, about 80%） and cholangiocarcinoma （CCA, about 15%）. Many etiological factors contribute to HCC development, such as hepatitis B virus （HBV）, hepatitis C virus （HCV）, aflatoxin B1 （AFB1）, alcohol, and metabolic diseases3. By contrast, the major risk factors for CCA are liver flukes （Opisthorchis viverrini and Clonorchis sinensis） and primary sclerosing cholangitis4,展开更多
Inpainting has been continuously studied in the field of computer vision.As artificial intelligence technology developed,deep learning technology was introduced in inpainting research,helping to improve performance.Cu...Inpainting has been continuously studied in the field of computer vision.As artificial intelligence technology developed,deep learning technology was introduced in inpainting research,helping to improve performance.Currently,the input target of an inpainting algorithm using deep learning has been studied from a single image to a video.However,deep learning-based inpainting technology for panoramic images has not been actively studied.We propose a 360-degree panoramic image inpainting method using generative adversarial networks(GANs).The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format,which has relatively little distortion and uses it as a training network.Since the cube map format is used,the correlation of the six sides of the cube map should be considered.Therefore,all faces of the cube map are used as input for the whole discriminative network,and each face of the cube map is used as input for the slice discriminative network to determine the authenticity of the generated image.The proposed network performed qualitatively better than existing single-image inpainting algorithms and baseline algorithms.展开更多
In the visual positioning of Unmanned Ground Vehicle(UGV),the visual odometer based on direct sparse method(DSO) has the advantages of small amount of calculation,high real-time performance and high robustness,so it i...In the visual positioning of Unmanned Ground Vehicle(UGV),the visual odometer based on direct sparse method(DSO) has the advantages of small amount of calculation,high real-time performance and high robustness,so it is more widely used than the visual odometer based on feature point method.Ordinary vision sensors have a narrower viewing angle than panoramic vision sensors,and there are fewer road signs in a single frame of image,resulting in poor road sign tracking and positioning capabilities,and severely restricting the development of visual odometry.Based on these considerations,this paper proposes a binocular stereo panoramic vision positioning algorithm based on extended DSO,which can solve these problems well.The experimental results show that the binocular stereo panoramic vision positioning algorithm based on the extended DSO can directly obtain the panoramic depth image around the UGV,which greatly improves the accuracy and robustness of the visual positioning compared with other ordinary visual odometers.It will have widely application prospects in the UGV field in the future.展开更多
BACKGROUND The diagnosis of coronoid process hyperplasia(CPH)is usually based on symptoms and radiological imaging.Because of its similar symptoms,it can be confused with temporomandibular joint diseases.Therefore,an ...BACKGROUND The diagnosis of coronoid process hyperplasia(CPH)is usually based on symptoms and radiological imaging.Because of its similar symptoms,it can be confused with temporomandibular joint diseases.Therefore,an objective and reproducible way of diagnosis should be determined.AIM To investigate CPH using Levandoski analysis on panoramic radiographs to determine its prevalence.METHODS A total of 300 panoramic radiograph images(600 coronoid processes)were examined.Having measured the Condyle-Gonion(Cd-Go)and Coronoid-Gonion(Cor-Go)distances,the Cor-Go:Cd-Go ratio was calculated for the left and right sides of each image.RESULTS There was a statistically significant difference in Cd-Go and Cor-Go distances between male and female participants(P<0.001).There was no statistically significant relationship between Cor-Go:Cd-Go ratios and gender(P>0.05).CONCLUSION Cd-Go and Cor-Go distances were statistically significantly increased in males on both the left and right sides.The ratio of Cor-Go:Cd-Go was preserved in both genders.The prevalence of CPH was found to be 0.3%.展开更多
