Joonki Paik

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by Joonki Paik

Способ стабилизации изображения в реальном масштабе времени

Техническая Акустика, 2006

Image Processing Apparatus and Image Processing Methods

Multisensor Super Resolution Using Directionally-Adaptive Regularization for UAV Images

Sensors, 2015

In various unmanned aerial vehicle (UAV) imaging applications, the multisensor super-resolution (... more In various unmanned aerial vehicle (UAV) imaging applications, the multisensor super-resolution (SR) technique has become a chronic problem and attracted increasing attention. Multisensor SR algorithms utilize multispectral low-resolution (LR) images to make a higher resolution (HR) image to improve the performance of the UAV imaging system. The primary objective of the paper is to develop a multisensor SR method based on the existing multispectral imaging framework instead of using additional sensors. In order to restore image details without noise amplification or unnatural post-processing artifacts, this paper presents an improved regularized SR algorithm by combining the directionally-adaptive constraints and multiscale non-local means (NLM) filter. As a result, the proposed method can overcome the physical limitation of multispectral sensors by estimating the color HR image from a set of multispectral LR images using intensity-hue-saturation (IHS) image fusion. Experimental results show that the proposed method provides better SR results than existing state-of-the-art SR methods in the sense of objective measures.

Download

Wavelength-Adaptive Dehazing Using Histogram Merging-Based Classification for UAV Images

Sensors (Basel, Switzerland), Jan 19, 2015

Since incoming light to an unmanned aerial vehicle (UAV) platform can be scattered by haze and du... more Since incoming light to an unmanned aerial vehicle (UAV) platform can be scattered by haze and dust in the atmosphere, the acquired image loses the original color and brightness of the subject. Enhancement of hazy images is an important task in improving the visibility of various UAV images. This paper presents a spatially-adaptive dehazing algorithm that merges color histograms with consideration of the wavelength-dependent atmospheric turbidity. Based on the wavelength-adaptive hazy image acquisition model, the proposed dehazing algorithm consists of three steps: (i) image segmentation based on geometric classes; (ii) generation of the context-adaptive transmission map; and (iii) intensity transformation for enhancing a hazy UAV image. The major contribution of the research is a novel hazy UAV image degradation model by considering the wavelength of light sources. In addition, the proposed transmission map provides a theoretical basis to differentiate visually important regions fr...

Download

Sensor-Based Auto-Focusing System Using Multi-Scale Feature Extraction and Phase Correlation Matching

Sensors (Basel, Switzerland), Jan 10, 2015

This paper presents a novel auto-focusing system based on a CMOS sensor containing pixels with di... more This paper presents a novel auto-focusing system based on a CMOS sensor containing pixels with different phases. Robust extraction of features in a severely defocused image is the fundamental problem of a phase-difference auto-focusing system. In order to solve this problem, a multi-resolution feature extraction algorithm is proposed. Given the extracted features, the proposed auto-focusing system can provide the ideal focusing position using phase correlation matching. The proposed auto-focusing (AF) algorithm consists of four steps: (i) acquisition of left and right images using AF points in the region-of-interest; (ii) feature extraction in the left image under low illumination and out-of-focus blur; (iii) the generation of two feature images using the phase difference between the left and right images; and (iv) estimation of the phase shifting vector using phase correlation matching. Since the proposed system accurately estimates the phase difference in the out-of-focus blurred ...

