Joong-Hwan Baek

Korea Aerospace University | KAU · School of Electronics, Telecommunication and Computer Engineering

To provide accessible, intelligent, and efficient remote access such as the internet of things, rehabilitation, autonomous driving, virtual games, and healthcare, human action recognition (HAR) has gained much attention among computer vision researchers. Several methods have already been addressed to ensure effective and efficient action recognitio...

Depth estimation using monocular camera sensors is an important technique in computer vision. Supervised monocular depth estimation requires a lot of data acquired from depth sensors. However, acquiring depth data is an expensive task. We sometimes cannot acquire data due to the limitations of the sensor. View synthesis-based depth estimation resea...

The lifestyle of humans has changed noticeably since the contagious COVID-19 disease struck globally. People should wear a face mask as a protective measure to curb the spread of the contagious disease. Consequently, real-world applications (i.e., electronic customer relationship management) dealing with human ages extracted from face images must m...

Nowadays, the demand for human–machine or object interaction is growing tremendously owing to its diverse applications. The massive advancement in modern technology has greatly influenced researchers to adopt deep learning models in the fields of computer vision and image-processing, particularly human action recognition. Many methods have been dev...

Object tracking is a technique for tracking a specific object appearing in a video sequence while observing its features or changes. Recently, many algorithms showing high performance have emerged by applying the Siamese network to the object tracking field. A Siamese network is designed to learn the similarity between two images. In object trackin...

The COVID-19 pandemic markedly changed the human shopping nature, necessitating a contactless shopping system to curb the spread of the contagious disease efficiently. Consequently, a customer opts for a store where it is possible to avoid physical contacts and shorten the shopping process with extended services such as personalized product recomme...

A colonoscopy is a medical examination used to check disease or abnormalities in the large intestine. If necessary, polyps or adenomas would be removed through the scope during a colonoscopy. Colorectal cancer can be prevented through this. However, the polyp detection rate differs depending on the condition and skill level of the endoscopist. Even...

Human activity recognition has become a significant research trend in the fields of computer vision, image processing, and human–machine or human–object interaction due to cost-effectiveness, time management, rehabilitation, and the pandemic of diseases. Over the past years, several methods published for human action recognition using RGB (red, gre...

In this study, authors aimed to predict the gender of a customer with face mask to manage the customer data, targeted advertisement, and future of retail. Amid the COVID-19 pandemic situation, a customer must wear a face mask, avoid contacts with store staffs and should stay for short period of times while shopping. Smart store can meet the require...

Human action recognition has turned into one of the most attractive and demanding fields of research in computer vision and pattern recognition for facilitating easy, smart, and comfortable ways of human-machine interaction. With the witnessing of massive improvements to research in recent years, several methods have been suggested for the discrimi...

This paper proposes a novel complete navigation system for autonomous flight of small unmanned aerial vehicles (UAVs) in GPS-denied environments. The hardware platform used to test the proposed algorithm is a small, custom-built UAV platform equipped with an onboard computer, RGB-D camera, 2D light detection and ranging (LiDAR), and altimeter. The...

Human gender is deemed as a prime demographic trait due to its various usage in the practical domain. Human gender classification in an unconstrained environment is a sophisticated task due to large variations in the image scenarios. Due to the multifariousness of internet images, the classification accuracy suffers from traditional machine learnin...

] Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by ma...

A progressive motile sperm sorting device with a diffuser-type microfluidic channel is proposed to improve fertilization in assisted reproductive technologies. When sperm cells swim against a fluid flow, they are positioned according to their motility in specific channel zones. A numerical simulation is carried out in a meso-sized diffuser-type cha...

In this paper, we propose an algorithm for on-line signature recognition using fingertip point in the air from the depth image acquired by Kinect. We extract 10 statistical features from X, Y, Z axis, which are invariant to changes in shifting and scaling of the signature trajectories in three-dimensional space. Artificial neural network is adopted...

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and util...

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which lo...