An effective algorithm of electronic image stabilization （EIS） of catadioptric panoramic imaging system for track robots is presented. The key techniques of this algorithm are as follows：① A model of electronic im...An effective algorithm of electronic image stabilization （EIS） of catadioptric panoramic imaging system for track robots is presented. The key techniques of this algorithm are as follows：① A model of electronic image stabilization is built by analyzing the imaging theory and the principle of EIS, and the image shift function of unwrapped panoramic image is deduced;② The relationship equation between motion estimation parameters of annular panoramic image and motion estimation parameters of unwrapped panoramic image is developed according to the constrained aspect ratio of real objects, motion parameters of annular panoramic image are firstly estimated, and then motion parameters among the image shift function are carried out according to the relationship equation;③ An excessive stabilization threshold is presented to prevent the phenomena of excessive stabilization, and the Kalman filtering is adopted to smooth the image sequences. Numerical experimental results show that this algorithm can effectively smooth out the unwanted motion and follow the intentional camera movement under certain resolutions.展开更多
The computer evaluation of weld X-ray film is an attractive technique for weld seam NDT （ nondestructive testing）. To achieve this target, digitalization of film is the first step and automatic defect identification...The computer evaluation of weld X-ray film is an attractive technique for weld seam NDT （ nondestructive testing）. To achieve this target, digitalization of film is the first step and automatic defect identification is another key technique. In this paper, a weld X-ray film digitalizing system has been established with linear array CCD and highlight LED light source. Its space resolution can reach 0. 04 mm/pixel and scanning speed can reach 100 mm/s for an industrial film. The transfer function curves of the system have been measured and the results indicate that its image gray resolution can reach 88 G/D at 4. 5D, and its dynamic range can be wider than 2. OD. In order to facilitate the evaluation of large welded structure, a panoramic evaluation algorithm is developed also. The algorithm includes image matching, image fusion and panoramic evaluation of the long linked film image.展开更多
文摘In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or overlooked. While deep learning techniques have been employed to segment teeth in panoramic X-ray images, accurate segmentation of individual teeth remains an underexplored area. In this study, we propose an end-to-end deep learning method that effectively addresses this challenge by employing an improved combinatorial loss function to separate the boundaries of adjacent teeth, enabling precise segmentation of individual teeth in panoramic X-ray images. We validate the feasibility of our approach using a challenging dataset. By training our segmentation network on 115 panoramic X-ray images, we achieve an intersection over union (IoU) of 86.56% for tooth segmentation and an accuracy of 65.52% in tooth counting on 87 test set images. Experimental results demonstrate the significant improvement of our proposed method in single tooth segmentation compared to existing methods.
基金the National Natural Science Foundation of China(61803206)the Key R&D Program of Jiangsu Province(BE2022053-2)the Nanjing Forestry University Youth Science and Technology Innovation Fund(CX2018004)for partly funding this project.
文摘In response to the challenges posed by insufficient real-time performance and suboptimal matching accuracy of traditional feature matching algorithms within automotive panoramic surround view systems,this paper has proposed a high-performance dimension reduction parallel matching algorithm that integrates Principal Component Analysis(PCA)and Dual-Heap Filtering(DHF).The algorithm employs PCA to map the feature points into the lower-dimensional space and employs the square of Euclidean distance for feature matching,which significantly reduces computational complexity.To ensure the accuracy of feature matching,the algorithm utilizes Dual-Heap Filtering to filter and refine matched point pairs.To further enhance matching speed and make optimal use of computational resources,the algorithm introduces a multi-core parallel matching strategy,greatly elevating the efficiency of feature matching.Compared to Scale-Invariant Feature Transform(SIFT)and Speeded Up Robust Features(SURF),the proposed algorithm reduces matching time by 77%to 80%and concurrently enhances matching accuracy by 5%to 15%.Experimental results demonstrate that the proposed algorithmexhibits outstanding real-time matching performance and accuracy,effectivelymeeting the feature-matching requirements of automotive panoramic surround view systems.
基金founded by National Key R&D Program of China (No.2021YFB2601200)National Natural Science Foundation of China (No.42171416)Teacher Support Program for Pyramid Talent Training Project of Beijing University of Civil Engineering and Architecture (No.JDJQ20200307).
