• Computers and Concrete
• /
• v.26 no.5
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• Current Optics and Photonics
• /
• v.4 no.6
• /
• pp.530-539
• /
• 2020

Hyperspectral images feature a relatively narrow band and are easily disturbed by noise. Accurate estimation of the types and parameters of noise in hyperspectral images can provide prior knowledge for subsequent image processing. Existing hyperspectral-noise estimation methods often pay more attention to the use of spectral information while ignoring the spatial information of hyperspectral images. To evaluate the noise in hyperspectral images more accurately, we have proposed a spectral-spatial cooperative noise-evaluation method. First, the feature of spatial information was extracted by Gabor-filter and K-means algorithms. Then, texture edges were extracted by the Otsu threshold algorithm, and homogeneous image blocks were automatically separated. After that, signal and noise values for each pixel in homogeneous blocks were split with a multiple-linear-regression model. By experiments with both simulated and real hyperspectral images, the proposed method was demonstrated to be effective and accurate, and the composition of the hyperspectral image was verified.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.512-517
• /
• 2011

In this paper, we propose an Active Shape Model (ASM) and Lucas-Kanade (LK) optical flow-based feature extraction and analysis method for analyzing the emotional features from facial images. Considering the facial emotion feature regions are described by Facial Action Coding System, we construct the feature-related shape models based on the combination of landmarks and extract the LK optical flow vectors at each landmarks based on the centre pixels of motion vector window. The facial emotion features are modelled by the combination of the optical flow vectors and the emotional states of facial image can be estimated by the probabilistic estimation technique, such as Bayesian classifier. Also, we extract the optimal emotional features that are considered the high correlation between feature points and emotional states by using common spatial pattern (CSP) analysis in order to improvise the operational efficiency and accuracy of emotional feature extraction process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.23-34
• /
• 2004

In this paper we propose a feature point tracking algorithm using optical flow under non-prior taming active feature model (NPT-AFM). The proposed algorithm mainly focuses on analysis non-rigid objects[1], and provides real-time, robust tracking by NPT-AFM. NPT-AFM algorithm can be divided into two steps: (i) localization of an object-of-interest and (ii) prediction and correction of the object position by utilizing the inter-frame information. The localization step was realized by using a modified Shi-Tomasi's feature tracking algoriam[2] after motion-based segmentation. In the prediction-correction step, given feature points are continuously tracked by using optical flow method[3] and if a feature point cannot be properly tracked, temporal and spatial prediction schemes can be employed for that point until it becomes uncovered again. Feature points inside an object are estimated instead of its shape boundary, and are updated an element of the training set for AFH Experimental results, show that the proposed NPT-AFM-based algerian can robustly track non-rigid objects in real-time.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.197-206
• /
• 2014

Motor imagery based Brain-computer Interface(BCI), which has recently attracted attention, is the technique for decoding the user's voluntary motor intention using Electroencephalography(EEG). For classifying the motor imagery, event-related desynchronization(ERD), which is the phenomenon of EEG voltage drop at sensorimotor area in ${\mu}$-band(8-13Hz), has been generally used but this method are not free from the performance degradation of the BCI system because EEG has low spatial resolution and shows different ERD-appearing band according to users. Common spatial pattern(CSP) was proposed to solve the low spatial resolution problem but it has a disadvantage of being very sensitive to frequency-band selection. Discriminative filter bank common spatial pattern(DFBCSP) tried to solve the frequency-band selection problem by using the Fisher ratio of the averaged EEG signal power and establishing discriminative filter bank(DFB) which only includes the feature frequency-band. However, we found that DFB might not include the proper filters showing the spatial pattern of ERD. To solve this problem, we apply a band-selection process using CSP feature vectors and linear discriminant analysis to DFBCSP instead of the averaged EEG signal power. The filter selection results and the classification accuracies of the existing and the proposed methods show that the CSP feature is more effective than signal power feature.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.30-41
• /
• 1993

Developed in this paper is a feature based modeling system for the design of welded plat construction(WPC) which is composed of flat or bended plates represented as reference plane with a constant thickness. First, the necessity and the characteristics of the modeing system for WPC as compared with the assembly of mechanical parts are investigated. Secondly, feature library for the assembly of WPC is shown which contains several types of features like joint feature, groove feature, material feature, and precision feature. Thirdly, the assembly procedures are presented which mainly consist of both the assembly transformation and the correct assembly checking. Fourthly, weld lines of the assembled WPC are defined so that those can be used in the process planning or the manufacturing stage. Finally, a prototype by a geometric modeling software Pro/Engineer, a graphic software GL(Graphic Library), and C language on a CAD workstation IRIS.

• Journal of Korea Spatial Information System Society
• /
• v.3 no.1 s.5
• /
• pp.49-62
• /
• 2001

Recently, component-based software has become main trends in designing and developing computer software products. This component-based software has advantage of the interoperability on distributed computing environment and the reusability of pre-developed components. Also, GIS is designed and implemented with this component-based methodology, called Open GIS Component. OGC(OpenGIS Consortium) have announced various implementation and design specification and topic in GIS. In GIS, Spatial analysis functions like network analysis, TIN analysis are very important function and basically, estimate system functionality and performance using this analysis methods. The simple feature geometry specification is announced by OGC to increase the full interoperability of various spatial data. This specification includes just geometry spatial data model. However, in GIS which manages spatial data, not only geometric data but also topological data and various analysis functions have been used. The performance of GIS depends on how this geometric and topological data is managed well and how various spatial analyses are executed efficiently. So it requires integrated spatial data model between geometry and topology and extended data model of topology for spatial analysis, in case network analysis and TIN analysis in open GIS component. In this paper, we design analysis component like network analysis component and TIN analysis component. To manage topological information for spatial analysis in open GIS component, we design extended data model of simple feature geometry for spatial analysis. In addition to, we design the overall system architecture of open GIS component contained this topology model for spatial analysis.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.39 no.4
• /
• pp.71-74
• /
• 2014

A new classification framework called 'support feature machine' was introduced in [2] for analyzing medical data. Contrary to authors' claim, however, the proposed method is not designed to guarantee minimizing the use of the spatial feature variables. This paper mathematically remedies this drawback and provides comments on models from [2].