• ETRI Journal
• /
• 제34권4호
• /
• pp.572-582
• /
• 2012

The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.

• Steel and Composite Structures
• /
• 제28권2호
• /
• pp.123-138
• /
• 2018

Eccentrically braced frames (EBF) represent an optimal structural solution for seismic prone areas, being able to provide high dissipative capacity and good elastic stiffness, to withstand strong seismic events without significant loss of bearing capacity and to avoid damage to non-structural elements in case of low and moderate earthquakes. The accurate knowledge of the cyclic behaviour of the dissipative links, characterizing the whole performance of EBFs, is required to optimize the structural properties and to refine the design techniques adopted for multi-storey buildings' analysis. Reliable numerical models for the links, at the same time requiring a limited computational effort, are then needed. The present work shows the results of a wide experimental test campaign executed on real-scale one storey/one bay frames with horizontal and vertical links, together with the elaboration of a simple semi-analytical model for the quick representation of the cyclic behaviour of shear links.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.370-376
• /
• 2023

Aiming at the problems of low image enhancement accuracy, long enhancement time and poor image quality in the traditional robot sequence motion image enhancement methods, an adaptive enhancement method for robot sequence motion image is proposed. The feature representation of the image was obtained by Karhunen-Loeve (K-L) transformation, and the nonlinear relationship between the robot joint angle and the image feature was established. The trajectory planning was carried out in the robot joint space to generate the robot sequence motion image, and an adaptive homomorphic filter was constructed to process the noise of the robot sequence motion image. According to the noise processing results, the brightness of robot sequence motion image was enhanced by using the multi-scale Retinex algorithm. The simulation results showed that the proposed method had higher accuracy and consumed shorter time for enhancement of robot sequence motion images. The simulation results showed that the image enhancement accuracy of the proposed method could reach 100%. The proposed method has important research significance and economic value in intelligent monitoring, automatic driving, and military fields.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.653-669
• /
• 2024

Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.739-748
• /
• 2014

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.

• 한국프랜차이즈경영연구
• /
• 제10권3호
• /
• pp.37-52
• /
• 2019

Purpose - This study examined the relationship between service quality, perceived value, customer satisfaction and behavioral intention of coffee shop using CoffeeSERV scale. In this model, CoffeeSERV scale consists of fundamental characteristics, physical environment, confidence, beverage characteristics, and representation factors. In particular, this study tried to demonstrate the moderating effect of customer's regulatory focus orientation among in the relationships between service quality, perceived value, customer satisfaction and behavioral intention. Research design, data, and methodology - This study intends to expand the existing service quality research by using the coffee shop service quality measurement tool developed by domestic researchers. I wanted to find some implications for the trend. In particular, this study applied the regulatory focus theory to identify individual differences of customers regulatory focusing motivation. In order to verify several hypotheses, the data were 227 college students and analyzed with SPSS/PC 21.0 and SmartPLS 3 program. The moderating role of customer's regulatory focusing motivation was tested using multi-group analysis with SmartPLS 3 program. Results - The resutls are as follows. First, the fundamental characteristic factors only had a significant influence on the utilitarian value perception, but in the hedonic value perception, all other service factors except for the beverage characteristic had a statistically significant effect. Second, utilitarian and hedonic value had significant effects on customer satisfaction. Third, customer satisfaction had a significant effect on behavioral intention. Finally, the regulatory focus orientation played a moderating role in the relationship between beverage characteristic - utilitarian value, representation - utilitarian value, fundamental characteristic - hedonic value, physical environment - hedonic value, confidence - hedonic value, and utilitarian value - behavioral intention. Conclusions - The results of this study show that the various service quality factors that make up the CoffeeSERV scale have different effects on utilitarian and hedonic value. This means that perceived benefits from product and service experience have different impacts on the customer's experience. Therefore, marketers should identify the impacts of service quality dimension that customers who use coffee shops consider important, understand the impact process of these quality factors on experience value, customer satisfaction, and behavioral intention, and allocate limited marketing budget. The results also show that it is possible to establish differentiatied response strategies using customer's regulatory focus orientation to find ways to enhance utlitarian and hedonic value, customer satisfaction, and behavioral intention using various Coffeeshop service quality factors. At the end of this paper, some limitations and future research directions were suggested.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권5호
• /
• pp.2141-2155
• /
• 2020

In order to meet the requirements of background change, illumination variation, moving shadow interference and high accuracy in object detection of moving camera, and strive for real-time and high efficiency, this paper presents an object detection algorithm based on sparse approximation recursion and sparse coding migration in subspace. First, low-rank sparse decomposition is used to reduce the dimension of the data. Combining with dictionary sparse representation, the computational model is established by the recursive formula of sparse approximation with the video sequences taken as subspace sets. And the moving object is calculated by the background difference method, which effectively reduces the computational complexity and running time. According to the idea of sparse coding migration, the above operations are carried out in the down-sampling space to further reduce the requirements of computational complexity and memory storage, and this will be adapt to multi-scale target objects and overcome the impact of large anomaly areas. Finally, experiments are carried out on VDAO datasets containing 59 sets of videos. The experimental results show that the algorithm can detect moving object effectively in the moving camera with uniform speed, not only in terms of low computational complexity but also in terms of low storage requirements, so that our proposed algorithm is suitable for detection systems with high real-time requirements.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.209-214
• /
• 2021

Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

• 대한전자공학회논문지SP
• /
• 제48권1호
• /
• pp.71-79
• /
• 2011

이미징 파이프라인(imaging pipeline)의 목적은 디스플레이 되는 영상을 원영상과 비슷하게 변환하는 것이다. 이를 위해 감마 조정 혹은 히스토그램기반 방법이 영상대비와 세부 영역을 개선하기 위해 제안되었다. 그러나 이러한 방법들은 조도성분과 색도성분이 위치에 따라 변화하므로 영상 개선에 한계가 있다. 따라서 MSR (Multi-Scale Retinex) 기법이 제안되었으며, 이는 영상에 따른 가우시안 필터의 크기에 의존하며, 독립적인 로그 신호를 기반으로 한다. 그러므로 영상 보정 후 후광효과(Halo), 색상변화(Color change or graying-out), 특정 색상의 두드러짐 등의 영상 왜곡(image distortion)이 발생한다. 따라서 본 논문에서는 영상을 전역조명성분, 국부조명성분, 반사성분으로 나누는 새로운 색상 보정 방법을 제안한다. 제안한 방법에서 전역조명성분은 가우시안 필터를 작용하여 획득하며, 국부 조명성분은 JND(Just-noticeable difference)기반 적응적 필터를 적용하여 획득한다. 반사성분은 원 영상에 획득된 전역조명성분과 국부조명성분으로 나누어 줌으로써 획득된다. 개선된 영상은 멱함수(power function)를 수행한 후 이들의 곱으로 획득되며, sRGB로 표현된다. 실험 결과에서 제안한 방법이 기존의 방법에 비해 우수한 성능을 보인다.