文摘In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strategy for extracting road cracks.This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images.The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously.A convolutional neural network is utilized to extract cracks from the panoramic sequence image.The extracted sequence image is then aligned with the laser point cloud,enabling the assignment of RGB information to the vehicle-mounted three dimensional(3D)point cloud and location information to the two dimensional(2D)panoramic image.Additionally,a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud.The three-dimensional data pertaining to the cracks can be acquired.The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks.The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks.This approach exhibits superior accuracy when compared to conventional methods.Moreover,it facilitates rapid and accurate identification and localization of road cracks,thereby playing a crucial role in ensuring road maintenance and traffic safety.Consequently,this technique finds extensive application in the domains of intelligent transportation and urbanization development.The technology exhibits significant promise for use in the domains of intelligent transportation and city development.
基金This research was funded by the Science and Technology Innovation Project for Laoshan Laboratory(No.LSKJ202204303)the National Natural Science Foundation of China(No.42030406)+1 种基金the Fundamental Research Funds for the Central Universities(No.202261006)the ESANRSCC Scientific Cooperation Project on Earth Observation Science and Applications:Dragon 5(No.58393).
文摘In this paper,we propose a novel approach to visualizing global geographical information:a panoramic sphere in an immersive environment.The whole geographical surface can be observed through the rotating of heads as the viewpoint of the panoramic sphere is inside the sphere.We compared three approaches to visualizing the earth for rendering the geographical information in a virtual reality environment.On the tasks of terrestrial and marine geographical information,we compare the visualization effects on a)a globe,b)a flat map and c)a panoramic sphere.Terrestrial geographical information tasks include the area comparison and direction determination.Marine geographical information tasks contain the visualization of sea surface temperature and sea surface currents.For terrestrial geographical information tasks,the experimental results show that the panoramic sphere outperforms the globe and the flat map,with a higher average accuracy and a shorter time.On marine geographical information task,the panoramic sphere visualization is also superior to the flat map and the globe in an immersive environment for the sea surface temperature data and the sea surface current fields.In all three visualization experiments,the panoramic sphere is most preferred by the participants,particularly for global,transcontinental and transoceanic needs.
基金supported by the National Natural Science Foundation of China(U1904145)the Joint Funds for the Innovation of Science and Technology of Fujian province(2019Y9128).
文摘Background:This study aims to predict the extraction difficulty of mandibular third molars based on panoramic images using transfer learning while employing super-resolution(SR)technology to enhance the feasibility and validity of the prediction.Methods:We reviewed a total of 608 preoperative mandibular third molar panoramic radiographs from two medical facilities:the First Affiliated Hospital of Zhengzhou University(n=509;456 in the training set and 53 in the test set)and the Henan Provincial Dental Hospital(n=99 in the validation set).We conducted a deep-transfer learning network on high-resolution(HR)panoramic radiographs to improve the longitudinal resolution of the images and obtained the SR images.Subsequently,we constructed models named Model-HR and Model-SR using high-dimensional quantitative features extracted through the Least Absolute Shrinkage and Selection Operator method.The models’performances were evaluated using the receiver operating characteristic curve(ROC).To assess the reliability of the model,we compared the results from the test set with those of three dentists.Results:Model-SR outperformed Model-HR(area under the curve(AUC):0.779,sensitivity:85.5%,specificity:60.9%,and accuracy:79.8%vs.AUC:0.753,sensitivity:73.7%,specificity:73.9%,and accuracy:73.7%)in predicting the difficulty of extracting mandibular third molars.Both Model-HR(AUC=0.821,95%CI 0.687–0.956)and Model-SR(AUC=0.963,95%CI 0.921–0.999)demonstrated superior performance compared to expert dentists(highest AUC=0.799,95%CI 0.671–0.927).Conclusions:Model-SR yielded superior predictive performance in determining the difficulty of extracting mandibular third molars when compared with Model-HR and expert dentists’visual assessments.
