• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3712-3729
• /
• 2020

Smoke detection is helpful for early fire detection. With its large coverage area and low cost, vision-based smoke detection technology is the main research direction of outdoor smoke detection. We propose a two-stage smoke detection method combined with block Deep Normalization and Convolutional Neural Network (DNCNN) and visual change image. In the first stage, each suspected smoke region is detected from each frame of the images by using block DNCNN. According to the physical characteristics of smoke diffusion, a concept of visual change image is put forward in this paper, which is constructed by the video motion change state of the suspected smoke regions, and can describe the physical diffusion characteristics of smoke in the time and space domains. In the second stage, the Support Vector Machine (SVM) classifier is used to classify the Histogram of Oriented Gradients (HOG) features of visual change images of the suspected smoke regions, in this way to reduce the false alarm caused by the smoke-like objects such as cloud and fog. Simulation experiments are carried out on two public datasets of smoke. Results show that the accuracy and recall rate of smoke detection are high, and the false alarm rate is much lower than that of other comparison methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.49-57
• /
• 2017

IoT can be connected through a single network not only objects which can be connected to existing internet but also objects which has communication capability. This IoT environment will be a huge change to the existing communication paradigm. However, the big security problem must be solved in order to develop further IoT. Security mechanisms reflecting these characteristics should be applied because devices participating in the IoT have low processing ability and low power. In addition, devices which perform abnormal behaviors between objects should be also detected. Therefore, in this paper, we proposed D-IDS technique for efficient detection of malicious attack nodes between devices participating in the IoT. The proposed technique performs the central detection and distribution detection to improve the performance of attack detection. The central detection monitors the entire network traffic at the boundary router using SVM technique and detects abnormal behavior. And the distribution detection combines RSSI value and reliability of node and detects Sybil attack node. The performance of attack detection against malicious nodes is improved through the attack detection process. The superiority of the proposed technique can be verified by experiments.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.140-145
• /
• 2009

Significant attention has recently been drawn to human robot interaction system that uses face detection technology. The most conventional face detection methods have applied under pixel domain. These pixel based face detection methods require high computational power. Hence, the conventional methods do not satisfy the robot environment that requires robot to operate in a limited computing process and saving space. Also, compensating the variation of illumination is important and necessary for reliable face detection. In this paper, we propose the illumination invariant face detection that is performed under the compressed domain. The proposed method uses color balancing module to compensate illumination variation. Experiments show that the proposed face detection method can effectively increase the face detection rate under existing illumination.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.2
• /
• pp.115-124
• /
• 2020

Due to the increasing threats of submarines from North Korea and other countries, ROK Navy should improve the detection capability of submarines. There are two ways to detect submarines : acoustic detection and non-acoustic detection. Since the acoustic-detection way has limitations in spite of its usefulness, it should have the complementary way. The non-acoustic detection is the way to detect submarines which are operating mast sets such as periscopes and snorkels by non-acoustic sensors. So, this paper proposes a new submarine non-acoustic detection model using an ensemble of Convolutional Neural Network models in order to automate the non-acoustic detection. The proposed model is trained to classify targets as 4 classes which are submarines, flag buoys, lighted buoys, small boats. Based on the numerical study with 10,287 images, we confirm the proposed model can achieve 91.5 % test accuracy for the non-acoustic detection of submarines.

• Journal of Satellite, Information and Communications
• /
• v.12 no.4
• /
• pp.26-33
• /
• 2017

A drone performs a mission through remote control or automatic control, which uses wireless communications technology. Recently the increasing use of drones, the drone signal RF detection is necessary. In this paper, we propose an efficient dron RF detection method through simulations considering Wi-Fi, Bluetooth and dedicated protocol dron communication method in ISM(Industry Science Medical) band.. After configuring an environment where a common terminal and a drone signal are mixed, a general terminal and a drone signal are distinguished from each other by using a RF characteristic according to a dron movement. The proposed drone RF detection method is the WRMD(Windowed RSSI Moving Detection) operation and the Doppler frequency identification method. The simulation environments consist to mixed for two signals and four signals. We analysis the performance to proposed drone RF detection technique thorough detection rate.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.83-90
• /
• 2015

Almost of current Automatic Incident Detection(AID) algorithms involve the vulnerability that detects the traffic accident in open road or in tunnel as the traffic jam not as the traffic accident. This paper proposes the improved accident detection algorithm to enhance the detection probability based on accident detection algorithms applied in open roads. The improved accident detection algorithm provides the preliminary judgment of potential accident by detecting the stopped object by Gaussian Mixture Model. Afterwards, it measures the detection area is divided into blocks so that the occupancy rate can be determined for each block. All experimental results of applying the new algorithm on a real incident was detected image without error.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.702-705
• /
• 2006

Change detection is a core function of remote sensing. It can be widely used in public services such as land monitoring, damage assessment from disaster, analysis of city growth, etc. However, it seems that the change detection using satellite imagery has not been fully used in public services. For the person who is in charge of public services, it seems not to be ease to implement the change detection because various functions are combined into it. So, to promote the use of the change detection in public services, the standard, the process and the method for the change detection in public services should be established. And the software which supports that will be very useful. This study aims to promote the use of satellite imagery in public services by building up the change detection process which are suitable for general public services and developing the change detection software to support the process. The software has been developed using ETRI Components for Satellite Image Processing to support the interoperability with other GIS software.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.321-327
• /
• 2012

This paper presents a comparative analysis on three different types of performance indices of obstacle detection for an overlapped ultrasonic sensor ring. Due to beam overlap, the entire sensing zone of each ultrasonic sensor can be divided into three smaller sensing subzones, which leads to significant reduction of positional uncertainty in obstacle detection. First, the positional uncertainty in obstacle detection is expressed in terms of the area of a sensing subzone, and type 1 performance index is then defined as the area ratio of side and center sensing subzones. Second, based on the area of a sensing subzone, type 2 performance index is defined taking into account the size of the entire range of obstacle detection as well as the degree of the positional uncertainty in obstacle detection. Third, the positional uncertainty in obstacle detection is now expressed in terms of the length of the uncertainty arc spanning a sensing subzone, and type 3 performance index is then defined as the average value of the uncertainty arc lengths over the entire range of obstacle detection. Fourth, using a commercial low directivity ultrasonic sensor, the changes of three different performance indices depending on the parameter of an overlapped ultrasonic sensor ring are examined and compared.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.122-128
• /
• 2013

This paper presents a detection algorithm that accurately finds the active area of a video player on monitors or smart TVs. Unlike the previous approaches, temporal difference-based detection algorithms or hooking programs, the proposed detection algorithm can locate the active video player by using the spatial and temporal correlation and a corner detection filter. First, an initial location of the video player is found using conventional temporal difference-based detection. Then, starting from the initial location, the four corners of the active video player are detected by the spatial edge information and the corner detection filter. The experimental results show that proposed algorithm provides fast detection speed and high accuracy.