Youngbae Hwang
KAIST
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Youngbae Hwang.
computer vision and pattern recognition | 2014
Youngbae Hwang; Joon-Young Lee; In So Kweon; Seon Joo Kim
This paper introduces a new color transfer method which is a process of transferring color of an image to match the color of another image of the same scene. The color of a scene may vary from image to image because the photographs are taken at different times, with different cameras, and under different camera settings. To solve for a full nonlinear and nonparametric color mapping in the 3D RGB color space, we propose a scattered point interpolation scheme using moving least squares and strengthen it with a probabilistic modeling of the color transfer in the 3D color space to deal with mis-alignments and noise. Experiments show the effectiveness of our method over previous color transfer methods both quantitatively and qualitatively. In addition, our framework can be applied for various instances of color transfer such as transferring color between different camera models, camera settings, and illumination conditions, as well as for video color transfers.
computer vision and pattern recognition | 2007
Youngbae Hwang; Jun-Sik Kim; In So Kweon
In this paper, we introduce the Skellam distribution as a sensor noise model for CCD or CMOS cameras. This is derived from the Poisson distribution of photons that determine the sensor response. We show that the Skellam distribution can be used to measure the intensity difference of pixels in the spatial domain, as well as in the temporal domain. In addition, we show that Skellam parameters are linearly related to the intensity of the pixels. This property means that the brighter pixels tolerate greater variation of intensity than the darker pixels. This enables us to decide automatically whether two pixels have different colors. We apply this modeling to detect the edges in color images. The resulting algorithm requires only a confidence interval for a hypothesis test, because it uses the distribution of image noise directly. More importantly, we demonstrate that without conventional Gaussian smoothing the noise model-based approach can automatically extract the fine details of image structures, such as edges and corners, independent of camera setting.
international conference on robotics and automation | 2007
Yunsu Bok; Youngbae Hwang; In So Kweon
The CCD camera and the 2D laser range finder are widely used for motion estimation and 3D reconstruction. With their own strengths and weaknesses, low-level fusion of these two sensors complements each other. We combine these two sensors to perform motion estimation and 3D reconstruction simultaneously and precisely. We develop a motion estimation scheme appropriate for this sensor system. In the proposed method, the motion between two frames is estimated using three points among the scan data, and refined by nonlinear optimization. We validate the accuracy of the proposed method using real images. The results show that the proposed system is a practical solution for motion estimation as well as for 3D reconstruction.
IEEE Transactions on Pattern Analysis and Machine Intelligence | 2012
Youngbae Hwang; Jun-Sik Kim; In So Kweon
By the laws of quantum physics, pixel intensity does not have a true value, but should be a random variable. Contrary to the conventional assumptions, the distribution of intensity may not be an additive Gaussian. We propose to directly model the intensity difference and show its validity by an experimental comparison to the conventional additive model. As a model of the intensity difference, we present a Skellam distribution derived from the Poisson photon noise model. This modeling induces a linear relationship between intensity and Skellam parameters, while conventional variance computation methods do not yield any significant relationship between these parameters under natural illumination. The intensity-Skellam line is invariant to scene, illumination, and even most of camera parameters. We also propose practical methods to obtain the line using a color pattern and an arbitrary image under natural illumination. Because the Skellam parameters that can be obtained from this linearity determine a noise distribution for each intensity value, we can statistically determine whether any intensity difference is caused by an underlying signal difference or by noise. We demonstrate the effectiveness of this new noise model by applying it to practical applications of background subtraction and edge detection.
computer vision and pattern recognition | 2016
Seonghyeon Nam; Youngbae Hwang; Yasuyuki Matsushita; Seon Joo Kim
Modelling and analyzing noise in images is a fundamental task in many computer vision systems. Traditionally, noise has been modelled per color channel assuming that the color channels are independent. Although the color channels can be considered as mutually independent in camera RAW images, signals from different color channels get mixed during the imaging process inside the camera due to gamut mapping, tone-mapping, and compression. We show the influence of the in-camera imaging pipeline on noise and propose a new noise model in the 3D RGB space to accounts for the color channel mix-ups. A data-driven approach for determining the parameters of the new noise model is introduced as well as its application to image denoising. The experiments show that our noise model represents the noise in regular JPEG images more accurately compared to the previous models and is advantageous in image denoising.
