• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.800-816
• /
• 2018

In recent years, video surveillance research has been able to recognize various behaviors of pedestrians and analyze the overall situation of objects by combining image analysis technology and deep learning method. Human Activity Recognition (HAR), which is important issue in video surveillance research, is a field to detect abnormal behavior of pedestrians in CCTV environment. In order to recognize human behavior, it is necessary to detect the human in the image and to estimate the pose from the detected human. In this paper, we propose a novel approach for 2D Human Pose Estimation based on object detection using RGB-D information. By adding depth information to the RGB information that has some limitation in detecting object due to lack of topological information, we can improve the detecting accuracy. Subsequently, the rescaled region of the detected object is applied to ConVol.utional Pose Machines (CPM) which is a sequential prediction structure based on ConVol.utional Neural Network. We utilize CPM to generate belief maps to predict the positions of keypoint representing human body parts and to estimate human pose by detecting 14 key body points. From the experimental results, we can prove that the proposed method detects target objects robustly in occlusion. It is also possible to perform 2D human pose estimation by providing an accurately detected region as an input of the CPM. As for the future work, we will estimate the 3D human pose by mapping the 2D coordinate information on the body part onto the 3D space. Consequently, we can provide useful human behavior information in the research of HAR.

• Korean Journal of Remote Sensing
• /
• v.27 no.6
• /
• pp.703-715
• /
• 2011

Forests have been considered one of the most important ecosystems on the earth, affecting the lives and environment. The sustainable forest management requires accurate and timely information of forest and tree parameters. Appropriately interpreted remotely sensed imagery can provide quantitative data for deriving forest information temporally and spatially. Especially, analysis of individual tree detection and crown delineation is significant issue, because individual trees are basic units for forest management. Individual trees in aerial imagery have reflectance characteristics according to tree species, crown shape and hierarchical status. This study suggested a method that identified individual trees and delineated crown boundaries through adopting gradient method algorithm to amplified greenness data using red and green band of aerial imagery. The amplification of specific band value improved possibility of detecting individual trees, and gradient method algorithm was performed to apply to identify individual tree tops. Additionally, tree crown boundaries were explored using spectral intensity pattern created by geometric characteristic of tree crown shape. Finally, accuracy of result derived from this method was evaluated by comparing with the reference data about individual tree location, number and crown boundary acquired by visual interpretation. The accuracy ($\hat{K}$) of suggested method to identify individual trees was 0.89 and adequate window size for delineating crown boundaries was $19{\times}19$ window size (maximum crown size: 9.4m) with accuracy ($\hat{K}$) at 0.80.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.2185-2191
• /
• 2015

With the advance of the environment where we can get various multimedia contents, adult image detection has become an important issue these days. In this paper, we suggest a method of robustly detecting navel areas from input images which can be usefully utilized in adult image detection. The suggested algorithm first extracts face regions and extracts candidate nipple areas using a nipple map. Our method then selects only actual nipple regions by filtering candidate areas with geometrical features and an average nipple filter. Subsequently, the method robustly detects navel areas by using the structural relation with the nipple areas and applying edge and saturation images. Experimental results show that the suggested algorithm can effectively detect navel regions.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.47-55
• /
• 2020

In this paper, we propose one stage multi-scale face detector based Fully Convolution Network using anchor free method. Recently almost all state-of-the-art face detectors which predict location of faces using anchor-based methods rely on pre-defined anchor boxes. However this face detectors need to hyper-parameters and additional computation in training. The key idea of the proposed method is to eliminate hyper-parameters and additional computation using anchor free method. To do this, we apply two ideas. First, by eliminating the pre-defined set of anchor boxes, we avoid the additional computation and hyper-parameters related to anchor boxes. Second, our detector predicts location of faces using multi-feature maps to reduce foreground/background imbalance issue. Through Quantitative evaluation, the performance of the proposed method is evaluated and analyzed. Experimental results on the FDDB dataset demonstrate the effective of our proposed method.

• Smart Structures and Systems
• /
• v.15 no.6
• /
• pp.1583-1600
• /
• 2015

When natural disasters occur, including earthquakes, tsunamis, and debris flows, they are often accompanied by various types of damages such as the collapse of buildings, broken bridges and roads, and the destruction of natural scenery. Natural disaster detection and warning is an important issue which could help to reduce the incidence of serious damage to life and property as well as provide information for search and rescue afterwards. In this study, we propose a novel computer vision technique for debris flow detection which is feature-based that can be used to construct a debris flow event warning system. The landscape is composed of various elements, including trees, rocks, and buildings which are characterized by their features, shapes, positions, and colors. Unlike the traditional methods, our analysis relies on changes in the natural scenery which influence changes to the features. The "background module" and "monitoring module" procedures are designed and used to detect debris flows and construct an event warning system. The multi-criteria decision-making method used to construct an event warring system includes gradient information and the percentage of variation of the features. To prove the feasibility of the proposed method for detecting debris flows, some real cases of debris flows are analyzed. The natural environment is simulated and an event warning system is constructed to warn of debris flows. Debris flows are successfully detected using these two procedures, by analyzing the variation in the detected features and the matched feature. The feasibility of the event warning system is proven using the simulation method. Therefore, the feature based method is found to be useful for detecting debris flows and the event warning system is triggered when debris flows occur.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.8C
• /
• pp.748-757
• /
• 2002

