• Title/Summary/Keyword: Descent image

Search Result 34, Processing Time 0.028 seconds

A Study on the Tensor-Valued Median Filter Using the Modified Gradient Descent Method in DT-MRI (확산텐서자기공명영상에서 수정된 기울기강하법을 이용한 텐서 중간값 필터에 관한 연구)

  • Kim, Sung-Hee;Kwon, Ki-Woon;Park, In-Sung;Han, Bong-Soo;Kim, Dong-Youn
    • Journal of Biomedical Engineering Research
    • /
    • v.28 no.6
    • /
    • pp.817-824
    • /
    • 2007
  • Tractography using Diffusion Tensor Magnetic Resonance Imaging (DT-MRI) is a method to determine the architecture of axonal fibers in the central nervous system by computing the direction of the principal eigenvector in the white matter of the brain. However, the fiber tracking methods suffer from the noise included in the diffusion tensor images that affects the determination of the principal eigenvector. As the fiber tracking progresses, the accumulated error creates a large deviation between the calculated fiber and the real fiber. This problem of the DT-MRI tractography is known mathematically as the ill-posed problem which means that tractography is very sensitive to perturbations by noise. To reduce the noise in DT-MRI measurements, a tensor-valued median filter which is reported to be denoising and structure-preserving in fiber tracking, is applied in the tractography. In this paper, we proposed the modified gradient descent method which converges fast and accurately to the optimal tensor-valued median filter by changing the step size. In addition, the performance of the modified gradient descent method is compared with others. We used the synthetic image which consists of 45 degree principal eigenvectors and the corticospinal tract. For the synthetic image, the proposed method achieved 4.66%, 16.66% and 15.08% less error than the conventional gradient descent method for error measures AE, AAE, AFA respectively. For the corticospinal tract, at iteration number ten the proposed method achieved 3.78%, 25.71 % and 11.54% less error than the conventional gradient descent method for error measures AE, AAE, AFA respectively.

A Steepest-Descent Image Restoration with a Regularization Parameter (정칙화 구속 변수를 사용한 Steepest-Descent 영상 복원)

  • 홍성용;이태홍
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.19 no.9
    • /
    • pp.1759-1771
    • /
    • 1994
  • We proposed the iterative image restoration method based on the method of steepest descent with a regularization constraint for restoring the noisy motion-blurred images. The conventional method proposed by Jan Biemond et al, had drawback to amplify the additive noise and make ringing effects in the restored images by determining the value of regularization parameter experimentally from the degraded image to be restored without considering local information of the restored one. The method we proposed had a merit to suppress the noise amplification and restoration error by using the regularization parameter which estimate the value of it adaptively from each pixels of the image being restored in order to reduce the noise amplification and ringing effects efficiently. Also we proposed the termination rule to stop the iteration automatically when restored results approach into or diverse from the original solution in satisfaction. Through the experiments, proposed method showed better result not only in a MSE of 196 and 453 but also in the suppression of the noise amplification in the flat region compared with those proposed by Jan Biemond et al. of which MSE of 216 and 467 respectively when we used 'Lean' and 'Jaguar' images as original images.

  • PDF

Principal Feature Extraction on Image Data Using Neural Networks of Learning Algorithm Based on Steepest Descent and Dynamic tunneling (기울기하강과 동적터널링에 기반을 둔 학습알고리즘의 신경망을 이용한 영상데이터의 주요특징추출)

  • Jo, Yong-Hyeon
    • The Transactions of the Korea Information Processing Society
    • /
    • v.6 no.5
    • /
    • pp.1393-1402
    • /
    • 1999
  • This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

  • PDF

Descent Dataset Generation and Landmark Extraction for Terrain Relative Navigation on Mars (화성 지형상대항법을 위한 하강 데이터셋 생성과 랜드마크 추출 방법)

  • Kim, Jae-In
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.6_1
    • /
    • pp.1015-1023
    • /
    • 2022
  • The Entry-Descent-Landing process of a lander involves many environmental and technical challenges. To solve these problems, recently, terrestrial relative navigation (TRN) technology has been essential for landers. TRN is a technology for estimating the position and attitude of a lander by comparing Inertial Measurement Unit (IMU) data and image data collected from a descending lander with pre-built reference data. In this paper, we present a method for generating descent dataset and extracting landmarks, which are key elements for developing TRN technologies to be used on Mars. The proposed method generates IMU data of a descending lander using a simulated Mars landing trajectory and generates descent images from high-resolution ortho-map and digital elevation map through a ray tracing technique. Landmark extraction is performed by an area-based extraction method due to the low-textured surfaces on Mars. In addition, search area reduction is carried out to improve matching accuracy and speed. The performance evaluation result for the descent dataset generation method showed that the proposed method can generate images that satisfy the imaging geometry. The performance evaluation result for the landmark extraction method showed that the proposed method ensures several meters of positioning accuracy while ensuring processing speed as fast as the feature-based methods.

Analysis of Optimal Landing Trajectory in Attitude Angular Velocity Influence at Powered Descent Phase of Robotic Lunar Lander (무인 달착륙선의 동력하강단계에서 자세각속도 영향에 따른 최적화 착륙궤적 분석)

  • Park, Jae-ik;Rew, Dong-Young
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.46 no.5
    • /
    • pp.402-409
    • /
    • 2018
  • In this paper, we propose a lunar landing scenario of a robotic lunar landing mission and implements an optimal landing trajectory at the powered descent phase based on the proposed scenario. The change of attitude of the lunar lander in the power descent phase affects not only the amount of fuel used but also sensor operation of image based navigation. Therefore, the attitude angular velocity is included in the cost function of the optimal control problem to minimize the unnecessary attitude change when the optimal landing trajectory generates at powered descent phase of the lunar landing. The influence of the change of attitude angular velocity on the optimal landing trajectory are analyzed by adjusting the weight of the attitude angular velocity. Based on the results, we suggest the proper weight to generate the optimal landing trajectory in order to minimize the influence of the attitude angular velocity.