Computer Vision and Image Understanding | 2008
Youngbae Hwang; Jun-Sik Kim; In So Kweon
We present a new noise model for color channels for statistical change detection. Based on this noise modeling, we estimate the distribution of Euclidean distances between the pixel colors of the background image and those of the foreground image. The optimal threshold for change detection is automatically determined using the estimated distribution. We show that our noise modeling is appropriate for various color spaces. Because the detection results differ according to the color space, we utilize the expected number of error pixels to select the appropriate color space for our method. Even if we detect changes based on the optimal threshold in a properly selected color space, there will inevitably be some false classifications. To reject these erroneous cases, we adopt graph cuts that efficiently minimize the global energy while taking into account the effect of neighboring pixels. To validate the proposed method, we show experimental results for a large number of images including indoor and outdoor scenes with complex clutter.
society of instrument and control engineers of japan | 2007
Youngbae Hwang; In So Kweon; Jun-Sik Kim
Conventional edge detectors suffer from inherent image noise and threshold determination. In this paper, we propose a noble edge detector based on the noise distribution for CCD or CMOS cameras. By assuming the dominant photon noise, we model the distribution of intensity differences between two neighborhood pixels. Since it is well known that photon noise follows a Poisson distribution, we introduce a Skellam distribution, which is the difference of two Poisson random variables. We show experimentally that the Skellam distribution can be used to model the noise distribution of pixels that are captured from the same scene radiance. For estimating the noise distribution given a single pixel, we find the important property that the Skellam parameters are linearly related to the intensity value of pixels. This linearity enables us to determine noise parameters according to the intensity value. In addition, parameters of the line are preserved under illumination, scene and camera setting changes except for only a gain change. Based on the noise distributions, we calculate intensity allowances of three channels for each pixel given a confidence interval. We propose a noble edge detector by skipping a pre-processing step of conventional Gaussian smoothing which is the main obstacle for robust and accurate edge detection. If the difference of intensity exceeds the intensity allowance at least in a single channel, the in- between pixel is marked as an edge pixel. We demonstrate that without conventional Gaussian smoothing the noise-model based approach can automatically extract the fine details of image structures, such as edge and corners, independent of camera setting.
intelligent robots and systems | 2004
Youngbae Hwang; Jun-Sik Kim; In So Kweon
We present a novel change detection method using a statistical model of the image noise. Most change detection methods are based on gray-level images. However, color images can provide much richer scene information. One major problem to use the color images in change detection is how to combine three components in color space as a detection cue. We use the Euclidean color distance of three channels to measure the difference between two consecutive images. Specifically, we present a new noise model for each color channel. Through this modeling we can estimate the distribution of the Euclidean color distance for unchanged regions. We can find the optimal threshold to detect changes using this estimated distribution. Although we use the optimal threshold, inevitably there may be false classifications. To reject these erroneous cases, we adopt the graph cuts method that efficiently minimizes the global energy, which takes into account the effect of neighboring pixels.
international conference on image processing | 2014
Juhan Bae; Youngbae Hwang; Jongwoo Lim
In this paper, we propose a video stabilization method that takes advantages of both online and offline video stabilization methods in a semi-online framework. Our approach takes the fixed length incoming frames for having the advantages of offline methods with the same length of delayed results. We stabilize input frames by warping to the keyframe to increase the visual stability. For preserving user intent camera motion correctly, we determine the next keyframe update by measuring inconsistency between a current keyframe and incoming frames. Moreover, inter-frame motion smoothing by quadratic fitting bridges the keyframes smoothly for pleasant viewing experiences. Our algorithm not only handles rapid camera motion changes, but also stabilizes the input camera path smoothly in real-time. Experimental results show that the proposed algorithm is comparable to the state-of-the-art offline video stabilization methods with only fixed length of incoming frames.
international soc design conference | 2016
Sang-Seol Lee; Eunchong Lee; Youngbae Hwang; Sung-Joon Jang
The high dynamic range (HDR) has become very important because of the rapid increase in demand for a variety of applications. However, most of them were implemented by expensive systems due to the high complex computation for processing the real-time 4K UHD video. In the proposed hardware, the non-linear camera response function (CRF) with the area optimization of logarithmic computations has been applied to improve HDR quality. And, for embedding in Field Programmable Gate Array (FPGA), we implement a dedicated hardware using 4006 lookup table (LUT) and 21KB sized internal memory. The proposed architecture enables a real-time HDR processing with pipelining for a UHD video (8 Mega pixels) at 30 frames per second.