• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.692-712
• /
• 2022

Buoys used for Aid to Navigation systems are widely used to guide the sea paths and are powered by batteries, requiring continuous battery replacement. However, since human labor is required to replace the batteries, humans can be exposed to dangerous situation, including even collision with shipping vessels. In addition, Maritime sensors are installed on the route signs, so that these are often damaged by collisions with small and medium-sized ships, resulting in significant financial loss. In order to prevent these accidents, maritime object detection technology is essential to alert ships approaching buoys. Existing studies apply a number of filters to eliminate noise and to detect objects within the sea image. For this process, most studies directly access the pixels and process the images. However, this approach typically takes a long time to process because of its complexity and the requirements of significant amounts of computational power. In an emergent situation, it is important to alarm the vessel's rapid approach to buoys in real time to avoid collisions between vessels and route signs, therefore minimizing computation and speeding up processes are critical operations. Therefore, we propose Fast Connected Component Labeling (FCCL) which can reduce computation to minimize the processing time of filter applications, while maintaining the detection performance of existing methods. The results show that the detection performance of the FCCL is close to 30 FPS - approximately 2-5 times faster, when compared to the existing methods - while the average throughput is the same as existing methods.

• Journal of the Korean Society of Marine Environment & Safety
• /
• 제28권7호
• /
• pp.1120-1128
• /
• 2022

In the event of a marine accident, the longer the exposure time to the sea increases, the faster the chance of survival decreases. However, because the search area of the sea is extremely wide compared to that of land, marine object detection technology based on the sensor mounted on a satellite or an aircraft must be applied rather than ship for an efficient search. The purpose of this study was to rapidly detect an object in the ocean using a hyperspectral image sensor mounted on an aircraft. The image captured by this sensor has a spatial resolution of 8,241 × 1,024, and is a large-capacity data comprising 127 spectra and a resolution of 0.7 m per pixel. In this study, a marine object detection model was developed that combines a seawater identification algorithm using DBSCAN and a density-based land removal algorithm to rapidly analyze large data. When the developed detection model was applied to the hyperspectral image, the performance of analyzing a sea area of about 5 km² within 100 s was confirmed. In addition, to evaluate the detection accuracy of the developed model, hyperspectral images of the Mokpo, Gunsan, and Yeosu regions were taken using an aircraft. As a result, ships in the experimental image could be detected with an accuracy of 90 %. The technology developed in this study is expected to be utilized as important information to support the search and rescue activities of small ships and human life.

• Korean Journal of Remote Sensing
• /
• 제38권6_4호
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제9권2호
• /
• pp.330-337
• /
• 2005

This paper proposes a method which improves the performance of face detection by using SVM(Support Vector Machine). first, it finds face region candidates by using AdaBoost based object detection method which selects a small number of critical features from a larger set. Next it classifies if the candidate is a face or non-face by using SVM(Support Vector Machine). Experimental results shows that the proposed method improve accuracy of face detection in comparison with existing method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 한국컴퓨터정보학회 2017년도 제56차 하계학술대회논문집 25권2호
• /
• pp.135-136
• /
• 2017

When driving at night time environment, the whole body of transports does not visible to us. Due to lack of light conditions, there are only two options, which is clearly visible their taillights and break lights. To improve the recognition correctness of vehicle detection, we present an approach to vehicle detection and tracking using finding contour of the object on binary image at night time. Bilateral filtering is used to make more clearly on threshold part. To remove unexpected small noises used morphological opening. In verification stage, paired tail lights are tracked during their existence in the ROI. The accuracy of the test results for vehicle detection is about 93%.

• Proceedings of the Korean Vacuum Society Conference
• /
• 한국진공학회 2012년도 제42회 동계 정기 학술대회 초록집
• /
• pp.182-182
• /
• 2012

Plasma etching is used in various semiconductor processing steps. In plasma etcher, optical- emission spectroscopy (OES) is widely used for in-situ endpoint detection. However, the sensitivity of OES is decreased if polymer is deposited on viewport or the proportion of exposed area on the wafer is too small. Because of these problems, the object is to investigate the suitability of using plasma impedance monitoring (PIM) and self plasma optical emission spectrocopy (SPOES) with statistical approach for in-situ endpoint detection. The endpoint was determined by impedance signal variation from I-V monitor (VI probe) and optical emission signal from SPOES. However, the signal variation at the endpoint is too weak to determine endpoint when $SiO_2$ and SiNx layers are etched by fluorocarbon on inductive coupled plasma (ICP) etcher, if the proportion of $SiO_2$ and SiNx area on Si wafer are small. Therefore, modified principal component analysis (mPCA) is applied to them for increasing sensitivity. For verifying this method, detected endpoint from impedance monitoring is compared with optical emission spectroscopy.

• Journal of IKEEE
• /
• 제22권4호
• /
• pp.1079-1087
• /
• 2018

Recently, computer vision field based deep learning artificial intelligence has become a hot topic among various image analysis boundaries. In this study, flames are detected in fire images using the Faster R-CNN algorithm, which is used to detect objects within the image, among various image recognition algorithms based on deep learning. In order to improve fire detection accuracy through a small amount of data sets in the learning process, we use image augmentation techniques, and learn image augmentation by dividing into 6 types and compare accuracy, precision and detection rate. As a result, the detection rate increases as the type of image augmentation increases. However, as with the general accuracy and detection rate of other object detection models, the false detection rate is also increased from 10% to 30%.

• Publications of The Korean Astronomical Society
• /
• 제30권2호
• /
• pp.235-236
• /
• 2015

Microlensing can be seen as a version of strong gravitation lensing where the separation angle of the image formed by light deflection by a massive object is too small to be seen by a ground based optical telescope. As a result, what can be observed is the change in light intensity as function of time; the light curve. Conventionally, the intensity of the source is expressed in magnitudes, which uses a logarithmic function of the apparent flux, known as the Pogson formulae. In this work, we compare the magnitudes from the Pogson formulae with magnitudes from the Asinh formulae (Lupton et al. 1999). We found for small fluxes, Asinh magnitudes give smaller deviations, about 0.01 magnitudes smalller than Pogson magnitudes. This result is expected to give significant improvement in detection level of microlensing light curves.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제26권6호
• /
• pp.813-826
• /
• 2022

AI-based image processing technologies in various fields have been widely studied. However, the lighter the board, the more difficult it is to reduce the weight of image processing algorithm due to a lot of computation. In this paper, we propose a method using deep learning for object recognition algorithm in lightweight embedded boards. We can determine the area using a deep neural network architecture algorithm that processes semantic segmentation with a relatively small amount of computation. After masking the area, by using more accurate deep learning algorithm we could operate object detection with improved accuracy for efficient neural network (ENet) and You Only Look Once (YOLO) toward executing object recognition in real time for lightweighted embedded boards. This research is expected to be used for autonomous driving applications, which have to be much lighter and cheaper than the existing approaches used for object recognition.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.