Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,...Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,and interference from contamination.To address these challenges,this paper proposes the Real-time Cable Defect Detection Network(RC2DNet),which achieves an optimal balance between detection accuracy and computational efficiency.Unlike conventional approaches,RC2DNet introduces a small object feature extraction module that enhances the semantic representation of small targets through feature pyramids,multi-level feature fusion,and an adaptive weighting mechanism.Additionally,a boundary feature enhancement module is designed,incorporating boundary-aware convolution,a novel boundary attention mechanism,and an improved loss function to significantly enhance boundary localization accuracy.Experimental results demonstrate that RC2DNet outperforms state-of-the-art methods in precision,recall,F1-score,mean Intersection over Union(mIoU),and frame rate,enabling real-time and highly accurate cable defect detection in complex backgrounds.展开更多
In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion ...In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion module is studied.Furthermore,a joint network of object detection and feature extraction is studied to construct a real-time multi-object tracking algorithm.For the problem of object association failure caused by UAV movement,image registration is applied to multi-object tracking and a camera motion discrimination model is proposed to improve the speed of the multi-object tracking algorithm.The simulation results show that the algorithm proposed in this study can improve the accuracy of multi-object tracking under the UAV platform,and effectively solve the problem of association failure caused by UAV movement.展开更多
A novel method is proposed to automatically extract foreground objects from Martian surface images.The characteristics of Mars images are distinct,e.g.uneven illumination,low contrast between foreground and background...A novel method is proposed to automatically extract foreground objects from Martian surface images.The characteristics of Mars images are distinct,e.g.uneven illumination,low contrast between foreground and background,much noise in the background,and foreground objects with irregular shapes.In the context of these characteristics,an image is divided into foreground objects and background information.Homomorphism filtering is first applied to rectify brightness.Then,wavelet transformation enhances contrast and denoises the image.Third,edge detection and active contour are combined to extract contours regardless of the shape of the image.Experimental results show that the method can extract foreground objects from Mars images automatically and accurately,and has many potential applications.展开更多
An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for des...An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for describing and recognizing categories, for automatic building extraction and for finding the mutual regions in image matching. The method includes directional filtering and searching for straight edge segments in every direction and scale, taking into account edge gradient signs. Line segments are ordered with respect to their orientation and average gradients in the region in question. These segments are used for the construction of an object descriptor. A hierarchical set of feature descriptors is developed, taking into consideration the proposed straight line segment detector. Comparative performance is evaluated on the noisy model and in real aerial and satellite imagery.展开更多
A novel and effective approach to global motion estimation and moving object extraction is proposed. First, the translational motion model is used because of the fact that complex motion can be decomposed as a sum of ...A novel and effective approach to global motion estimation and moving object extraction is proposed. First, the translational motion model is used because of the fact that complex motion can be decomposed as a sum of translational components. Then in this application, the edge gray horizontal and vertical projections are used as the block matching feature for the motion vectors estimation. The proposed algorithm reduces the motion estimation computations by calculating the onedimensional vectors rather than the two-dimensional ones. Once the global motion is robustly estimated, relatively stationary background can be almost completely eliminated through the inter-frame difference method. To achieve an accurate object extraction result, the higher-order statistics （HOS） algorithm is used to discriminate backgrounds and moving objects. Experimental results validate that the proposed method is an effective way for global motion estimation and object extraction.展开更多
In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly conne...In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly connected and structured, which makes motion connectivity an advanced feature for segmentation. Accordingly, after sharp noise elimination, the cumulated difference image, which exhibits the coherent motion of the moving object, is adaptively thresholded. Then the maximal connected region is labeled, post-processed and output as the final segmenting mask. Hence the initial video object is effectively extracted. Comparative experimental results show that the proposed algorithm extracts the initial video object automatically, promptly and properly, thereby achieving satisfactory subjective and objective performance.展开更多