In this paper, we propose an on-line signature recognition algorithm using fingertip point in the air from the depth image acquired by Kinect. We use ten statistical features for each X, Y, Z axis to react to changes in Shifting and Scaling of the signature trajectories in three-dimensional space. Artificial Neural Network is a machine learning alg...

In this paper, we propose a ultra sound inspection technique for automatic defect detection and classification in aircraft composite materials. Using local maximum values of ultra sound wave, we choose peak values for defect detection. Distance data among peak values are used to construct histogram and to determine surface and back-wall echo from t...

Recently UAV(unmanned aerial vehicle) is frequently used not only for military purpose but also for civil purpose. UAV automatically navigates following the coordinates input in advance using GPS information. However it is impossible when GPS cannot be received because of jamming or external interference. In order to solve this problem, we propose...

The task of 3D gesture recognition for controlling equipments is highly challenging due to the propagation of 3D smart TV recently. In this paper, the AdaBoost algorithm is applied to 3D gesture recognition by using Kinect sensor. By tracking time interval trajectory of hand, wrist and arm by Kinect, AdaBoost algorithm is used to train and classify...

In this paper, we proposed an algorithm for real-time lane detecting against luminance variation using morphological image processing and edge-based region segmentation. In order to apply the most appropriate threshold value, the adaptive threshold was used in every frame, and perspective transform was applied to correct image distortion. After tha...

In this paper, we propose Modified Multi CAMShift Algorithm based on Kalman filter and Weighted Search Windows(KWMCAMShift) that extracts skin color area and tracks several human body parts for real-time human tracking system. We propose modified CAMShift algorithm that generates background model, extracts skin area of hands and head, and tracks th...

Effective perimeter protection mechanisms for industrial sites and critical infrastructure must contend with a large variety of potential threats as well as with the fact that normal site activity can be both complex and diverse. This paper documents the development of a system level approach capable of functioning under such challenging conditions...

form only given. The rapid evolution of tools and software systems to design experiments, automatically monitor, collect and warehouse large amounts of data, from applications such as life sciences and industrial processes has resulted in a new paradigm shift. This change of paradigm is so fast that some of the practices for optimization and manage...

Object classification in computer vision is the task of classifying a given object in an image or video sequence to one of a set of predefined object categories. There are two main factors which affect the performance of object classification. These are image representation and classification. We investigate object classification using visual featu...

In this paper, we propose a fast object classification method based on texture and color information for video surveillance. We take the advantage of local patches by extracting SURF and color histogram from images. SURF gives intensity content information and color information strengthens distinctiveness by providing links to patch content. We ach...

In this paper, we propose Modified Multi CAMShift Algorithm(Modified Multi Continuously Adaptive Mean Shift Algorithm) that extracts skin color area and tracks several human body parts for real-time human tracking system. Skin color area is extracted by filtering input image in predefined RGB value range. These areas are initial search windows of h...

Recently, due to the development of mobile phone and supply of smart phone, many contents have been developed. Especially, since the small-sized cameras are equiped in mobile devices, people are interested in the image based contents development, and it also becomes important part in their practical use. Among them, the character recognition system...

Markerless augmented reality system must have the capability to recognize and match natural objects both in indoor and outdoor environment. In this paper, a novel approach is proposed for extracting features and recognizing natural objects using visual descriptors and codebooks. Since the augmented reality applications are sensitive to speed of ope...

This paper presents a simple and robust face detection algorithm that can be utilized to video summary. Because the characteristic of the face can be changed from unexpected condition like as shadows or lighting, we firstly process the illumination-compensation for maintaining face components. We then analyze color-based face region in YCbCr space...

In this paper, we propose an object recognition technique for implementing marker less augmented reality. Scale Invariant Feature Transform (SIFT) is used for finding the local features from object images. These features are invariant to scale, rotation, translation, and partially invariant to illumination changes. Extracted Features are distinct a...

