• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.277-285
• /
• 2016

Moving object detection system has been an emerging research field in various advanced driver assistance systems (ADAS) and surveillance system. In this paper, we propose two optical flow based moving object detection methods at dynamic scenes. Both proposed methods consist of three successive steps; pre-processing, foreground segmentation, and post-processing steps. Two proposed methods have the same pre-processing and post-processing steps, but different foreground segmentation step. Pre-processing calculates mainly optical flow map of which each pixel has the amplitude of motion vector. Dense optical flows are estimated by using Farneback technique, and the amplitude of the motion normalized into the range from 0 to 255 is assigned to each pixel of optical flow map. In the foreground segmentation step, moving object and background are classified by using the optical flow map. Here, we proposed two algorithms. One is Gaussian mixture model (GMM) based background subtraction, which is applied on optical map. Another is adaptive thresholding based foreground segmentation, which classifies each pixel into object and background by updating threshold value column by column. Through the simulations, we show that both optical flow based methods can achieve good enough object detection performances in dynamic scenes.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2006.06b
• /
• pp.465-469
• /
• 2006

Pre-treatment methods to determine various heavy metal contents in packaging papers were investigated by ICP-ES (Inductively Coupled Plasma Emission Spectrometry) analysis. Pre-treatment methods utilized in this study include dry ashing and decomposition methods ($HNO_{3-}HClO_{4-}HF,\;HNO_{3},\;and\;H_{2}SO_{4-}HNO_{3}$). They were compared with the conventional extraction (water) and migration (3% acetic acid) methods. The five representative heavy metals (Cd, As, Pb, Cr and Hg) were analyzed. For Cd, Hg, and As, the results were below detection limit of the instrument. In case of Cr and Pb, the migration test is considered to be a better method compared to the extraction test, but all pretreated methods showed much higher detection efficiency than the extraction or migration test. However, the detection ratio between the migration test and decomposition methods was different. Among all decomposition methods, the nitric acid - perchloric acid - hydrofluoric acid treatment brought a slightly higher detection value than others, but there was no significant difference among them except sulfuric acid - nitric acid method. Concerning Pb, the sulfuric acid - nitric acid method showed a low detection efficiency compared to other decomposition methods. The sulfuric acid - nitric acid method is, thus, not considered to be a suitable analysis method for Pb in packaging papers.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Journal of the Korean association of regional geographers
• /
• v.5 no.1
• /
• pp.137-150
• /
• 1999

Five land use change detection methods were applied to 1994 and 1997 Landsat Thematic Mapper (TM) images of Pook-Gu, Taegu city to determine the land-cover changes between the two dates. The two images were coregistred to UTM coordinates. A post-classification comparison method was the most commonly used quantitative method of change detection. A pre-classification comparison method was more effective method to change detection of land cover than a post-classification comparison method. Two indices were used to assess the accuracies of the studied methods. A image differencing method was found to be most accurate for detecting change verse no change among five land use change detection methods. The difference image of band 2 was found to be most accurate. The overall accuracy and Kappa index agreement of the difference image of band 2 were 0.810 and 0.447.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.

• Proceedings of the KIEE Conference
• /
• 2002.07c
• /
• pp.1827-1829
• /
• 2002

This paper describes AC test for long delivered drum length of cable using pre-breakdown partial discharge detection(PPD) method, which can be applied to observe the causes of electrical breakdown of EHV XLPE insulation. This method is to de-energize applied voltage to cable rapidly using pre-breakdown partial discharge, and is able to prevent complete breakdown. By this effect, defects such as voids, metal particles and protrusion in cable can be observed clearly. AC resonant test set was used for PPD method. Localization of partial discharge was performed by time difference detection of the traveling wave. Accuracy of localization was 1% to the length of test cable. Through several experiments with XLPE cable, successful results of PPD method were obtained.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.698-701
• /
• 2006

Remotely sensed data have been utilized efficiently for damage detection immediately after the natural disaster since they provide valuable information on land cover change due to spatial synchronization and multitemporal observation over large areas. Damage information obtained at an early stage is important for rapid emergency response and recovery works. Many useful techniques to analyze the characteristics of the pre- and post-event satellite images in large-scale damage detection have been successfully investigated for emergency management. Since high-resolution satellite images provide a wealth of information on damage occurred in urban areas, they are successfully utilized for damage detection in urban areas. In this research, a method to perform automated damage detection is proposed based on the differences of the textural characteristics in pre- and post- high resolution satellite images.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• Nuclear Engineering and Technology
• /
• v.51 no.1
• /
• pp.146-154
• /
• 2019

An improved principal component analysis (PCA) method is applied for sensor fault detection and isolation (FDI) in a nuclear power plant (NPP) in this paper. Data pre-processing and false alarm reducing methods are combined with general PCA method to improve the model performance in practice. In data pre-processing, singular points and random fluctuations in the original data are eliminated with various techniques respectively. In fault detecting, a statistics-based method is proposed to reduce the false alarms of $T^2$ and Q statistics. Finally, the effects of the proposed data pre-processing and false alarm reducing techniques are evaluated with sensor measurements from a real NPP. They are proved to be greatly beneficial to the improvement on the reliability and stability of PCA model. Meanwhile various sensor faults are imposed to normal measurements to test the FDI ability of the PCA model. Simulation results show that the proposed PCA model presents favorable performance on the FDI of sensors no matter with major or small failures.