This paper introduces a novel technique for object detection using genetic algorithms and morphological processing. The method employs a kind of object oriented structure element, which is derived by genetic algorithm...This paper introduces a novel technique for object detection using genetic algorithms and morphological processing. The method employs a kind of object oriented structure element, which is derived by genetic algorithms. The population of morphological filters is iteratively evaluated according to a statistical performance index corresponding to object extraction ability, and evolves into an optimal structuring element using the evolution principles of genetic search. Experimental results of road extraction from high resolution satellite images are presented to illustrate the merit and feasibility of the proposed method.展开更多
This paper proposes an object-tracking algorithm with multiple randomly-generated features. We mainly improve the tracking performance which is sometimes good and sometimes bad in compressive tracking. In compressive ...This paper proposes an object-tracking algorithm with multiple randomly-generated features. We mainly improve the tracking performance which is sometimes good and sometimes bad in compressive tracking. In compressive tracking, the image features are generated by random projection. The resulting image features are affected by the random numbers so that the results of each execution are different. If the obvious features of the target are not captured, the tracker is likely to fail. Therefore the tracking results are inconsistent for each execution. The proposed algorithm uses a number of different image features to track, and chooses the best tracking result by measuring the similarity with the target model. It reduces the chances to determine the target location by the poor image features. In this paper, we use the Bhattacharyya coefficient to choose the best tracking result. The experimental results show that the proposed tracking algorithm can greatly reduce the tracking errors. The best performance improvements in terms of center location error, bounding box overlap ratio and success rate are from 63.62 pixels to 15.45 pixels, from 31.75% to 64.48% and from 38.51% to 82.58%, respectively.展开更多
Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noti...Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.展开更多
This paper presents a novel approach for moving object extraction in the H.264/AVC compressed domain, which based on Ant Colony clustering Algorithm (ACA) and threshold method in macro block layer. Firstly, the Motion...This paper presents a novel approach for moving object extraction in the H.264/AVC compressed domain, which based on Ant Colony clustering Algorithm (ACA) and threshold method in macro block layer. Firstly, the Motion Vector (MV) field and the macro block types are extracted from the H.264/AVC compressed video, and then merge MVs with the same characteristic. Secondly, an improved ACA is used to classify the MV field into different motion homogenous regions. At the same time, use macro block types to determine the location of objects. Finally, using the complementarities of macro block template and MVs clustering template to obtain final objects. Experimental results for several video sequences demonstrate that in the case of ensuring accuracy, the proposed approach can extract moving object faster.展开更多
The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpow...The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.展开更多
Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained ...Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained Convolutional Neural Network (CNN) architectures to extract powerful features from images for object recognition purposes. We have built on the existing concept of extending the learning from pre-trained CNNs to new databases through activations by proposing to consider multiple deep layers. We have exploited the progressive learning that happens at the various intermediate layers of the CNNs to construct Deep Multi-Layer (DM-L) based Feature Extraction vectors to achieve excellent object recognition performance. Two popular pre-trained CNN architecture models i.e. the VGG_16 and VGG_19 have been used in this work to extract the feature sets from 3 deep fully connected multiple layers namely “fc6”, “fc7” and “fc8” from inside the models for object recognition purposes. Using the Principal Component Analysis (PCA) technique, the Dimensionality of the DM-L feature vectors has been reduced to form powerful feature vectors that have been fed to an external Classifier Ensemble for classification instead of the Softmax based classification layers of the two original pre-trained CNN models. The proposed DM-L technique has been applied to the Benchmark Caltech-101 object recognition database. Conventional wisdom may suggest that feature extractions based on the deepest layer i.e. “fc8” compared to “fc6” will result in the best recognition performance but our results have proved it otherwise for the two considered models. Our experiments have revealed that for the two models under consideration, the “fc6” based feature vectors have achieved the best recognition performance. State-of-the-Art recognition performances of 91.17% and 91.35% have been achieved by utilizing the “fc6” based feature vectors for the VGG_16 and VGG_19 models respectively. The recognition performance has been achieved by considering 30 sample images per class whereas the proposed system is capable of achieving improved performance by considering all sample images per class. Our research shows that for feature extraction based on CNNs, multiple layers should be considered and then the best layer can be selected that maximizes the recognition performance.展开更多
