• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.817-827
• /
• 2014

In the satellite remote sensing, the operational environment of the satellite sensor causes image degradation during the image acquisition. The degradation results in noise and blurring which badly affect identification and extraction of useful information in image data. This study proposes a maximum a posteriori (MAP) estimation using Point-Jacobian iteration to restore a degraded image. The proposed method assumes a Gaussian additive noise and Markov random field of spatial continuity. The proposed method employs a neighbor window of spoke type which is composed of 8 line windows at the 8 directions, and a boundary adjacency measure of Mahalanobis square distance between center and neighbor pixels. For the evaluation of the proposed method, a pixel-wise classification was used for simulation data using various patterns similar to the structure exhibited in high resolution imagery and an unsupervised segmentation for the remotely-sensed image data of 1 mspatial resolution observed over the north area of Anyang in Korean peninsula. The experimental results imply that it can improve analytical accuracy in the application of remote sensing high resolution imagery.

• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.945-953
• /
• 2012

A depth map can be obtained by projecting/capturing patterns of stripes using a projector-camera system and analyzing the geometric relationship between the projected patterns and the captured patterns. This is usually called structured light technique. In this paper, we propose a new multi-threading scheme for accelerating a conventional structured light technique. On CPUs and GPUs, multi-threading can be implemented by using OpenMP and CUDA, respectively. However, the problem is that their performance changes according to the computational conditions of partial processes of a structured light technique. In other words, OpenMP (using multiple CPUs) outperformed CUDA (using multiple GPUs) in partial processes such as pattern decoding and depth estimation. In contrast, CUDA outperformed OpenMP in partial processes such as rectification and pattern segmentation. Therefore, we carefully analyze the computational conditions where each outperforms the other and do use the better one in the related conditions. As a result, the proposed method can estimate a depth map in a speed of over 25 fps on $1280{\times}800$ images.

• International Journal of Contents
• /
• v.9 no.1
• /
• pp.6-10
• /
• 2013

Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.

• Transactions of Materials Processing
• /
• v.13 no.4
• /
• pp.334-341
• /
• 2004

In this study, a remeshing algorithm adapted to the mesh density map using the Delaunay mesh generation method is developed. In the finite element simulation of forging process, the numerical error increases as the process goes on because of discrete property of the finite elements and distortion of elements. Especially, in the region where stresses and strains are concentrated, the numerical error will be highly increased. However, it is not desirable to use a uniformly fine mesh in the whole domain. Therefore, it is necessary to reduce the analysis error by constructing locally refined mesh at the region where the error is concentrated such as at the die corner. In this paper, the point insertion algorithm is used and the mesh size is controlled by using a mesh density map constructed with a posteriori error estimation. An optimized smoothing technique is adopted to have smooth distribution of the mesh and improve the mesh element quality.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.8
• /
• pp.773-780
• /
• 2015

Navigation in outdoor environments is a fundamental and challenging problem for unmanned ground vehicles. Detecting lane markings or boundaries on the road may be one of the solutions to make navigation easy. However, because of various environments and road conditions, a robust lane detection is difficult. In this paper, we propose a new approach for estimating virtual lanes on a traversable region. Estimating the virtual lanes consist of two steps: (i) we detect virtual road region through road model selection based on traversability at current frame and similarity between the interframe and (ii) we estimate virtual lane using the number of lane on the road and results of previous frame. To improve the detection performance and reduce the searching region of interests, we use a probability map representing the traversability of the outdoor terrain. In addition, by considering both current and previous frame simultaneously, the proposed method estimate more stable virtual lanes. We evaluate the performance of the proposed approach using real data in outdoor environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.464-471
• /
• 2000

The number of quantization bits of the input signals $X_k$,$Y_k$ need to be optimally determined through the trade-off between the H/W complexity and the BER performance in Turbo codes applications. Also, an effective means to incorporate a channel reliability $L_c$ in the Log-MAP-based Turbo decoding is highly required. because it has a major effect on both the complexity and the performance. In this paper, a novel bit-shifting approach that substitutes for the multiplying is proposed so as to effectively incorporate. $L_c$ in Turbo decoding. The optimal number of quantization bits of $X_k$,$Y_k$ is investigated through Monte-Carlo simulations assuming that bit-shifting approach is adopted. In addition. The effects of an incorrect estimation of noise variance on the performance of Turbo codes is investigated. There is a confined range in which the effects of an incorrect estimation can be ignored.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.428-435
• /
• 2017

In this paper, we propose a novel motion field estimation algorithm for which a U-disparity map and forward-and-backward error removal are applied in a vehicular environment. Generally, a motion exists in an image obtained by a camera attached to a vehicle by vehicle movement; however, the obtained motion vector is inaccurate because of the surrounding environmental factors such as the illumination changes and vehicles shaking. It is, therefore, difficult to extract an accurate motion vector, especially on the road surface, due to the similarity of the adjacent-pixel values; therefore, the proposed algorithm first removes the road surface region in the obtained image by using a U-disparity map, and uses then the optical flow that represents the motion vector of the object in the remaining part of the image. The algorithm also uses a forward-backward error-removal technique to improve the motion-vector accuracy and a vehicle's movement is predicted through the application of the RANSAC (RANdom SAmple Consensus) to the previously obtained motion vectors, resulting in the generation of a motion field. Through experiment results, we show that the performance of the proposed algorithm is superior to that of an existing algorithm.

• Journal of Biosystems Engineering
• /
• v.36 no.3
• /
• pp.180-186
• /
• 2011

The objective of this research was to establish the estimation method of growth information on potato using Multi-Spectral Image Sensor (MSIS) and Global Positioning System (GPS). And growth estimation map for determining a prescription map over the entire field was generated. To determine the growth model, 10 ground-truth points of areas of $4m^2$ each were selected and investigated. The growth information included stem number, crop height and SPAD value. In addition, images information involving the ground-truth points were also taken by an unmanned helicopter, and reflectance value of Green, Red, and NIR bands were calculated with image processing. Then, growth status of potato was modeled by multi-regression analysis using these reflectance value of Green, Red, and NIR. As a result, potato growth information could be detected by analyzing Green, Red, and NIR images. Stem number, crop height and SPAD value could be estimated with $R^2$ values of 0.600, 0.657 and 0.747 respectively. The generated GIS map would describe variability of the potato growth in a whole field.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.929-932
• /
• 2012

Beat map shows the distribution property of the beating sound in the bell structure. Using the beat map, beat control and beat estimation are available. To draw the beat map, mode pair parameters of the bell are required. However, in case of large bell which is struck by a heavy wooden hammer, it is very difficult to measure the excitation force and to obtain the mode pair parameters. In this paper, we determined the mode pair parameters of the bell from the transmissibility between the roving signal and reference signal, using ODS(operational deflection shape) method. The mode pair data are input to the theoretical model of the beat response and beating waves are generated on the bell circumference. All the numerical and beat map drawing procedures are automatized using Matlab. Finally, the reliability of the beat map generated by the program is verified.