• Korean Journal of Remote Sensing
• /
• v.33 no.6_1
• /
• pp.1019-1027
• /
• 2017

As high resolution satellite images can be used, numerous studies have been carried out for exploiting these images in various fields. This paper proposes horse hoof shaped object detection method based on mathematical morphology to extract interesting targets. Interesting targets have conceptually similar shapes such as a horse hoof, not having exact size or shape. Detection of an object with the similar shapes is possible by applying mathematical morphology processes. The proposed method allows an automatic object detection system to detect the meaningful object in a large satellite image rapidly. The mathematical morphology process can be applied to binary images, and thus this method is very simple. Therefore, this method can easily extract a "horse hoof shaped object" from any image that has indistinct edges of the interesting object and different image qualities depending on the filming location, filming time, and filming environment. Using the proposed method by which a "horse hoof shaped object" can be rapidly extracted, the performance of the automatic object detection system can be improved.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.383-392
• /
• 2007

This study focuses on co-registration and band selection, which are one of the pre-processing steps to apply the change detection technique using hyperspectral images. We carried out automatic co-registration by using the SIFT algorithm which performance was already established in the computer vision fields, and selected the bands fur change detection by estimating the noise of image through the PIFs reflecting the radiometric consistency. The EM algorithm was also applied to select the band objectively. Hyperion images were used for the proposed techniques, and non-calibrated bands and striping noises contained in Hyperion image were removed. Throughout the results, we could develop the reliable co-registration procedure which coincided with accuracy within 0.2 pixels (RMSE) for change detection, and verified that band selection depending on the visual inspection could be objective by extracting the PIFs.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.8-15
• /
• 2019

Recently, the importance of pre-shipment quality inspection has been emphasized due to the increase of STB supply. In this paper, we propose a method to support automation of quality inspection through simultaneous multi-channel input of STB video signal. The proposed method extracts a fingerprint using the center scan line of the image after stable video shot boundary detection using CeLDP combining color information and LDP code and performs synchronization between input video channels. The proposed method shows stronger shot boundary detection performance than the conventional shot detection method. Through the experiments applied to the real environment, it is possible to secure reliability and real-time quality check for synchronization between multi-channel inputs required for STB quality inspection. Also, based on the proposed method, we intend to study a large-scale quality inspection method in the future and propose a more effective quality inspection system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.3
• /
• pp.399-407
• /
• 2019

In Korea, the construction industry has been known to have the highest risk of safety accidents compared to other industries. Therefore, in order to improve safety in the construction industry, several researches have been carried out from the past. This study aims at improving safety of labors in construction site by constructing an effective automatic safety helmet detection system using object detection algorithm based on image data of construction field. Deep learning was conducted using Region-based Fully Convolutional Network (R-FCN) which is one of the object detection algorithms based on Convolutional Neural Network (CNN) with Transfer Learning technique. Learning was conducted with 1089 images including human and safety helmet collected from ImageNet and the mean Average Precision (mAP) of the human and the safety helmet was measured as 0.86 and 0.83, respectively.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.1
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.11 no.1
• /
• pp.23-28
• /
• 2012

In this paper, we proposed and developed a fast and efficient real time face detection and recognition which can be run on embedded system instead of high performance desktop. In the face detection process, we detect a face by finding eye part which is one of the most salient facial features after applying various image processing methods, then in the face recognition, we finally recognize the face by comparing the current face with the prepared face database using a template matching algorithm. Also we optimized the algorithm in our system to be successfully used in the embedded system, and performed the face detection and recognition experiments on the embedded board to verify the performance. The developed method can be applied to automatic door, mobile computing environment and various robot.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.251-261
• /
• 2015

We present a novel method for real-time automatic license plate detection in high-resolution videos. Although there have been extensive studies of license plate detection since the 1970s, the suggested approaches resulting from such studies have difficulties in processing high-resolution imagery in real-time. Herein, we propose a novel cascade structure, the fastest classifier available, by rejecting false positives most efficiently. Furthermore, we train the classifier using the core patterns of various types of license plates, improving both the computation load and the accuracy of license plate detection. To show its superiority, our approach is compared with other state-of-the-art approaches. In addition, we collected 20,000 images including license plates from real traffic scenes for comprehensive experiments. The results show that our proposed approach significantly reduces the computational load in comparison to the other state-of-the-art approaches, with comparable performance accuracy.

• Journal of Navigation and Port Research
• /
• v.40 no.5
• /
• pp.265-270
• /
• 2016

Extreme tropospheric anomalies such as typhoons or regional torrential rain can degrade positioning accuracy of the GPS signal. It becomes one of the main error terms affecting high-precision positioning solutions in network RTK. This paper proposed a detection algorithm to be used during atmospheric anomalies in order to detect the tropospheric irregularities that can degrade the quality of correction data due to network errors caused by inhomogeneous atmospheric conditions between multi-reference stations. It uses an atmospheric grid that consists of four meteorological stations and estimates the troposphere zenith total delay difference at a low performance point in an atmospheric grid. AWS (automatic weather station) meteorological data can be applied to the proposed tropospheric anomaly detection algorithm when there are different atmospheric conditions between the stations. The concept of probability density distribution of the delta troposphere slant delay was proposed for the threshold determination.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.34-37
• /
• 2005

An efficient and robust neural network-based scheme is introduced in this paper to perform automatic cloud detection. Unlike many existing cloud detection schemes which use thresholding and statistical methods, we used the artificial neural network methods, the multi-layer perceptrons (MLP) with back-propagation algorithm and radial basis function (RBF) networks for cloud detection from Geostationary satellite images. We have used a simple scene (a mixed scene containing only cloud and clear sky). The main results show that the neural networks are able to handle complex atmospheric and meteorological phenomena. The experimental results show that two methods performed well, obtaining a classification accuracy reaching over 90 percent. Moreover, the RBF model is the most effective method for the cloud classification.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.233-235
• /
• 2005

This paper presents an unsupervised change detection methodology designed for the detection of landslide areas. The proposed methodology consists of two analytical steps: one for multi-temporal segmentation and the other for automatic selection of thresholding values. By considering the conditions of landslide occurrences and the spectral behavior of multi-temporal remote sensing images, some specific procedures are included in the analytical steps mentioned above. The effectiveness and applicability of the methodology proposed here were illustrated by a case study of the Gangneung area, Korea. The case study demonstrated that the proposed methodology could detect about $83\%$ of landslide occurrences.