• Title/Summary/Keyword: computer based estimation

Search Result 1,366, Processing Time 0.025 seconds

Hypergraph model based Scene Image Classification Method (하이퍼그래프 모델 기반의 장면 이미지 분류 기법)

  • Choi, Sun-Wook;Lee, Chong Ho
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.24 no.2
    • /
    • pp.166-172
    • /
    • 2014
  • Image classification is an important problem in computer vision. However, it is a very challenging problem due to the variability, ambiguity and scale change that exists in images. In this paper, we propose a method of a hypergraph based modeling can consider the higher-order relationships of semantic attributes of a scene image and apply it to a scene image classification. In order to generate the hypergraph optimized for specific scene category, we propose a novel search method based on a probabilistic subspace method and also propose a method to aggregate the expression values of the member semantic attributes that belongs to the searched subsets based on a linear transformation method via likelihood based estimation. To verify the superiority of the proposed method, we showed that the discrimination power of the feature vector generated by the proposed method is better than existing methods through experiments. And also, in a scene classification experiment, the proposed method shows a competitive classification performance compared with the conventional methods.

Segmentation-based tnage Coding Method without Need for Transmission of Contour Information (윤곽선 정보의 전송이 불필요한 분할기반 영상 부호화 방법)

  • Choi Jae Gark;Kang Hyun-Soo;Koh Chang-Rim;Kwon Oh-Jun;Lee Jong-Keuk
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.32 no.5
    • /
    • pp.187-195
    • /
    • 2005
  • A new segmentation-based image coding method which no needs transmission of contour data is proposed. The shape information acts as bottleneck in the segmentation-based video coding because it has much portion of transmission data. The proposed method segments a previous decoded frame, instead of a current frame. As a result, there is no need for transmission of contour information to a decoder. Therefore, the saved bits can be assigned to encode other information such as error signals. As shown in experiment results, if data rate is very highly increased due to abrupt motion under very low bit rate coding having limited transmission bits, PSNR of conventional block-based method go down about 20dB, while the proposed method shows a good reconstruction quality without rapid PSNR drop.

Super Resolution Technique Through Improved Neighbor Embedding (개선된 네이버 임베딩에 의한 초해상도 기법)

  • Eum, Kyoung-Bae
    • Journal of Digital Contents Society
    • /
    • v.15 no.6
    • /
    • pp.737-743
    • /
    • 2014
  • For single image super resolution (SR), interpolation based and example based algorithms are extensively used. The interpolation algorithms have the strength of theoretical simplicity. However, those algorithms are tending to produce high resolution images with jagged edges, because they are not able to use more priori information. Example based algorithms have been studied in the past few years. For example based SR, the nearest neighbor based algorithms are extensively considered. Among them, neighbor embedding (NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the sizes of local training sets are always too small. So, NE algorithm is weak in the performance of the visuality and quantitative measure by the poor generalization of nearest neighbor estimation. An improved NE algorithm with Support Vector Regression (SVR) was proposed to solve this problem. Given a low resolution image, the pixel values in its high resolution version are estimated by the improved NE. Comparing with bicubic and NE, the improvements of 1.25 dB and 2.33 dB are achieved in PSNR. Experimental results show that proposed method is quantitatively and visually more effective than prior works using bicubic interpolation and NE.

Dense-Depth Map Estimation with LiDAR Depth Map and Optical Images based on Self-Organizing Map (라이다 깊이 맵과 이미지를 사용한 자기 조직화 지도 기반의 고밀도 깊이 맵 생성 방법)

