• Journal of KIISE:Software and Applications
• /
• v.26 no.8
• /
• pp.1000-1009
• /
• 1999

본 논문에서는 비디오 데이타를 분석하여 다양한 카메라의 동작을 정량적으로 추출하는 방법을 제안한다. 본 논문에서 제안하는 카메라의 동작 추출 방법은 어파인 모델을 이용한 방법으로 인접 영상으로부터 추출한 동작 벡터를 어파인 모델에 적용하고 회귀분석법을 통해 어파인 모델을 구성하는 파라미터를 구한다. 그런 다음, 파라미터들의 크기를 분석하고 상호 관계를 해석하여 카메라의 동작을 추출한다. 본 논문에서는 잡음이 포함된 동작 벡터를 필터링하여 사용하므로 잡음에 강건한 결과를 얻을 수 있다. 그리고 어파인 모델을 구성하는 파라미터만을 분석함으로써 카메라의 다양한 동작을 간단하면서도 비교적 정확하게 추출한다. 실험 결과는 카메라의 동작을 정확하게 추출하고 있음을 보여준다.Abstract This paper presents an elegant method, an affine-model based approach, that can qualitatively estimate the information of camera motion. We define various types of camera motion by means of parameters of an affine-model. To get those parameters from images, we fit an affine-model to the field of instantaneous velocities, rather than raw images. We correlate consecutive images to get instantaneous velocities. The size filtering of the velocities are applied to remove noisy components, and the regression approach is employed for the fitting procedure. The fitted values of the parameters are examined to get the estimates of camera motion. The experimental results show that the suggested approach can yield the qualitative information of camera motion successfully.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.468-476
• /
• 2002

The confidence of information from image processing depends on the original image quality. Enhancing the confidence by an algorithm has an essential limitation. Especially, road images are exposed to lots of noisy sources, which makes image processing difficult. We, in this paper, propose a FNN (fuzzy-neural network) capable oi deciding the quality of a road image prior to extracting lane-related information. According to the decision by the FNN, road images are classified into good or bad to extract lane-related information. A CDF (cumulative distribution function), a function of edge histogram, is utilized to construct input parameters of the FNN, it is based on the fact that the shape of the CDF and the image quality has large correlation. Input pattern vector to the FNN consists of ten parameters in which nine parameters are from the CDF and the other one is from intensity distribution of raw image. Correlation analysis shows that each parameter represents the image quality well. According to the experimental results, the proposed FNN system was quite successful. We carried out simulations with real images taken by various lighting and weather conditions and achieved about 99% successful decision-making.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.65-80
• /
• 1999

This paper presents an elegant method, an affine-model based approach, that can qualitatively estimate the information of camera motion. We define various types of camera motion by means of parameters of an affine-model. To get those parameters form images, we fit an affine-model to the field of instantaneous velocities, rather than raw images. We correlate consecutive images to get instantaneous velocities. The size filtering of the velocities are applied to remove noisy components, and the regression approach is employed for the fitting procedure. The fitted values of the parameters are examined to get the estimates of camera motion. The experimental results show that the suggested approach can yield the qualitative information of camera motion successfully.

• Smart Media Journal
• /
• v.1 no.3
• /
• pp.22-28
• /
• 2012

As the smart media becomes more popular, the demand for high-quality 3D images and depth maps is increasing. However, performance of the current technologies to acquire depth maps is not sufficient. The depth maps from stereo matching methods have low accuracy in homogeneous regions. The depth maps from depth cameras are noisy and have low-resolution due to technical limitations. In this paper, we introduce the state-of-the-art algorithms for depth map enhancement and up-sampling from conventional methods using only depth maps to the latest algorithms referring to both depth maps and their corresponding color images. We also present depth map enhancement algorithms for hybrid camera systems in detail.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.1-8
• /
• 2010

Noise removal methods for noisy images have been studied a lot in the domain of spatial and transform filtering. Low pass filtering was initially applied in the spatial domain. Recently, discrete wavelet transform has widely used for image denoising as well as image compression due to an excellent energy compaction and a property of multiresolution. In this paper, Gabor cosine and sine transform which is considered as human visual filter is applied to image denoising areas using soft thresholding technique. GCST is compared with excellent wavelet transform which uses existing soft thresholding methods from PSNR point of view. Resultant images removed noises are also visually compared. Experimental results with adding four different standard deviation levels of Gaussian distributed noises to real images show that the proposed transform has better PSNR performance of a maximum of 1.18 dB and visible perception than wavelet transform.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.871-886
• /
• 2011

