• 대한임베디드공학회논문지
• /
• 제12권4호
• /
• pp.231-238
• /
• 2017

Detecting small infrared targets from the low-SCR images at a long distance is very hard. The previous Local Contrast Method (LCM) algorithm based on the human visual system shows a superior performance of detecting small targets by a background suppression technique through local contrast measure. However, its slow processing speed due to the heavy multi-scale processing overhead is not suitable to a variety of real-time applications. This paper presents a lightweight real-time small target detection algorithm, called by the Improved Selective Local Contrast Method (ISLCM), to reduce the scale-invariant computational overhead. The proposed ISLCM applies the improved local contrast measure to the predicted selective region so that it may have a comparable detection performance as the previous LCM while guaranteeing low scale-invariant computational load by exploiting both adaptive scale estimation and small target feature feasibility. Experimental results show that the proposed algorithm can reduce its computational overhead considerably while maintaining its detection performance compared with the previous LCM.

• 한국정밀공학회지
• /
• 제31권3호
• /
• pp.233-241
• /
• 2014

This paper contributes to development of a new method for detecting rear-side vehicles and estimating the positions for blind spot region or providing the lane change information by using vision systems. Because the real image acquired during car driving has a lot of information including the target vehicle and background image as well as the noises such as lighting and shading, it is hard to extract only the target vehicle against the background image with satisfied robustness. In this paper, the target vehicle has been detected by repetitive image processing such as sobel and morphological operations and a Kalman filter has been also designed to cancel the background image and prevent the misreading of the target image. The proposed method can get faster image processing and more robustness rather than the previous researches. Various experiments were performed on the highway driving situations to evaluate the performance of the proposed algorithm.

• 한국지진공학회논문집
• /
• 제25권4호
• /
• pp.161-168
• /
• 2021

Existing old reinforced concrete buildings could be vulnerable to earthquakes because they were constructed without satisfying seismic design and detail requirements. In current seismic design standards, the target collapse probability for a given Maximum Considered Earthquake (MCE) ground-shaking hazard is defined as 10% for ordinary buildings. This study aims to estimate the collapse probabilities of a three-story, old, reinforced concrete building designed by only considering gravity loads. Four different seismic design categories (SDC), A, B, C, and D, are considered. This study reveals that the RC building located in the SDC A region satisfies the target collapse probability. However, buildings located in SDC B, C, and D regions do not meet the target collapse probability. Since the degree of exceedance of the target probability increases with an increase in the SDC level, it is imminent to retrofit non-ductile RC buildings similar to the model building. It can be confirmed that repair and reinforcement of old reinforced concrete buildings are required.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권8호
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.

• Journal of Advanced Research in Ocean Engineering
• /
• 제2권4호
• /
• pp.169-178
• /
• 2016

Recently, artificial reefs (ARs) have been frequently used primarily owing to the development in AR materials and projects for relatively complicated, large ARs. Among several engineering issues of ARs, wake region of an AR has been characterized because these regions have a high probability of recruiting seaweed spores, providing an energy saving zone, and facilitating deposition of sediments, nutrients, and bio-deposits. To characterize an efficiency index of an AR wake region and its dependency on the prevailing water flow directions, this study proposes a so-called efficiency index diagram. This characterization is done by normalizing the wake volumes with respect to the real AR volume and illustrating how efficiency indices vary with respect to the inlet flow directions. As a result, according to the diagram characteristics such as an averaged efficiency index, fundamental symmetric angle, secure angles, and principal directions, we can easily figure out how a target AR should be aligned along the main water flows to maximize the wake region around the AR. In addition, six ARs are considered and their efficiency index diagrams are illustrated to pinpoint the physical characteristics.

• 제어로봇시스템학회논문지
• /
• 제8권12호
• /
• pp.991-997
• /
• 2002

The concept of feasible & invariant region plays an important role to derive closed loop stability and achie adequate performance of constrained receding horizon predictive control. In this paper, we define a complex polyhedral feasible & invariant set for all stabilizable input-constrained linear systems by using a complex transform and propose a one-norm based receding horizon control scheme using these invariant sets. In order to get a larger stabilizable set, a convex hull of invariant sets which are defined for different state feedback gains is used as a target invariant set of the constrained receding horizon control. The proposed constrained receding horizon control scheme is formulated so that it can be solved via linear programming.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.27-34
• /
• 2012

In this paper, a novel text binarization is presented that can deal with some complex conditions, such as shadows, non-uniform illumination due to highlight or object projection, and messy backgrounds. To locate the target text region, a focus line is assumed to pass through a text region. Next, connected component analysis and stroke width estimation based on location information of the focus line is used to locate the bounding box of the text region, and each box of connected components. A series of classifications are applied to identify whether each CC(Connected component) is text or non-text. Also, a modified K-means clustering method based on an HCL color space is applied to reduce the color dimension. A text binarization procedure based on location of text component and seed color pixel is then used to generate the final result.

• 산업경영시스템학회지
• /
• 제37권1호
• /
• pp.91-95
• /
• 2014

During a flood season, Bo region could be easily exposed to flood due to increase of ground water level and the water drain difficulty even the water amount of Bo can be managed. GFI for the flood risk is measured by mean depth to water during a dry season and minimum depth to water and tangent degree during a flood season. In this paper, a forecasting model of the target variable, GFI and predictors as differences of height between ground water and Bo water, distances from water resource, and soil characteristics are obtained for the dry season of 2012 and the flood season of 2012 with empirical data of Gangjungbo and Hamanbo. Obtained forecasting model would be used for keep the value of GFI below the maximum allowance for no flooding during flooding seasons with controlling the values of significant predictors.

• Applied Science and Convergence Technology
• /
• 제23권5호
• /
• pp.301-307
• /
• 2014

We have fabricated $SnO_2$/Zn core-shell nanowires by employing a sputtering technique with a Zn target. Scanning electron microscopy indicated that the surface of the nanowires became rougher by the coating. X-ray diffraction of the coated nanowires exhibited the hexagonal Zn diffraction peaks. TEM image of coated structures showed that shell layer was mainly comprised of hexagonal Zn phase. EDX spectra suggested that the shell layer consisted of Zn elements. The photoluminescence spectrum of the coated nanowires in conjunction with Gaussian fitting analysis revealed that the emission was disconvoluted with three Gaussian functions, which are centered at 2.1 eV in the yellow region, 2.4 eV in the green region, and 3.3 eV in the ultraviolet region. We speculated the possible mechanisms of these emission peaks.