- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Interactive Image Segmentation on Multiscale Appearances
摘要： Interactive segmentation algorithms based on graph cuts can extract the foreground successfully from a simple scene. However, they are ineffective for complex-scene images. To improve the segmentation performance, we propose an interactive segmentation algorithm, which combines the segmentation and the multiscale smoothing into a unified model. This model consists of the segmentation and the smoothing. The segmentation relies on the multiscale appearances, which depend on the smoothing. In the smoothing part, the total variation is used to preserve the geometric shape of the foreground and captures different scale edges and appearances for segmentation. Combining the multiscale edges and appearances, we propose a novel Gibbs energy functional for segmentation. The exact global minima of the energy can be found by jointing the image smoothing and the optimization of segmentation. In this algorithm, the smoothing motivates that the foreground could be detected easily from a proper scale. Experimental results on the BSD300 data set and Weizmann horse's database indicate that, compared with the existing interactive segmentation algorithms, the proposed algorithm provides competitive performance in terms of segmentation accuracy.
关键词： multiscale appearance,multiscale edge,Interactive image segmentation,graph cut
更新于2025-09-23 15:23:52
-
Photocatalytic overall water splitting on isolated semiconductor photocatalyst sites in an ordered mesoporous silica matrix: A multiscale strategy
摘要： Photocatalytic overall water splitting (OWS) in a stoichiometric ratio has attracted increasing attention for the realization of a sustainable, environmentally friendly future. However, this reaction exhibits sluggish kinetics due to efficiency limitations of the involved steps, including photon absorption, electron transfer, and the reactions that occur at triple-phase boundary regions. Herein, we report a general multiscale strategy to address this challenge by designing a model composite catalyst with a high loading density of isolated Bi0.5Y0.5VO4 nanocrystals, as building blocks, dispersed in a hexagonally ordered mesoporous silica matrix. In contrast to the well-recognized heterojunction formed between different semiconductors, we show that confined growth favours the formation of isolated quaternary solid-solution photocatalysts (Bi0.5Y0.5VO4), which can further interface with the insulating silica to overcome temperature limitations and exhibit enhanced photon absorption and electrochemical and mass transfer properties due to the transparent periodic porous structure of silica and the as-formed small nanocrystals with high crystallinity and a passivated surface. When the semiconductor photocatalyst is incorporated with the inert silica insulator, this nanoarchitecture does not inhibit the OWS activity but actually delivers a 10-fold higher OWS activity than bulk Bi0.5Y0.5VO4 prepared by the conventional solid-state method.
关键词： Multiscale strategy,Photocatalysis,Isolated solid-solution nanocrystal,Overall water splitting,Mesoporous composite
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) - Qingdao, China (2018.9.14-2018.9.16)] 2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) - A Real-time Detection Algorithm for Unmanned Aerial Vehicle Target in Infrared Search System
摘要： Aiming at the difficulty of infrared target detection of 'low and slow small' unmanned aerial vehicles (UAV) in complex low-altitude background, this paper proposes a new target detection algorithm based on multiscale fusion filtering. Combined with spatial multiscale decomposition filtering and temporal multiscale difference processing, the algorithm can effectively overcome many difficulties such as complex low-altitude background interference, unknown target scale, unknown angular velocity and low target signal-to-noise ratio (SNR). The test result shows that the algorithm can effectively detect the UAV targets with different distances in complex low-altitude background, and the false alarm rate is low. The algorithm is realized in TI 6657 DSP and realizes 100Hz real-time processing of mid-wave infrared images with 640*512 resolution, which has been effectively applied to the large-field circumferential scanning infrared search system developed by ATR Lab.