This paper proposes a powerful SVM-ASM filter, the adaptive switching median(ASM) filter based on support vector machines(SVMs), to effectively reduce impulse noise in corrupted images while preserving image details and features. The proposed SVM-ASM filter is composed of two stages: SVM impulse detection and ASM filtering. SVM impulse detection determines whether the pixels are corrupted by noise or not according to an optimal discrimination function. ASM filtering implements the image filtering with a variable window size to effectively remove the noisy pixels determined by the SVM impulse detection. Experimental results show that the SVM-ASM filter performs significantly better than many other existing filters for denoising impulse noise even in highly corrupted images with regard to noise suppression and detail preservation. The SVM-ASM filter is also extremely robust with respect to various test images and various percentages of image noise.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.229-236
• /
• 2008

This paper examines effectiveness of using color images instead of grayscale ones for automatic lipreading. First, we show the effect of color information for performance of humans' lipreading. Then, we compare the performance of automatic lipreading using features obtained by applying principal component analysis to grayscale and color images. From the experiments for various color representations, it is shown that color information is useful for improving performance of automatic lipreading; the best performance is obtained by using the RGB color components, where the average relative error reductions for clean and noisy conditions are 4.7% and 13.0%, respectively.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.556-564
• /
• 2021

Numerous spatial and transform-domain-based conventional denoising algorithms struggle to keep critical and minute structural features of the image, especially at high noise levels. Although neural network approaches are effective, they are not always reliable since they demand a large quantity of training data, are computationally complicated, and take a long time to construct the model. A new framework of enhanced hybrid filtering is developed for denoising color images tainted by additive white Gaussian Noise with the goal of reducing algorithmic complexity and improving performance. In the first stage of the proposed approach, the noisy image is refined using a high-dimensional non-local means filter based on Principal Component Analysis, followed by the extraction of the method noise. The wavelet transform and SURE Shrink techniques are used to further culture this method noise. The final denoised image is created by combining the results of these two steps. Experiments were carried out on a set of standard color images corrupted by Gaussian noise with multiple standard deviations. Comparative analysis of empirical outcome indicates that the proposed method outperforms leading-edge denoising strategies in terms of consistency and performance while maintaining the visual quality. This algorithm ensures homogeneous noise reduction, which is almost independent of noise variations. The power of both the spatial and transform domains is harnessed in this multi realm consolidation technique. Rather than processing individual colors, it works directly on the multispectral image. Uses minimal resources and produces superior quality output in the optimal execution time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.175-183
• /
• 2015

The proposed algorithm consists of two stages: the learning and synthesis stages. At the learning stage, we first collect various high-resolution (HR)-low-resolution (LR) text image pairs, and quantize the LR images, and extract HR-LR block pairs. Based on quantized LR blocks, the LR-HR block pairs are clustered into a pre-determined number of classes. For each class, an optimal 2D-FIR filter is computed, and it is stored into a dictionary with the corresponding LR block for indexing. At the synthesis stage, each quantized LR block in an input LR image is compared with every LR block in the dictionary, and the FIR filter of the best-matched LR block is selected. Finally, a HR block is synthesized with the chosen filter, and a final HR image is produced. Also, in order to cope with noisy environment, we generate multiple dictionaries according to noise level at the learning stage. So, the dictionary corresponding to the noise level of the input image is chosen, and a final HR image is produced using the selected dictionary. Experimental results show that the proposed algorithm outperforms the previous works for noisy images as well as noise-free images.

• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.8-15
• /
• 2020

This research is a case study of underwater object tracking based on real-time recurrent regression networks (Re³). Re³ has the concept of generic object tracking. Because of these characteristics, it is very effective to apply this model to unclear underwater sonar images. The model also an pursues object tracking method, thus it solves the problem of calculating load that may be limited when object detection models are used, unlike the tracking models. The model is also highly intuitive, so it has excellent continuity of tracking even if the object being tracked temporarily becomes partially occluded or faded. There are 4 types of the dataset using multi-beam sonar images: including (a) dummy object floated at the testbed; (b) dummy object settled at the bottom of the sea; (c) tire object settled at the bottom of the testbed; (d) multi-objects settled at the bottom of the testbed. For this study, the experiments were conducted to obtain underwater sonar images from the sea and underwater testbed, and the validity of using noisy underwater sonar images was tested to be able to track objects robustly.