文摘To satisfy the requirements of real-time and high quality mosaics, a bionic compound eye visual system was designed by simulating the visual mechanism of a fly compound eye. Several CCD cameras were used in this system to imitate the small eyes of a compound eye. Based on the optical analysis of this system, a direct panoramic image mosaic algorithm was proposed. Several sub-images were collected by the bionic compound eye visual system, and then the system obtained the overlapping proportions of these sub-images and cut the overlap sections of the neighboring images. Thus, a panoramic image with a large field of view was directly mosaicked, which expanded the field and guaranteed the high resolution. The experimental results show that the time consumed by the direct mosaic algorithm is only 2.2% of that by the traditional image mosaic algorithm while guaranteeing mosaic quality. Furthermore, the proposed method effectively solved the problem of misalignment of the mosaic image and eliminated mosaic cracks as a result of the illumination factor and other factors. This method has better real-time properties compared to other methods.
文摘Abstract： Based on digital signal processor（DSP） and field programmable gate array（FPGA） techniques, the architecture of super large view field（SLVF） panoramic night vision image processing hardware platform was established. The panoramic unwrapping and correcting algorithm, up to a full 360°, based on coordinate rotation digital computer （CORDIC） and night vision image enhancement algorithm, based on histogram equalization theory and edge detection theory, was presented in this paper, with the purpose of processing night vision dynamic panoramic annular image. The annular image can be unwrapped and corrected to conventional rectangular panorama by the panoramic image processing algorithm, which uses the pipelined CORDIC configuration to realize a trigonometric function generator with high speed and high precision. Histogram equalization algorithm can perfectly enhance the contrast of the night vision image. Edge detection algorithm can be propitious to find and detect small dim dynamic targets in night vision circumstances. After abundant experiment, the al- gorithm for panoramic image processing and night vision image enhancement is successfully implemented in FPGA and DSP. The panoramic night vision image system is a compact device, with no external rotating parts. And the system can reliably and dynamically detect 360＊ SLVF panoramic night vision image.
基金Supported by the National Natural Science Foundation of China(61233014)the China Postdoctoral Science Foundation(2012M5210711,20123218110031)the National Natural Science Major International Cooperation Projects(61161120323)
文摘Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of an embedded ARM system and one array of 16 micro-image sensors. The system achieves the synchronization of captured photos in 10 ms,as well as 10 f /s video capture. The software architecture includes the TCP /IP protocol,video capture procedures in"Poll/Read"or"video streaming"modes,thread pool monitoring in multi-threading mutex,synchronization control with the"event""mutex signal"and"critical region"functions,and a synthetic image algorithm characterized by its portability,modularity,and remote transmission. The panoramic imaging system is expected to be a vision sensor for mobile robotics.
基金supported,in part,by the Precision Medical Research Program from Ministry of Science and Technology of China(Grant No.YL 2017YFC0908400)National Science and Technology Major Project for Infectious Disease and Funding(Grant No.YL 17-163-12-ZT-005-095-01)+2 种基金Science and Technology Commission in Ministry of National Defense of China(Grant No.YL 17-163-12-ZT-005-095-01)Xinwei Wang was supported by the intramural research program of the Center for Cancer Research,National Cancer Institute of the United StatesJunfang Ji was supported by the Thousand Young Talents Plan of China,National Natural Science Foundation of China(Grant No.81672905)
文摘Introduction Primary liver cancer, the second most common cause of cancer related death worldwide, presents ethnic, etiological, sex, and geographical diversity2 （Figure 1A）. At the histological level, liver cancer includes two major types： hepatocellular carcinoma （HCC, about 80%） and cholangiocarcinoma （CCA, about 15%）. Many etiological factors contribute to HCC development, such as hepatitis B virus （HBV）, hepatitis C virus （HCV）, aflatoxin B1 （AFB1）, alcohol, and metabolic diseases3. By contrast, the major risk factors for CCA are liver flukes （Opisthorchis viverrini and Clonorchis sinensis） and primary sclerosing cholangitis4,
基金Korea Electric Power Corporation(Grant No.R18XA02).
文摘Inpainting has been continuously studied in the field of computer vision.As artificial intelligence technology developed,deep learning technology was introduced in inpainting research,helping to improve performance.Currently,the input target of an inpainting algorithm using deep learning has been studied from a single image to a video.However,deep learning-based inpainting technology for panoramic images has not been actively studied.We propose a 360-degree panoramic image inpainting method using generative adversarial networks(GANs).The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format,which has relatively little distortion and uses it as a training network.Since the cube map format is used,the correlation of the six sides of the cube map should be considered.Therefore,all faces of the cube map are used as input for the whole discriminative network,and each face of the cube map is used as input for the slice discriminative network to determine the authenticity of the generated image.The proposed network performed qualitatively better than existing single-image inpainting algorithms and baseline algorithms.