  • Choi, Hansol;Lee, Jongseok;Sim, Donggyu
    • Journal of Broadcast Engineering
    • /
    • v.26 no.3
    • /
    • pp.283-295
    • /
    • 2021
  • This paper proposes a method for generating dense depth map using information of color images and depth map generated based on lidar based on self-organizing map. The proposed depth map upsampling method consists of an initial depth prediction step for an area that has not been acquired from LiDAR and an initial depth filtering step. In the initial depth prediction step, stereo matching is performed on two color images to predict an initial depth value. In the depth map filtering step, in order to reduce the error of the predicted initial depth value, a self-organizing map technique is performed on the predicted depth pixel by using the measured depth pixel around the predicted depth pixel. In the process of self-organization map, a weight is determined according to a difference between a distance between a predicted depth pixel and an measured depth pixel and a color value corresponding to each pixel. In this paper, we compared the proposed method with the bilateral filter and k-nearest neighbor widely used as a depth map upsampling method for performance comparison. Compared to the bilateral filter and the k-nearest neighbor, the proposed method reduced by about 6.4% and 8.6% in terms of MAE, and about 10.8% and 14.3% in terms of RMSE.

Error Correction Scheme in Location-based AR System Using Smartphone (스마트폰을 이용한 위치정보기반 AR 시스템에서의 부정합 현상 최소화를 위한 기법)

  • Lee, Ju-Yong;Kwon, Jun-Sik
    • Journal of Digital Contents Society
    • /
    • v.16 no.2
    • /
    • pp.179-187
    • /
    • 2015
  • Spread of smartphone creates various contents. Among many contents, AR application using Location Based Service(LBS) is needed widely. In this paper, we propose error correction algorithm for location-based Augmented Reality(AR) system using computer vision technology in android environment. This method that detects the early features with SURF(Speeded Up Robust Features) algorithm to minimize the mismatch and to reduce the operations, and tracks the detected, and applies it in mobile environment. We use the GPS data to retrieve the location information, and use the gyro sensor and G-sensor to get the pose estimation and direction information. However, the cumulative errors of location information cause the mismatch that and an object is not fixed, and we can not accept it the complete AR technology. Because AR needs many operations, implementation in mobile environment has many difficulties. The proposed approach minimizes the performance degradation in mobile environments, and are relatively simple to implement, and a variety of existing systems can be useful in a mobile environment.

A Pilot Study on Hip Bone Mineral Densities Estimation from Forearm CBCT images

  • Ko, Hoon;Lee, Chang-Hoon;Jeong, Kwanmoon;Lee, Myeung Su;Nam, Yunyoung;Yoon, Kwon-Ha;Lee, Jinseok
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.11 no.12
    • /
    • pp.6054-6068
    • /
    • 2017
  • In this paper, we defined the relative cross-sectional area of forearm cortical bone and investigated its correlation with hip bone mineral density values of total femur, femoral neck, femoral trochanter, femoral inter-trochanter and femoral ward's triangle, respectively. Based on the correlations, we established a linear transformation between the relative cross-sectional area of forearm cortical bone and each hip bone BMD. We obtained forearm images using CBCT and hip bone BMDs using dual-energy X-ray absorptiometry (DXA) for 28 subjects. We also investigated the optimal forearm region to provide the strongest correlation coefficient. We used the optimized forearm region to establish each linear transformation to estimate BMD values for total femur, femoral neck, femoral trochanter, femoral inter-trochanter and femoral ward's triangle from the relative cross-sectional area of forearm cortical bone, respectively. We observed the strong correlations with total femur (r=0.889), femoral neck (r=0.924), femoral trochanter (r=0.821), femoral inter-trochanter (r=0.867) and femoral ward's triangle (r=0.895), respectively. The strongest correlation was observed in the forearm mid-shaft regions. Our results suggest that the hip bone BMD values can be simply estimated from forearm CBCT images in a convenient sitting position without X-ray exposure on a hip including genital organs, and may be useful for screening osteoporosis.