关键词： real-time algorithm,multiscale fusion filtering,UAV target detection,low-altitude background,low and slow small targets
更新于2025-09-23 15:23:52
-
A CNN With Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification
摘要： Recently, researchers have shown the powerful ability of deep methods with multilayers to extract high-level features and to obtain better performance for hyperspectral image classification. However, a common problem of traditional deep models is that the learned deep models might be suboptimal because of the limited number of training samples, especially for the image with large intraclass variance and low interclass variance. In this paper, novel convolutional neural networks (CNNs) with multiscale convolution (MS-CNNs) are proposed to address this problem by extracting deep multiscale features from the hyperspectral image. Moreover, deep metrics usually accompany with MS-CNNs to improve the representational ability for the hyperspectral image. However, the usual metric learning would make the metric parameters in the learned model tend to behave similarly. This similarity leads to obvious model’s redundancy and, thus, shows negative effects on the description ability of the deep metrics. Traditionally, determinantal point process (DPP) priors, which encourage the learned factors to repulse from one another, can be imposed over these factors to diversify them. Taking advantage of both the MS-CNNs and DPP-based diversity-promoting deep metrics, this paper develops a CNN with multiscale convolution and diversified metric to obtain discriminative features for hyperspectral image classification. Experiments are conducted over four real-world hyperspectral image data sets to show the effectiveness and applicability of the proposed method. Experimental results show that our method is better than original deep models and can produce comparable or even better classification performance in different hyperspectral image data sets with respect to spectral and spectral–spatial features.
关键词： deep metric learning,determinantal point process (DPP),image classification,multiscale features,Convolutional neural network (CNN),hyperspectral image
更新于2025-09-23 15:23:52
-
Quaternion-Based Multiscale Analysis for Feature Extraction of Hyperspectral Images
摘要： This paper proposes a new method called multiscale quaternion Weber local descriptor histogram (MQWLDH) for feature extraction of hyperspectral images (HSIs), which is used to model spatial information based on the corresponding spectral features. The proposed method first transforms spectral data into an orthogonal space using principal component analysis, and extracts the first three principal components (PCs) based on the maximum variance theory. Then construct the MQWLDH to extract spatial features based on those first three PCs. The proposed method uses the algebraic structure of quaternions to unify the process of processing the first three PCs, which reduces the computational cost and the dimensionality of the extracted spatial feature vector. Moreover, the constructed quaternion Weber local descriptor effectively characterizes the variations of each pixel neighborhood and detects the edges of HSIs. To capture more intrinsic spatial information contained in homogeneous regions of different sizes and shapes, multiscale feature histograms are constructed. Finally, a feature fusion framework is proposed to fuse spectral and spatial features, so that spectral information can be fully utilized. The experimental results on three HSI data sets demonstrate that the proposed method provides effective features to different classifiers and achieves excellent classification performance.
关键词： multiscale feature histograms.,principal component analysis (PCA),Feature extraction,quaternion Weber local descriptor (QWLD)
更新于2025-09-23 15:22:29
-
Automated Visual Inspection of Glass Bottle Bottom With Saliency Detection and Template Matching
摘要： Glass bottles are widely used as containers in the food and beverage industry, especially for beer and carbonated beverages. As the key part of a glass bottle, the bottle bottom and its quality are closely related to product safety. Therefore, the bottle bottom must be inspected before the bottle is used for packaging. In this paper, an apparatus based on machine vision is designed for real-time bottle bottom inspection, and a framework for the defect detection mainly using saliency detection and template matching is presented. Following a brief description of the apparatus, our emphasis is on the image analysis. First, we locate the bottom by combining Hough circle detection with the size prior, and we divide the region of interest into three measurement regions: central panel region, annular panel region, and annular texture region. Then, a saliency detection method is proposed for finding defective areas inside the central panel region. A multiscale filtering method is adopted to search for defects in the annular panel region. For the annular texture region, we combine template matching with multiscale filtering to detect defects. Finally, the defect detection results of the three measurement regions are fused to distinguish the quality of the tested bottle bottom. The proposed defect detection framework is evaluated on bottle bottom images acquired by our designed apparatus. The experimental results demonstrate that the proposed methods achieve the best performance in comparison with many conventional methods.
关键词： multiscale filtering,machine vision,template matching,saliency detection,Defect detection
更新于2025-09-23 15:22:29
-
Empirical system of image enhancement for digital microscopic pneumonia bacteria images
摘要： In this paper the image processing method is used to enhance the pneumonia bacteria images. This paper recognized the bacteria images based on two domains. The enhancement techniques used for bacteria image enhancement were median filter, wiener filter, single scale retinex and multiscale retinex. Image enhancement has a very important role in digital image processing. The median and wiener filters were used for grayscale image enhancement. Then single scale retinex and multiscale retinex were used for color image enhancement. Based on performance metrics identified median filter is suitable for bacteria images in grayscale image enhancement and multiscale retinex is suitable for bacteria color image enhancement (Tab. 2, Fig. 8, Ref. 21). Text in PDF www.elis.sk.