基金the Project of National Natural Science Foundation of China(Grant No.61773059)the Project of National Defense Technology Foundation Program of China(Grant No.20230028) to provide fund for conducting experiments。
文摘In the visual positioning of Unmanned Ground Vehicle(UGV),the visual odometer based on direct sparse method(DSO) has the advantages of small amount of calculation,high real-time performance and high robustness,so it is more widely used than the visual odometer based on feature point method.Ordinary vision sensors have a narrower viewing angle than panoramic vision sensors,and there are fewer road signs in a single frame of image,resulting in poor road sign tracking and positioning capabilities,and severely restricting the development of visual odometry.Based on these considerations,this paper proposes a binocular stereo panoramic vision positioning algorithm based on extended DSO,which can solve these problems well.The experimental results show that the binocular stereo panoramic vision positioning algorithm based on the extended DSO can directly obtain the panoramic depth image around the UGV,which greatly improves the accuracy and robustness of the visual positioning compared with other ordinary visual odometers.It will have widely application prospects in the UGV field in the future.
文摘BACKGROUND The diagnosis of coronoid process hyperplasia(CPH)is usually based on symptoms and radiological imaging.Because of its similar symptoms,it can be confused with temporomandibular joint diseases.Therefore,an objective and reproducible way of diagnosis should be determined.AIM To investigate CPH using Levandoski analysis on panoramic radiographs to determine its prevalence.METHODS A total of 300 panoramic radiograph images(600 coronoid processes)were examined.Having measured the Condyle-Gonion(Cd-Go)and Coronoid-Gonion(Cor-Go)distances,the Cor-Go:Cd-Go ratio was calculated for the left and right sides of each image.RESULTS There was a statistically significant difference in Cd-Go and Cor-Go distances between male and female participants(P<0.001).There was no statistically significant relationship between Cor-Go:Cd-Go ratios and gender(P>0.05).CONCLUSION Cd-Go and Cor-Go distances were statistically significantly increased in males on both the left and right sides.The ratio of Cor-Go:Cd-Go was preserved in both genders.The prevalence of CPH was found to be 0.3%.
基金Supported by State Key Laboratory of Explosion Science and Technology Foundation(ZDKT08-05)
文摘An effective algorithm of electronic image stabilization （EIS） of catadioptric panoramic imaging system for track robots is presented. The key techniques of this algorithm are as follows：① A model of electronic image stabilization is built by analyzing the imaging theory and the principle of EIS, and the image shift function of unwrapped panoramic image is deduced;② The relationship equation between motion estimation parameters of annular panoramic image and motion estimation parameters of unwrapped panoramic image is developed according to the constrained aspect ratio of real objects, motion parameters of annular panoramic image are firstly estimated, and then motion parameters among the image shift function are carried out according to the relationship equation;③ An excessive stabilization threshold is presented to prevent the phenomena of excessive stabilization, and the Kalman filtering is adopted to smooth the image sequences. Numerical experimental results show that this algorithm can effectively smooth out the unwanted motion and follow the intentional camera movement under certain resolutions.
文摘The computer evaluation of weld X-ray film is an attractive technique for weld seam NDT （ nondestructive testing）. To achieve this target, digitalization of film is the first step and automatic defect identification is another key technique. In this paper, a weld X-ray film digitalizing system has been established with linear array CCD and highlight LED light source. Its space resolution can reach 0. 04 mm/pixel and scanning speed can reach 100 mm/s for an industrial film. The transfer function curves of the system have been measured and the results indicate that its image gray resolution can reach 88 G/D at 4. 5D, and its dynamic range can be wider than 2. OD. In order to facilitate the evaluation of large welded structure, a panoramic evaluation algorithm is developed also. The algorithm includes image matching, image fusion and panoramic evaluation of the long linked film image.