Measurement of the Flow Field Around a Quadcopter in Vertical Descending Flight (수직 하강 비행 조건에서의 쿼드콥터 주위의 유동장 계측)

  • Kwon, Min-Jeong;Kwon, Ki-Jung
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.46 no.5
    • /
    • pp.359-367
    • /
    • 2018
  • The vortex ring state that occurs during the descending flight of a rotorcraft generates a circulating flow like a donut near the rotating surface, and it often causes a rotorcraft fall due to loss of thrust. In this paper, we have physically identified the flow field in the vortex ring state of the quadcopter, one of the types of unmanned aerial vehicles. The descending flight of the quadcopter was simulated in a 1m subsonic wind tunnel of the Korea Aerospace Research Institute(KARI) and the Particle Image Velocimetry(PIV) was used for the flow field measurement. The induced velocity in the hovering state is estimated by using the momentum theory and the test was carried out in the range of descent rate at which the vortex ring condition could be caused. The development and the direction of the vortex ring were confirmed by the measurement of the flow field according to not only the descent rate but also propeller separation distance. In addition, the results of the study show the vortex ring state can be predicted sufficiently by measuring the flow velocity around the quadcopter.

Image Classification using Deep Learning Algorithm and 2D Lidar Sensor (딥러닝 알고리즘과 2D Lidar 센서를 이용한 이미지 분류)

  • Lee, Junho;Chang, Hyuk-Jun
    • Journal of IKEEE
    • /
    • v.23 no.4
    • /
    • pp.1302-1308
    • /
    • 2019
  • This paper presents an approach for classifying image made by acquired position data from a 2D Lidar sensor with a convolutional neural network (CNN). Lidar sensor has been widely used for unmanned devices owing to advantages in term of data accuracy, robustness against geometry distortion and light variations. A CNN algorithm consists of one or more convolutional and pooling layers and has shown a satisfactory performance for image classification. In this paper, different types of CNN architectures based on training methods, Gradient Descent(GD) and Levenberg-arquardt(LM), are implemented. The LM method has two types based on the frequency of approximating Hessian matrix, one of the factors to update training parameters. Simulation results of the LM algorithms show better classification performance of the image data than that of the GD algorithm. In addition, the LM algorithm with more frequent Hessian matrix approximation shows a smaller error than the other type of LM algorithm.

A New Block-based Gradient Descent Search Algorithm for a Fast Block Matching (고속 블록 정합을 위한 새로운 블록 기반 경사 하강 탐색 알고리즘)

  • 곽성근
    • Journal of the Korea Computer Industry Society
    • /
    • v.4 no.10
    • /
    • pp.731-740
    • /
    • 2003
  • Since motion estimation remove the redundant data to employ the temporal correlations between adjacent frames in a video sequence, it plays an important role in digital video coding. And in the block matching algorithm, search patterns of different shapes or sizes and the distribution of motion vectors have a large impact on both the searching speed and the image quality. In this paper, we propose a new fast block matching algorithm using the small-cross search pattern and the block-based gradient descent search pattern. Our algorithm first finds the motion vectors that are close to the center of search window using the small-cross search pattern, and then quickly finds the other motion vectors that are not close to the center of search window using the block-based gradient descent search pattern. Through experiments, compared with the block-based gradient descent search algorithm(BBGDS), the proposed search algorithm improves as high as 26-40% in terms of average number of search point per motion vector estimation.

  • PDF

Vehicle Face Recognition Algorithm Based on Weighted Nonnegative Matrix Factorization with Double Regularization Terms

  • Shi, Chunhe;Wu, Chengdong
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.14 no.5
    • /
    • pp.2171-2185
    • /
    • 2020
  • In order to judge that whether the vehicles in different images which are captured by surveillance cameras represent the same vehicle or not, we proposed a novel vehicle face recognition algorithm based on improved Nonnegative Matrix Factorization (NMF), different from traditional vehicle recognition algorithms, there are fewer effective features in vehicle face image than in whole vehicle image in general, which brings certain difficulty to recognition. The innovations mainly include the following two aspects: 1) we proposed a novel idea that the vehicle type can be determined by a few key regions of the vehicle face such as logo, grille and so on; 2) Through adding weight, sparseness and classification property constraints to the NMF model, we can acquire the effective feature bases that represent the key regions of vehicle face image. Experimental results show that the proposed algorithm not only achieve a high correct recognition rate, but also has a strong robustness to some non-cooperative factors such as illumination variation.

Fast Iterative Image Restoration Algorithm

  • Moon, J.I.;Paik, J.K.
    • Journal of Electrical Engineering and information Science
    • /
    • v.1 no.2
    • /
    • pp.67-76
    • /
    • 1996
  • In the present paper we propose two new improved iterative restoration algorithms. One is to accelerate convergence of the steepest descent method using the improved search directions, while the other accelerates convergence by using preconditioners. It is also shown that the proposed preconditioned algorithm can accelerate iteration-adaptive iterative image restoration algorithm. The preconditioner in the proposed algorithm can be implemented by using the FIR filter structure, so it can be applied to practical application with manageable amount of computation. Experimental results of the proposed methods show good perfomance improvement in the sense of both convergence speed and quality of the restored image. Although the proposed methods cannot be directly included in spatially-adaptive restoration, they can be used as pre-processing for iteration-adaptive algorithms.

  • PDF