Download

Light-receiving unit for optical mouse and optical mouse having the same

Block matching-based background generation and non-rigid shape tracking for video surveillance

2007 International Conference on Wavelet Analysis and Pattern Recognition, 2007

Download

Memory-efficient H.264/AVC CAVLC for fast decoding

IEEE Transactions on Consumer Electronics, 2006

A fast decoding method is presented for memory-efficient context-based adaptive variable length c... more A fast decoding method is presented for memory-efficient context-based adaptive variable length coding (CAVLC). The CAVLC algorithm in H.264/MPEG-4 AVC significantly increased the compression ratio compared with variable length coding (VLC) of conventional video coding standards such as H.263 and MPEG-4 Visual because of adaptive use of neighboring blocks' context. Implementation of the CAVLC decoding algorithm, however, is much more complicated than existing VLC decoding methods because of frequent access to the unstructured VLC tables, adaptive switching of tables, and five syntax elements. Especially in mobile video terminals such as digital multimedia broadcasting (DMB) and digital video broadcastinghandheld (DVB-H) player, conventional CAVLC decoding algorithms result in increased power consumption due to frequent memory access. This paper presents a new CAVLC decoding method using arithmetic operations instead of the conventional table look-up method that requires a lots of memory access. Experimental results show that the proposed algorithm has 50% higher speed and 95% less memory access comparing with three conventional CAVLC algorithms, such as table look-up by sequential search, table look-up by binary search, and Moon's method 1 .

Download

Adaptive contrast enhancement using gain-controllable clipped histogram equalization

IEEE Transactions on Consumer Electronics, 2008

Histogram equalization is a simple and effective method for contrast enhancement as it can automa... more Histogram equalization is a simple and effective method for contrast enhancement as it can automatically define the intensity transformation function based on statistical characteristics of the image. However, it tends to alter the brightness of the entire image, which it is not suitable for consumer electronic products, where preservation of the original brightness is essential to avoid annoying artifacts. This paper presents a new contrast enhancement method for generalization of the existing bihistogram equalization (BHE) and recursive mean-separate histogram equalization (RMSHE) methods. The proposed method is referred to gain-controllable clipped histogram equalization (GC-CHE) to provide both histogram equalization and brightness preservation. More specifically adaptive contrast enhancement is realized by using clipped histogram equalization with controllable gain. The clipping rate is determined based on the mean brightness, and the clipping threshold is determined based on the clipping rate. The clipping rate is adaptively controlled to enhance the contrast with preserving the mean brightness. It is mathematically proven that the mean brightness of the output image converges to that of the input image with adaptive controlled. Simulation results show that the proposed GC-CHE method outperforms existing histogram-based methods, such as HE, BHE, and RMSHE, in various situations 1 .

Download

Defocus-invariant image registration for phase-difference detection auto focusing

The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014), 2014

This paper presents a defocus-invariant image registration method for measuring the shifting valu... more This paper presents a defocus-invariant image registration method for measuring the shifting value between two differently located patterns in an imaging sensor. Existing registration methods fail with unfocused images since features or regions of interest are degraded by defocus. In order to solve this problem, the proposed method consists of three stages: i) pre-generation of the set of point spread functions (PSFs) estimated in different focusing positions, ii) the geometric transformation estimation using estimated PSF data, and iii) registration using estimated transformation matrix. The proposed method improves out-of-focus degradation through estimation of PSF. For this reason, the proposed method can accurately estimate the difference of phase between two out-offocus images. Furthermore, it can be applied to phase-difference detection auto focusing, and provide accurate auto focusing performance.

Download

Gate-togate togate togate automated video tracking and location

An automated gate-to-gate, airport, video tracking system is proposed and simulated using a virtu... more An automated gate-to-gate, airport, video tracking system is proposed and simulated using a virtual threedimensional (3D) scale model of the airport’s main concourse. The proposed research interactively combines two state-of-the-art technologies: (i) video analysis and processing and (ii) 3D visualization and simulation. The video tracking algorithm, which is realized by technology (i), has been developed with emphasis on seamless handover of a moving object using multiple cameras. The simulation environment was created based on Knoxville’s McGhee-Tyson airport using Envision software by Deneb.