The forecast results of temperature based on the intelligent grids of the Central Meteorological Observatory and the meteorological bureau of the autonomous region and the numerical forecast model of the European Cent...The forecast results of temperature based on the intelligent grids of the Central Meteorological Observatory and the meteorological bureau of the autonomous region and the numerical forecast model of the European Center(EC model)from February to December in 2022 were used.Based on the data of the national intelligent grid forecast,the intelligent grid forecast of the regional bureau,EC model,etc.,temperature was predicted.According to the research of the grid point forecast synthesis algorithm with the highest accuracy rate in the recent three days,the temperature grid point correction was conducted in two forms of stations and grids.In order to reduce the deviation caused by the seasonal system temperature difference,a temperature prediction model was established by using the rolling forecast errors of 5,10,15,20,25 and 30 d as the basis data.The verification and evaluation of objective correction results show that the accuracy rate of temperature forecast by the intelligent grid of the regional bureau,the national intelligent grid,and EC model could be increased by 10%,8%,and 12%,respectively.展开更多
A novel multi level image segmentation methodology is been proposed with the aim of extracting the salient object,keeping in view,only a small part of the visual scene undergoes attention and reaches the level of awar...A novel multi level image segmentation methodology is been proposed with the aim of extracting the salient object,keeping in view,only a small part of the visual scene undergoes attention and reaches the level of awareness while rest of details are futile.Taking advantage of multilevel gray scale quantization,image prominent object is separated from background,keeping in view the fact;salient object is having high contrast as compared to the background.The inutile fragments were removed using morphological operations of opening and closing and making the image smoothened with Gaussian filter.The optimum threshold is selected for the binary conversion and final extrication of the salient object from the image.The experimental data indicates that hybrid approach leads to improved segmentation with the apparent assertion of prime object extraction.展开更多
Taking TM images, SPOT photos and DEM images as the basic information, this paper had not only put forward a kind of manual controlled computer-automatic extraction method, but also completed the task of extracting th...Taking TM images, SPOT photos and DEM images as the basic information, this paper had not only put forward a kind of manual controlled computer-automatic extraction method, but also completed the task of extracting the main types of ground objects in the Three Gorges Reservoir area under relatively high accuracy, after finishing such preprocessing tasks as correcting the topographical spectrum and synthesizing the data. Taking the specialized image analysis software-eCognition as the platform, the research achieved the goal of classifying through choosing samples, picking out the best wave bands, and producing the identifying functions. At the same time the extraction process partly dispelled the influence of such phenomena as the same thing with different spectrums, different things with the same spectrum, border transitions, etc. The research did certain exploration in the aspect of technological route and method of using automatic extraction of the remote sensing image to obtain the information of land cover for the regions whose ground objects have complicated spectrums.展开更多
Geospatial objects detection within complex environment is a challenging problem in remote sensing area. In this paper, we derive an extension of the Relevance Vector Machine (RVM) technique to multiple kernel version...Geospatial objects detection within complex environment is a challenging problem in remote sensing area. In this paper, we derive an extension of the Relevance Vector Machine (RVM) technique to multiple kernel version. The proposed method learns an optimal kernel combination and the associated classifier simultaneously. Two feature types are extracted from images, forming basis kernels. Then these basis kernels are weighted combined and resulted the composite kernel exploits interesting points and appearance information of objects simultaneously. Weights and the detection model are finally learnt by a new algorithm. Experimental results show that the proposed method improve detection accuracy to above 88%, yields good interpretation for the selected subset of features and appears sparser than traditional single-kernel RVMs.展开更多
Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, simil...Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and in- variant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li's(or Zernike's) polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regres- sion neural network(GRNN) was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.展开更多
Generalized morphological operator can generate less statistical bias in the output than classical morphological operator. Comprehensive utilization of spectral and spatial information of pixels, an endmember extracti...Generalized morphological operator can generate less statistical bias in the output than classical morphological operator. Comprehensive utilization of spectral and spatial information of pixels, an endmember extraction algorithm based on generalized morphology is proposed. For the limitations of morphological operator in the pixel arrangement rule and replacement criteria, the reference pixel is introduced. In order to avoid the cross substitution phenomenon at the boundary of different object categories in the image, an endmember is extracted by calculating the generalized opening-closing(GOC) operator which uses the modified energy function as a distance measure. The algorithm is verified by using simulated data and real data. Experimental results show that the proposed algorithm can extract endmember automatically without prior knowledge and achieve relatively high extraction accuracy.展开更多