Genetic screen has been facilitating molecular geneticists to analyze mutants that produce certain phenotypes. However traditional methods for behavioral phenotype screen of mutant Caenorhabditis elegans rely on human observers and therefore are subjective and imprecise. This work dedicates a model to quantify and analyze the worm behavior using au...

Distinctive Behavioral Phenotypes are defined as those exclusive behaviors that a species has yet others do not. It has facilitated the genetic analysis of many important aspects of nervous system function and development in the nematode such as Caenorhabditis elegans (C.elegans). Although a large number of distinctive phenotypes can be distinguish...

We present a novel method for face detection and recognition methods applicable to video retrieval. The person matching efficiency largely depends on how robustly faces are detected in the video frames. Face regions are detected in video frames using viola-jones features boosted with the Adaboost algorithm After face detection, PCA (Principal Compo...

This paper presents a simple and robust face detection algorithm that can be utilized to video summary. Because the characteristic of the face can be change from unexpected condition like as shadows or lighting, we firstly process the illumination-compensation for maintaining face components. And then, we analyze color-based face region in YCbCr sp...

There are several important representative features in music. Among them beat is highly distinguishable one. Based on the pattern of beats' appearance in the music, we propose a music identification method that can be used for background music retrieval from video. In this paper, a music signal is primarily segmented into a number of small frames i...

In this paper, we propose a novel navigation method combined limit-cycle method and the vector field method for navigating a mobile robot with avoiding unexpected obstacles in the dynamic environment. The limit-cycle method is applied to avoiding obstacles placed in front of the robot and the vector field method is applied to avoiding obstacles pla...

Nematodes are primitive creatures that are endangering and devouring many of the essential resources beneficial to human beings. For effective inspection and quarantine, we have devised an image based system for quantitatively characterizing and identifying nematodes, and achieved average successful identification rate of 71.2% for the Uncoordinate...

In this paper, we propose a system to categorize audio in 7 classes. For classification features, we use the mean and variance of RMS, ZCR, fundamental frequency and frequency peak which are extracted from every frame of 25ms length. In addition to the audio content classification, we also perform speaker identification with the voice sequences ext...

In this paper, we propose a moving object tracking algorithm by using motion estimation in UAV(Unmanned Aerial Vehicle) video. Proposed algorithm is based on generation of initial image from detected reference image, and tracking of moving object under the time-varying image. With a series of this procedure, tracking process is stable even when the...

Nematodes are primitive organisms which nonetheless devour many of the essential resources that are critical for human beings. For effective and quick inspection and quarantine, we propose a general image based system for quantitatively characterizing and identifying nematodes. We also describe the key methods ranging from gray level image acquisit...

In this paper, an efficient and robust scene change detection algorithm is proposed by using low-level audiovisual features and several classification methods. The proposed algorithm consists of three stages. The first stage is shot boundary detection by using Support Vector Machine (SVM) and the second stage is the scene boundary detection using...

Scene boundary detection is an essential research in content-based video summary, retrieval, and browsing. In this paper, we present an efficient and robust scene extraction algorithm. The proposed algorithm consists of three stages. The first stage is shot boundary detection, and the second stage is the musical scene boundary detection through det...

Scene boundary detection is an essential research field in content-based video summary, retrieval, and browsing. In this paper, we propose an efficient and robust scene extraction algorithm by using both video and audio information. The proposed algorithm consists of three stages: shot boundary detection, scene boundary detection, and scene boundar...

Motion estimation is the biggest part of any video encoding system since it could significantly affect the encoding time and output quality. Until now, several motion estimation algorithms that have the fast motion estimation and a good PSNR are proposed. However these are not considered an embedded system processor using SDRAM as a video frame mem...

Genetic analysis of nervous system function relies on the rigorous description of behavioral phenotypes. However, standard methods for classifying the behavioral patterns of mutant Caenorhabditis elegans rely on human observation and are therefore subjective and imprecise. Here we describe the application of machine learning to quantitatively defin...