Download

Coarse to Fine: Progressive and Multi-Task Learning for Salient Object Detection

Most deep learning-based salient object detection (SOD) methods tried to manipulate the convoluti... more Most deep learning-based salient object detection (SOD) methods tried to manipulate the convolution block to effectively capture the context of object. In this paper, we propose a novel method, called progressive and mutl-task learning scheme, to extract the context of object by only manipulating the learning scheme without changing the network architecture. The progressive learning scheme is a method to grow the decoder progressively in the train phase. In other words, starting from easier low-resolution layers, it gradually adds high-resolution layers. Although the progressive learning successfully captures the context of object, its output boundary tends to be rough. To solve this problem, we also propose a multi-task learning (MTL) scheme that processes the object saliency map and contour in a single network jointly. The proposed MTL scheme trains the network in an edge-preserved direction through an auxiliary branch that learns contours. The proposed a learning scheme can be co...

Download

Surface modeling using multi-view range and color images

Integrated Computer-Aided Engineering

This paper presents a framework of surface modeling from multi-view range and color images. The i... more This paper presents a framework of surface modeling from multi-view range and color images. The input to the algorithms are pairs of triangle meshes and color images, and each pair is obtained by a single-view scanning. In the proposed framework, the triangle meshes from raw data are first processed by the novel surface denoising algorithm based on area decreasing flow, which avoids the difficulty in curvature estimation of mean curvature flow. The proposed adaptive triangle mesh smoothing algorithm is based on crease edge strength of each vertex and uses tensor voting of the normal vector field inside a geodesic window. Surfaces from multiple views are then integrated into a single 3D model. Two integration approaches are discussed, which are based on mesh zippering and implicit surface fusion, respectively. Color images are incorporated to generate textured models. The reconstructed surfaces are finally post-processed by volumetric smoothing and filling the holes. Experimentation using two different range scanners shows that the proposed surface modeling framework is robust and flexible in processing data from different types of range scanners.

Download

Computational Approach to Color Overlapped Integral Imaging for Depth Estimation

IEIE Transactions on Smart Processing and Computing, 2014

A computational approach to depth estimations using a color over lapped integral imaging system i... more A computational approach to depth estimations using a color over lapped integral imaging system is presented. The proposed imaging system acquires multiple color images simultaneously through a single lens with an array of multiple pinholes that are distributed around the optical axis. This paper proposes a computational model of the relationship between the real distance of an object and the disparity among different color images. The proposed model can serve as a computational basis of a single camera-based depth estimation.

Download

Gate-to-gate automated video tracking and location

An automated gate-to-gate, airport, video tracking system is proposed and simulated using a virtu... more An automated gate-to-gate, airport, video tracking system is proposed and simulated using a virtual threedimensional (3D) scale model of the airport's main concourse. The proposed research interactively combines two state-of-the-art technologies: (i) video analysis and processing and (ii) 3D visualization and simulation. The video tracking algorithm, which is realized by technology (i), has been developed with emphasis on seamless handover of a moving object using multiple cameras. The simulation environment was created based on Knoxville's McGhee-Tyson airport using Envision software by Deneb.

Download

Digital image stabilization using binary edge data

Motion Deblurring Using Appearance Information of an Arbitary Point

Itc Cscc International Technical Conference on Circuits Systems Computers and Communications, Jul 1, 2007

Camera panning or shaking can degrade the quality of acquired images. Removal of such motion blur... more Camera panning or shaking can degrade the quality of acquired images. Removal of such motion blur is typical an ill-posed problem. The existing blind deconvolution methods based on frequency-domain constraints have difficulties in seriously blurred images or overly simplified parametric forms. In order to solve this problem, we present a novel deblurring method using appearance information in the regularization space. An arbitrary point is used to estimate the point spread function (PSF) that defines the extent and the direction of motion blur. The proposed method can be applied in a variety of digital photographs because it uses a simple, robust estimation algorithm.

Apparatus and Method for Enhancing Image Quality of Image Captured by Using Multiple Color-Filter Aperture

Image processing apparatus and systems using estimated point spread function

Digital zooming circuit with compensation of the edge degradation

Joonki Paik

Uploads

Papers by Joonki Paik

Log In