With the explosive growth of surveillance video data,browsing videos quickly and effectively has become an urgent problem.Video key frame extraction has received widespread attention as an effective solution.However,a...With the explosive growth of surveillance video data,browsing videos quickly and effectively has become an urgent problem.Video key frame extraction has received widespread attention as an effective solution.However,accurately capturing the local motion state changes of moving objects in the video is still challenging in key frame extraction.The target center offset can reflect the change of its motion state.This observation proposed a novel key frame extraction method based on moving objects center offset in this paper.The proposed method utilizes the center offset to obtain the global and local motion state information of moving objects,and meanwhile,selects the video frame where the center offset curve changes suddenly as the key frame.Such processing effectively overcomes the inaccuracy of traditional key frame extraction methods.Initially,extracting the center point of each frame.Subsequently,calculating the center point offset of each frame and forming the center offset curve by connecting the center offset of each frame.Finally,extracting candidate key frames and optimizing them to generate final key frames.The experimental results demonstrate that the proposed method outperforms contrast methods to capturing the local motion state changes of moving objects.展开更多
Single step and multi step CARE processes are optimized by computer simulations based on the mathematical model proposed previously. The product of purification factor and recovery yield is used as the objective fun...Single step and multi step CARE processes are optimized by computer simulations based on the mathematical model proposed previously. The product of purification factor and recovery yield is used as the objective function for optimizing a single step process. The objective function for the optimization of a multi step process is considered to obtain an anticipated product purity at a maximum recovery yield and a minimum number of CARE inividuals. Pairs of the operating conditions (eluant and affinity recycle flow rates) exist to give the maximums of above objective functions when membrane rejections to ligates and contaminants are equal in value. The optimum affinity recycle flow rate decreases with the increase of membrane rejections and equilibrium binding fractions of ligates. For a multi step process, when contaminants are rejected less than ligate, only one pair of the optimum eluant and affinity recycle flow rates exists.展开更多
基金supported by the National Natural Science Foundation of China under Grant 62306128the Basic Science Research Project of Jiangsu Provincial Department of Education under Grant 23KJD520003the Leading Innovation Project of Changzhou Science and Technology Bureau under Grant CQ20230072.
文摘Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,and interference from contamination.To address these challenges,this paper proposes the Real-time Cable Defect Detection Network(RC2DNet),which achieves an optimal balance between detection accuracy and computational efficiency.Unlike conventional approaches,RC2DNet introduces a small object feature extraction module that enhances the semantic representation of small targets through feature pyramids,multi-level feature fusion,and an adaptive weighting mechanism.Additionally,a boundary feature enhancement module is designed,incorporating boundary-aware convolution,a novel boundary attention mechanism,and an improved loss function to significantly enhance boundary localization accuracy.Experimental results demonstrate that RC2DNet outperforms state-of-the-art methods in precision,recall,F1-score,mean Intersection over Union(mIoU),and frame rate,enabling real-time and highly accurate cable defect detection in complex backgrounds.
基金the National Natural Science Foundation of China (No.61627810)the National Science and Technology Major Program of China (No.2018YFB1305003)the National Defense Science and Technology Outstanding Youth Science Foundation (No.2017-JCJQ-ZQ-031)。
文摘In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion module is studied.Furthermore,a joint network of object detection and feature extraction is studied to construct a real-time multi-object tracking algorithm.For the problem of object association failure caused by UAV movement,image registration is applied to multi-object tracking and a camera motion discrimination model is proposed to improve the speed of the multi-object tracking algorithm.The simulation results show that the algorithm proposed in this study can improve the accuracy of multi-object tracking under the UAV platform,and effectively solve the problem of association failure caused by UAV movement.
基金Supported by the National 973 Program of China(No.2007CB310804)the National Natural Science Foundation of China(No.61173061).
文摘A novel method is proposed to automatically extract foreground objects from Martian surface images.The characteristics of Mars images are distinct,e.g.uneven illumination,low contrast between foreground and background,much noise in the background,and foreground objects with irregular shapes.In the context of these characteristics,an image is divided into foreground objects and background information.Homomorphism filtering is first applied to rectify brightness.Then,wavelet transformation enhances contrast and denoises the image.Third,edge detection and active contour are combined to extract contours regardless of the shape of the image.Experimental results show that the method can extract foreground objects from Mars images automatically and accurately,and has many potential applications.