Cyber-terror trials are increased in nowadays and these attacks are commonly using security vulnerability and information gathering method by variable services grew by the continuous development of Internet Technology. IDS's application environment is affected by this increasing Cyber Terror. General Network based IDS detects intrusion by signature based Intrusion Detection module about inflowing packet through network devices. Up to now security in network is commonly secure host, an regional issue adopted in special security system but these system is vulnerable intrusion about the attack in globally connected Internet systems. Security mechanism should be produced to expand the security in whole networks. In this paper, we analyzer the DARPA's program and study Infusion Detection related Technology. We design policy security framework for policy enforcing in whole network and look at the modules's function. Enforcement of security policy is acted by Intrusion Detection system on gateway system which is located in network packet's inflow point. Additional security policy is operated on-line. We can design and execute central security policy in managed domain in this method.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.10
• /
• pp.5195-5199
• /
• 2012

Objectives: Global cancer statistical data show that India has one of the highest incidence rates of oral cancer worldwide. Early detection is extremely important as it results in lower morbidity and death rates. The present study was undertaken to assess awareness of oral cancer and knowledge of its early signs and risk factors in the general public of the semi-urban Gorakhpur area of Uttar Pradesh (India). It was also intended to educate the same population for early detection by increasing their ability to recognize signs and risk factors. Method: A questionnaire-based household survey was conducted over a period of one month in different parts of Gorakhpur district, a region where tobacco use is apparently very high. A total of 2,093 persons participated in the survey. The collected data were analyzed using SPSS software to assess and associate oral cancer awareness with the prevalence, and abstract risk factors, as well as other confounding variables. Results: The general awareness, knowledge of signs and risk factors of oral cancer were found to be proportionate to the literacy level with the highest rate of awareness being among high school and graduates and lowest among illiterates. It was also observed that on most of these dimensions the younger age groups (<30 years) were significantly more knowledgeable. Conclusion: Overall, the awareness of oral cancer in the high-risk population of Gorakhpur was not satisfactory, pointing to a need for further dissemination of information on this issue and its associated risks. This is especially important for the youngsters, as this may possibly help them keep away from the deleterious habit of tobacco indulgence in any form. If necessary risk factor cessation counselling should be provided.

• Korean Journal of Biological Psychiatry
• /
• v.20 no.4
• /
• pp.119-128
• /
• 2013

Objectives Memory impairment is a very important mental health issue for elderly and adults. Mild cognitive impairment (MCI) is a prodromal stage of Alzheimer's disease (AD). Early detection of the prodromal stage of patients with AD is an important topic of interest for both mental health clinicians and policy makers. Methods Electroencephalograpgy (EEG) has been used as a possible biological marker for patients with MCI, and AD. In this review, we will summarize the clinical implications of EEG and ERP as a biological marker for AD and MCI. Results EEG power density, functional coupling, spectral coherence, synchronization, and connectivity were analyzed and proved their clinical efficacy in patients with the prodromal stage of AD. Serial studies on late event-related potentials (ERPs) were also conducted in MCI patients as well as healthy elders. Even though these EEG and ERP studies have some limitations for their design and method, their clinical implications are increasing rapidly. Conclusion EEG and ERP can be used as biological markers of AD and MCI. Also they can be used as useful tools for early detection of AD and MCI patients. They are useful and sensitive research tools for AD and MCI patients. However, some problems remain to be solved until they can be practical measures in clinical setting.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.136-141
• /
• 2012

One of the main reasons for serious road accidents is driving while drowsy. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. One of the effective signals is to measure electroencephalogram (EEG) signals and electrooculogram (EOG) signals. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, drowsiness, sleepiness. This paper proposes a neural-network-based drowsiness detection system using Linear Predictive Coding (LPC) coefficients as feature vectors and Multi-Layer Perceptron (MLP) as a classifier. Samples of EEG data from each predefined state were used to train the MLP program by using the proposed feature extraction algorithms. The trained MLP program was tested on unclassified EEG data and subsequently reviewed according to manual classification. The classification rate of the proposed system is over 96.5% for only very small number of samples (250ms, 64 samples). Therefore, it can be applied to real driving incident situation that can occur for a split second.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.364-367
• /
• 2008

Earthwork is very equipment-intensive task and researches related to automated excavation have been conducted. There is an issue to secure the safety for an automated excavating system. Therefore, this paper focuses on how to improve safety for semi- or fully-automated backhoe excavation. The primary objective of this research is to develop object detection algorithm for automated safety system in excavation work. In order to satisfy the research objective, a diverse sensing technologies are investigated and analysed in terms of functions, durability, and reliability and verified its performance by several tests. The authors developed the objects detecting algorithm for user interface program using laser sensor. The results of this study would be the basis for developing the automated object detection system.