Shell Partition-based Constant Modulus Algorithm (Shell 분할 기반 CMA)

  • Lee, Gi-Hun;Park, Rae-Hong;Park, Jae-Hyuk;Lee, Byung-Uk
    • Journal of the Korean Institute of Telematics and Electronics B
    • /
    • v.33B no.1
    • /
    • pp.133-143
    • /
    • 1996
  • The constant modulus algorithm (CMA), one of the widely used blind equalization algorithms, equalizes channels using the second-order statistic of equalizer outputs. The performance of the CMA for multi-level signals such as the quadrature amplitude modulation (QAM) signal degrades because the CMA maps all signal power onto a single modulus. in this paper, to improve the equalization performance of a QAM system, we propose a shell partitioning method based on error magnitude. We assume the probability distribution of an equalizer output as Gaussian, and obtain decision boundaries by maximum likelihood estimation based on the fact that the distribution of the equalizer output power is noncentral $x^2$. The proposed CMA constructs a multi-moduli equlization system based on the fact that each shell separated by decision boundaries employs a single modulus. Computer simulation results for 32-QAM and 64-QAM show the effectiveness of the proposed algorithm.

  • PDF

A Video Deinterlacing Algorithm Using Geometric Duality (기하 쌍대성의 원리가 적용된 비디오 디인터레이싱 알고리듬)

  • Lee, Kwang-Bo;Park, Sung-Han
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.46 no.6
    • /
    • pp.68-77
    • /
    • 2009
  • A single field deinterlacing method, namely interpolation algorithm derived from low resolution (ILR), is presented in this paper. Traditional deinterlacing methods usually employ edge-based interpolation technique within pixel-based estimation. However, edge-based methods are somehow sensitive to noise and intensity variation in the image. Moreover, the methods are not satisfied in deciding the exact edge direction which controls the performance of the interpolation. In order to reduce the sensitivity, the proposed algorithm investigates low-resolution characteristics of the pixel to be interpolated, and applies it to high-resolution image. Simulation results demonstrates that the proposed method gives not only a better objective performance in terms of PSNR results compare to conventional edge-based interpolation methods, but also better subjective image quality.

Accuracy evaluation of ZigBee's indoor localization algorithm (ZigBee 실내 위치 인식 알고리즘의 정확도 평가)

  • Noh, Angela Song-Ie;Lee, Woong-Jae
    • Journal of Internet Computing and Services
    • /
    • v.11 no.1
    • /
    • pp.27-33
    • /
    • 2010
  • This paper applies Bayesian Markov inferred localization techniques for determining ZigBee mobile device's position. To evaluate its accuracy, we compare it with conventional technique, map-based localization. While the map-based localization technique referring to database of predefined locations and their RSSI data, the Bayesian Markov inferred localization is influenced by changes of time, direction and distance. All determinations are drawn from the estimation of Received Signal Strength (RSS) using ZigBee modules. Our results show the relationship between RSSI and distance in indoor ZigBee environment and higher localization accuracy of Bayesian Markov localization technique. We conclude that map-based localization is not suitable for flexible changes in indoors because of its predefined condition setup and lower accuracy comparing to distance-based Markov Chain inference localization system.

Performance Analysis of Adaptive Beamforming System Based on Planar Array Antenna (평면 배열 안테나 기반의 적응 빔형성 시스템 성능 분석)

  • Mun, Ji-Youn;Hwang, Suk-Seung
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.13 no.6
    • /
    • pp.1207-1212
    • /
    • 2018
  • The signal intelligence (SIGINT) technology is actively used for collecting various data, in a number of fields, including a military industry. In order to collect the signal information and data and to transmit/receive the collected data efficiently, the accurate angle-of-arrival (AOA) information is required and communication disturbance from the interference or jamming signal should be minimized. In this paper, we present the structure of an adaptive beam-forming satellite system based on the planar array antenna, for collecting and transmitting/receiving the signal information and data efficiently. The presented adaptive beam-forming system consists of an antenna in the form of a planar array, an AOA estimator based on the Multiple Signal Classification (MUSIC) algorithm, an adaptive Minimum Variance Distortionless Response (MVDR) interference canceler, a signal processing and D/B unit, and a transmission beamformer based on Minimum mean Square Error (MMSE). In addition, through the computer simulation, we evaluate and analyze the performance of the proposed system.