文摘An advanced edge-based method of feature detection and extraction is developed for object description in digital images. It is useful for the comparison of different images of the same scene in aerial imagery, for describing and recognizing categories, for automatic building extraction and for finding the mutual regions in image matching. The method includes directional filtering and searching for straight edge segments in every direction and scale, taking into account edge gradient signs. Line segments are ordered with respect to their orientation and average gradients in the region in question. These segments are used for the construction of an object descriptor. A hierarchical set of feature descriptors is developed, taking into consideration the proposed straight line segment detector. Comparative performance is evaluated on the noisy model and in real aerial and satellite imagery.
基金The National Natural Science Foundation of China(No.60574006)
文摘A novel and effective approach to global motion estimation and moving object extraction is proposed. First, the translational motion model is used because of the fact that complex motion can be decomposed as a sum of translational components. Then in this application, the edge gray horizontal and vertical projections are used as the block matching feature for the motion vectors estimation. The proposed algorithm reduces the motion estimation computations by calculating the onedimensional vectors rather than the two-dimensional ones. Once the global motion is robustly estimated, relatively stationary background can be almost completely eliminated through the inter-frame difference method. To achieve an accurate object extraction result, the higher-order statistics （HOS） algorithm is used to discriminate backgrounds and moving objects. Experimental results validate that the proposed method is an effective way for global motion estimation and object extraction.
基金The National Natural Science Foundation of China(No60672094)
文摘In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly connected and structured, which makes motion connectivity an advanced feature for segmentation. Accordingly, after sharp noise elimination, the cumulated difference image, which exhibits the coherent motion of the moving object, is adaptively thresholded. Then the maximal connected region is labeled, post-processed and output as the final segmenting mask. Hence the initial video object is effectively extracted. Comparative experimental results show that the proposed algorithm extracts the initial video object automatically, promptly and properly, thereby achieving satisfactory subjective and objective performance.
文摘This paper introduces a novel technique for object detection using genetic algorithms and morphological processing. The method employs a kind of object oriented structure element, which is derived by genetic algorithms. The population of morphological filters is iteratively evaluated according to a statistical performance index corresponding to object extraction ability, and evolves into an optimal structuring element using the evolution principles of genetic search. Experimental results of road extraction from high resolution satellite images are presented to illustrate the merit and feasibility of the proposed method.
文摘This paper proposes an object-tracking algorithm with multiple randomly-generated features. We mainly improve the tracking performance which is sometimes good and sometimes bad in compressive tracking. In compressive tracking, the image features are generated by random projection. The resulting image features are affected by the random numbers so that the results of each execution are different. If the obvious features of the target are not captured, the tracker is likely to fail. Therefore the tracking results are inconsistent for each execution. The proposed algorithm uses a number of different image features to track, and chooses the best tracking result by measuring the similarity with the target model. It reduces the chances to determine the target location by the poor image features. In this paper, we use the Bhattacharyya coefficient to choose the best tracking result. The experimental results show that the proposed tracking algorithm can greatly reduce the tracking errors. The best performance improvements in terms of center location error, bounding box overlap ratio and success rate are from 63.62 pixels to 15.45 pixels, from 31.75% to 64.48% and from 38.51% to 82.58%, respectively.
基金The paper is supported by the Research Foundation for OutstandingYoung Teachers , China University of Geosciences ( Wuhan) ( No .CUGQNL0616) Research Foundationfor State Key Laboratory of Geo-logical Processes and Mineral Resources ( No . MGMR2002-02)Hubei Provincial Depart ment of Education (B) .
文摘Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.
基金Supported by the Shanghai Normal University Funded Project(No.SK 201127)
文摘This paper presents a novel approach for moving object extraction in the H.264/AVC compressed domain, which based on Ant Colony clustering Algorithm (ACA) and threshold method in macro block layer. Firstly, the Motion Vector (MV) field and the macro block types are extracted from the H.264/AVC compressed video, and then merge MVs with the same characteristic. Secondly, an improved ACA is used to classify the MV field into different motion homogenous regions. At the same time, use macro block types to determine the location of objects. Finally, using the complementarities of macro block template and MVs clustering template to obtain final objects. Experimental results for several video sequences demonstrate that in the case of ensuring accuracy, the proposed approach can extract moving object faster.