Caenorhabditis (C.) elegans is often used in genetic analysis in neuroscience because it has simple model organisms; an adult hermaphrodite contains only 302 neurons. We use an automated tracking system, which makes it possible to measure the rate and direction of movement for each worm and to compute the frequency of reversals in direction. In thi...

Because of simple model organisms, Caenorhabditis (C.) elegans is often used in genetic analysis in neuroscience. The classification and analysis of C. elegans was previously performed subjectively. So the result of classification is not reliable and often imprecise. For this reason, automated video capture and analysis systems appeared. In this pa...

In this paper, an automatic traffic flow measuring system and a real-time image processing algorithm have been developed. The picture of moving vehicles taken by an industrial television (ITV) camera are digitized into sample points in odd ITV frames and the points are processed in even ITV frames by a personal computer. We detect the presence of v...

We propose an abrupt shot change detection method using multiple features and classification tree. Typical shot change detection algorithms have usually used single feature obtained between consecutive frames, and the shot change is determined with only one fixed threshold in whole video sequences. However, the contents of the video frames at shot...

In this paper, we introduce a computer vision system for automatic classification and clustering of C. elegans according to their behavioral phenotypes. We extract three kinds of features such as worm movement, body size, and body shape. A total of 117 features are extracted for each worm. Then the features are used to build an optimal classificati...

In this paper, we discuss recovery schemes for errors occurring when image data encoded with variable length coding (VLC) is transmitted through additive white Gaussian noise (AWGN) and multiple-access interference in direct sequence code division multiple access (DS/CDMA) systems. VLC such as JPEG is so sensitive to channel errors that severe degr...

Mutants with abnormal patterns of locomotion, also known as uncoordinated (Unc) mutants, have facilitated the genetic dissection of many important aspects of nervous system function and development in the nematode Caenorhabditis elegans. Although a large number of distinct classes of Unc mutants can be distinguished by an experienced observer, prec...

As the number of autonomous vehicles is increased, drivers are trending toward constant interests in detecting distance between vehicles in close-range and maintaining the distance between forward and backward vehicles for drivers' safety. In this paper, we propose a method of detecting the distance between two vehicles by computing the disparity o...

One of the most important problems in time-varying image sequences is the automatic target tracking. This paper proposes a position prediction and tracking technique of moving object using fuzzy prediction. First, the object is segmented from background of the image using accumulative difference image technique. Then centroid of the segmented objec...

Instrument flight simulators are used for training the interpretation and operation techniques for all kinds of aircraft instruments, cockpit procedures, etc., in order that pilots cope with the situations which can be occurred in actual flight. However, the simulators developed so far are concerned about operating in same environment to actual air...

In this paper, we propose an AVLS(Automatic Vehicle Location System) using the DSRC(Dedicated Short Range Communication) which adopts a radio communication tool between RSE(Road-Side Equipment) and OBE(On-Board Equipment) on a vehicle and uses the ISM bandwidth of 5.8GHz radio frequency. Typical AVLS uses the sensors for detecting the vehicle, but...

Feature extraction is the most important phase in object recognition because accuracy of the system relies on how well the features are extracted. In this paper a new parallel extended local feature extraction method is proposed which can be implemented on a distributed memory machine. In order to reduce the complexity in the extended local feature...

We propose a new occluded object recognition method using extended local features and hashing. First we present some methods for extracting the extended local features such as corners, arcs, parallel-lines, and corner-arcs from the preprocessed images. Then we construct the knowledge-base using hashing, which can reduce the searching time significa...

First Page of the Article

Content-based video indexing and retrieval algorithms are presented in this paper that aim at temporally indexing a video sequence according to actors. Our system splits a video into a sequence of a few representative frames. We use color information and then SGLD matrix on the representative frames for face region detection. Detected faces are use...

Genetic analysis of nervous system function relies on the rigorous description of animal behaviors. However, standard methods for classifying the behavioral patterns of mutant Caenorhabditis elegans (a microscopic worm) rely on human observation and are therefore subjective and imprecise. Here we describe the application of machine learning and ima...