关键词： image processing,median filter,multiscale retinex,image enhancement,wiener filter,single scale retinex,Pneumonia bacteria
更新于2025-09-23 15:22:29
-
Spectral–spatial classification of hyperspectral images by algebraic multigrid based multiscale information fusion
摘要： In this work, we present a novel spectral-spatial classification framework of hyperspectral images (HSIs) by integrating the techniques of algebraic multigrid (AMG), hierarchical segmentation (HSEG) and Markov random field (MRF). The proposed framework manifests two main contributions. First, an effective HSI segmentation method is developed by combining the AMG-based marker selection approach and the conventional HSEG algorithm to construct a set of unsupervised segmentation maps in multiple scales. To improve the computational efficiency, the fast Fish Markov selector (FMS) algorithm is exploited for feature selection before image segmentation. Second, an improved MRF energy function is proposed for multiscale information fusion (MIF) by considering both spatial and inter-scale contextual information. Experiments were performed using two airborne HSIs to evaluate the performance of the proposed framework in comparison with several popular classification methods. The experimental results demonstrated that the proposed framework can provide superior performance in terms of both qualitative and quantitative analysis.
关键词： hierarchical segmentation,algebraic multigrid,hyperspectral images,spectral-spatial classification,multiscale information fusion,Markov random field
更新于2025-09-23 15:22:29
-
The effect of grain-size on fracture of polycrystalline silicon carbide: A multiscale analysis using a molecular dynamics-peridynamics framework
摘要： A robust atomistic to mesoscale computational multiscale/multiphysics modeling framework that explicitly takes into account atomic-scale descriptions of grain-boundaries, is implemented to examine the interplay between grain-size and fracture of polycrystalline cubic silicon carbide (3C-SiC). A salient feature of the developed framework is the establishment of scale-parity between the chosen atomistic and the mesoscale methods namely molecular dynamics (MD) and peridynamics (PD) respectively, which enables the ability to model the effect of the underlying microstructure as well as obtain relevant new insights into the role of grain-size on the ensuing mechanical response of 3C-SiC. Material properties such as elastic modulus, and fracture toughness of single crystals and bicrystals of various orientations are obtained from MD simulations, and using appropriate statistical analysis, MD derived properties are interfaced with PD simulations, resulting in mesoscale simulations that accurately predict the role of grain-size on failure strength, fracture energy, elastic modulus, fracture toughness, and tensile toughness of polycrystalline 3C-SiC. In particular, it is seen that the fracture strength follows a Hall-Petch law with respect to grain-size variations, while mode-I fracture toughness increases with increasing grain-size, consistent with available literature on brittle fracture of polycrystalline materials. Equally importantly, the developed MD-PD multiscale/multiphysics framework represents an important step towards developing materials modeling paradigms that can provide a comprehensive and predictive description of the microstructure-property-performance interplay in solid-state materials.
关键词： Peridynamics,Polycrystalline,Multiscale modeling,3C-SiC,Grain boundaries,Molecular dynamics
更新于2025-09-23 15:22:29
-
Multiscale Visual Attention Networks for Object Detection in VHR Remote Sensing Images
摘要： Object detection plays an active role in remote sensing applications. Recently, deep convolutional neural network models have been applied to automatically extract features, generate region proposals, and predict corresponding object class. However, these models face new challenges in VHR remote sensing images due to the orientation and scale variations and the cluttered background. In this letter, we propose an end-to-end multiscale visual attention networks (MS-VANs) method. We use skip-connected encoder–decoder model to extract multiscale features from a full-size image. For feature maps in each scale, we learn a visual attention network, which is followed by a classification branch and a regression branch, so as to highlight the features from object region and suppress the cluttered background. We train the MS-VANs model by a hybrid loss function which is a weighted sum of attention loss, classification loss, and regression loss. Experiments on a combined data set consisting of Dataset for Object Detection in Aerial Images and NWPU VHR-10 show that the proposed method outperforms several state-of-the-art approaches.
关键词： object detection,VHR remote sensing image,visual attention,Multiscale feature
更新于2025-09-23 15:21:21