基金supported by the National Key Research and Development Program of China(2020YFB1807500)the National Natural Science Foundation of China(62072360,62001357,62172438,61901367)+4 种基金the key research and development plan of Shaanxi province(2021ZDLGY02-09,2023-GHZD-44,2023-ZDLGY-54)the Natural Science Foundation of Guangdong Province of China(2022A1515010988)Key Project on Artificial Intelligence of Xi'an Science and Technology Plan(2022JH-RGZN-0003,2022JH-RGZN-0103,2022JH-CLCJ-0053)Xi'an Science and Technology Plan(20RGZN0005)the Proof-ofconcept fund from Hangzhou Research Institute of Xidian University(GNYZ2023QC0201).
文摘The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.
文摘Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained Convolutional Neural Network (CNN) architectures to extract powerful features from images for object recognition purposes. We have built on the existing concept of extending the learning from pre-trained CNNs to new databases through activations by proposing to consider multiple deep layers. We have exploited the progressive learning that happens at the various intermediate layers of the CNNs to construct Deep Multi-Layer (DM-L) based Feature Extraction vectors to achieve excellent object recognition performance. Two popular pre-trained CNN architecture models i.e. the VGG_16 and VGG_19 have been used in this work to extract the feature sets from 3 deep fully connected multiple layers namely “fc6”, “fc7” and “fc8” from inside the models for object recognition purposes. Using the Principal Component Analysis (PCA) technique, the Dimensionality of the DM-L feature vectors has been reduced to form powerful feature vectors that have been fed to an external Classifier Ensemble for classification instead of the Softmax based classification layers of the two original pre-trained CNN models. The proposed DM-L technique has been applied to the Benchmark Caltech-101 object recognition database. Conventional wisdom may suggest that feature extractions based on the deepest layer i.e. “fc8” compared to “fc6” will result in the best recognition performance but our results have proved it otherwise for the two considered models. Our experiments have revealed that for the two models under consideration, the “fc6” based feature vectors have achieved the best recognition performance. State-of-the-Art recognition performances of 91.17% and 91.35% have been achieved by utilizing the “fc6” based feature vectors for the VGG_16 and VGG_19 models respectively. The recognition performance has been achieved by considering 30 sample images per class whereas the proposed system is capable of achieving improved performance by considering all sample images per class. Our research shows that for feature extraction based on CNNs, multiple layers should be considered and then the best layer can be selected that maximizes the recognition performance.
文摘The forecast results of temperature based on the intelligent grids of the Central Meteorological Observatory and the meteorological bureau of the autonomous region and the numerical forecast model of the European Center(EC model)from February to December in 2022 were used.Based on the data of the national intelligent grid forecast,the intelligent grid forecast of the regional bureau,EC model,etc.,temperature was predicted.According to the research of the grid point forecast synthesis algorithm with the highest accuracy rate in the recent three days,the temperature grid point correction was conducted in two forms of stations and grids.In order to reduce the deviation caused by the seasonal system temperature difference,a temperature prediction model was established by using the rolling forecast errors of 5,10,15,20,25 and 30 d as the basis data.The verification and evaluation of objective correction results show that the accuracy rate of temperature forecast by the intelligent grid of the regional bureau,the national intelligent grid,and EC model could be increased by 10%,8%,and 12%,respectively.
文摘A novel multi level image segmentation methodology is been proposed with the aim of extracting the salient object,keeping in view,only a small part of the visual scene undergoes attention and reaches the level of awareness while rest of details are futile.Taking advantage of multilevel gray scale quantization,image prominent object is separated from background,keeping in view the fact;salient object is having high contrast as compared to the background.The inutile fragments were removed using morphological operations of opening and closing and making the image smoothened with Gaussian filter.The optimum threshold is selected for the binary conversion and final extrication of the salient object from the image.The experimental data indicates that hybrid approach leads to improved segmentation with the apparent assertion of prime object extraction.
基金Under the auspices of the Construction Committeeof Three GorgesR eservoirProject(No .SX [2002]00401) andChineseAcademy ofSciences(No .KZCX2-SW-319-01 )
文摘Taking TM images, SPOT photos and DEM images as the basic information, this paper had not only put forward a kind of manual controlled computer-automatic extraction method, but also completed the task of extracting the main types of ground objects in the Three Gorges Reservoir area under relatively high accuracy, after finishing such preprocessing tasks as correcting the topographical spectrum and synthesizing the data. Taking the specialized image analysis software-eCognition as the platform, the research achieved the goal of classifying through choosing samples, picking out the best wave bands, and producing the identifying functions. At the same time the extraction process partly dispelled the influence of such phenomena as the same thing with different spectrums, different things with the same spectrum, border transitions, etc. The research did certain exploration in the aspect of technological route and method of using automatic extraction of the remote sensing image to obtain the information of land cover for the regions whose ground objects have complicated spectrums.
基金Supported by the National Natural Science Foundation of China (No.41001285)
文摘Geospatial objects detection within complex environment is a challenging problem in remote sensing area. In this paper, we derive an extension of the Relevance Vector Machine (RVM) technique to multiple kernel version. The proposed method learns an optimal kernel combination and the associated classifier simultaneously. Two feature types are extracted from images, forming basis kernels. Then these basis kernels are weighted combined and resulted the composite kernel exploits interesting points and appearance information of objects simultaneously. Weights and the detection model are finally learnt by a new algorithm. Experimental results show that the proposed method improve detection accuracy to above 88%, yields good interpretation for the selected subset of features and appears sparser than traditional single-kernel RVMs.
基金the Fundamental Research Funds for Central Universities(No.HEUCF110111)the National Natural Science Foundation of China(No.51009040)+2 种基金the China Postdoctoral Science Foundation(No.2012M510928)the Heilongjiang Post-doctoral Fund(No.LBH-Z11205)the National High Technology Research and Development Program(863)of China(No.2011AA09A106)
文摘Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and in- variant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li's(or Zernike's) polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regres- sion neural network(GRNN) was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.
基金supported by the National Natural Science Foundation of China(No.61275010)the PhD Programs Foundation of Ministry of Education of China(No.20132304110007)
文摘Generalized morphological operator can generate less statistical bias in the output than classical morphological operator. Comprehensive utilization of spectral and spatial information of pixels, an endmember extraction algorithm based on generalized morphology is proposed. For the limitations of morphological operator in the pixel arrangement rule and replacement criteria, the reference pixel is introduced. In order to avoid the cross substitution phenomenon at the boundary of different object categories in the image, an endmember is extracted by calculating the generalized opening-closing(GOC) operator which uses the modified energy function as a distance measure. The algorithm is verified by using simulated data and real data. Experimental results show that the proposed algorithm can extract endmember automatically without prior knowledge and achieve relatively high extraction accuracy.
基金This work was supported by the National Nature Science Foundation of China(Grant No.61702347,61772225)Natural Science Foundation of Hebei Province(Grant No.F2017210161).
文摘With the explosive growth of surveillance video data,browsing videos quickly and effectively has become an urgent problem.Video key frame extraction has received widespread attention as an effective solution.However,accurately capturing the local motion state changes of moving objects in the video is still challenging in key frame extraction.The target center offset can reflect the change of its motion state.This observation proposed a novel key frame extraction method based on moving objects center offset in this paper.The proposed method utilizes the center offset to obtain the global and local motion state information of moving objects,and meanwhile,selects the video frame where the center offset curve changes suddenly as the key frame.Such processing effectively overcomes the inaccuracy of traditional key frame extraction methods.Initially,extracting the center point of each frame.Subsequently,calculating the center point offset of each frame and forming the center offset curve by connecting the center offset of each frame.Finally,extracting candidate key frames and optimizing them to generate final key frames.The experimental results demonstrate that the proposed method outperforms contrast methods to capturing the local motion state changes of moving objects.
文摘Single step and multi step CARE processes are optimized by computer simulations based on the mathematical model proposed previously. The product of purification factor and recovery yield is used as the objective function for optimizing a single step process. The objective function for the optimization of a multi step process is considered to obtain an anticipated product purity at a maximum recovery yield and a minimum number of CARE inividuals. Pairs of the operating conditions (eluant and affinity recycle flow rates) exist to give the maximums of above objective functions when membrane rejections to ligates and contaminants are equal in value. The optimum affinity recycle flow rate decreases with the increase of membrane rejections and equilibrium binding fractions of ligates. For a multi step process, when contaminants are rejected less than ligate, only one pair of the optimum eluant and affinity recycle flow rates exists.
