• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.5
• /
• pp.449-457
• /
• 2011

As automated image processing techniques have been required in multi-temporal/multi-sensor geospatial image applications, use of automated but highly invariant image matching technique has been a critical ingredient. Note that there is high possibility of geometric and spectral differences between multi-temporal/multi-sensor geospatial images due to differences in sensor, acquisition geometry, season, and weather, etc. Among many image matching techniques, the SIFT (Scale Invariant Feature Transform) is a popular method since it has been recognized to be very robust to diverse imaging conditions. Therefore, the SIFT has high potential for the geospatial image processing. This paper presents a performance test results of the SIFT on geospatial imagery by simulating various image differences such as shear, scale, rotation, intensity, noise, and spectral differences. Since a geospatial image application often requires a number of good matching points over the images, the number of matching points was analyzed with its matching positional accuracy. The test results show that the SIFT is highly invariant but could not overcome significant image differences. In addition, it guarantees no outlier-free matching such that it is highly recommended to use outlier removal techniques such as RANSAC (RANdom SAmple Consensus).

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.502-504
• /
• 1995

In video image compression, it is important to extract the exact notion information from image sequence in order to perform the data compression, the field rate conversion, and the motion compensated interpolation effectively. It is well known that the location of the smallest sum of absolute difference(SAD) does not always give the true motion vector(MV) since the MV obtained via full block search is often corrupted by noise. In this paper, we first classifies the input blocks into 3 categories : the background, the shade-motion, and the edge-motion. According to the characteristics of the classified blocks, multiple locations of relatively small SAD are searched with an adaptive search window by using the proposed method. The proposed method picks MVs among those candidates by using temporal correlation. Since temporal correlation reveals the noise level in a particular region of the video image sequence, we are able to reduce the search are very effectively.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1264-1274
• /
• 2015

Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.90-95
• /
• 2012

Remotely sensed data provide valuable information on land monitoring due to multi-temporal observation over large areas. Especially, high resolution imagery with 0.6~1.0 m spatial resolutions contain a wealth of information and therefore are very useful for thematic mapping and monitoring change in urban areas. Recently, remote sensing technology has been successfully utilized for natural disaster monitoring such as forest fire, earthquake, and floods. In this paper, an efficient change detection method based on texture differences observed from high resolution multi-temporal data sets is proposed for mapping disaster damage and extracting damage information. It is composed of two parts: feature extraction and detection process. Timely and accurate information on disaster damage can provide an effective decision making and response related to damage.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.443-453
• /
• 2020

The automatic land category extraction method was proposed, and the accuracy was evaluated by learning the aerial photo characteristics by land category in the border area with various restrictions on the acquisition of geospatial data. As experimental data, this study used four years' worth of published aerial photos as well as serial cadastral maps from the same time period. In evaluating the results of land category extraction by learning features from different temporal and spatial ranges of aerial photos, it was found that land category extraction accuracy improved as the temporal and spatial ranges increased. Moreover, the greater the diversity and quantity of provided learning images, the less the results were affected by the quality of images at a specific time to be extracted, thus generally demonstrating accurate and practical land category feature extraction.

• Korean Journal of Remote Sensing
• /
• v.24 no.1
• /
• pp.79-89
• /
• 2008

Irregular temporal sampling is a common feature of geophysical and biological time series in remote sensing. This study proposes an on-line system for reconstructing observation image series contaminated by noises resulted from mechanical problems or sensing environmental condition. There is also a high likelihood that during the data acquisition periods the target site corresponding to any given pixel may be covered by fog or cloud, thereby resulting in bad or missing observation. The surface parameters associated with the land are usually dependent on the climate, and many physical processes that are displayed in the image sensed from the land then exhibit temporal variation with seasonal periodicity. A feedback system proposed in this study reconstructs a sequence of images remotely sensed from the land surface having the physical processes with seasonal periodicity. The harmonic model is used to track seasonal variation through time, and a Gibbs random field (GRF) is used to represent the spatial dependency of digital image processes. The experimental results of this simulation study show the potentiality of the proposed system to reconstruct the image series observed by imperfect sensing technology from the environment which are frequently influenced by bad weather. This study provides fundamental information on the elements of the proposed system for right usage in application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• ETRI Journal
• /
• v.43 no.1
• /
• pp.40-52
• /
• 2021

DNS (Domain Name System) tunnels almost obscure the true network activities of users, which makes it challenging for the gateway or censorship equipment to identify malicious or unpermitted network behaviors. An efficient way to address this problem is to conduct a temporal-spatial analysis on the tunnel traffic. Nevertheless, current studies on this topic limit the DNS tunnel to those with a single protocol, whereas more than one protocol may be used simultaneously. In this paper, we concentrate on the refined identification of two protocols mixed in a DNS tunnel. A feature set is first derived from DNS query and response flows, which is incorporated with deep neural networks to construct a regression model. We benchmark the proposed method with captured DNS tunnel traffic, the experimental results show that the proposed scheme can achieve identification accuracy of more than 90%. To the best of our knowledge, the proposed scheme is the first to estimate the ratios of two mixed protocols in DNS tunnels.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.57-58
• /
• 2022

Sleep apnea (SA) is a common chronic sleep disorder that disrupts breathing during sleep. Clinically, the standard for diagnosing SA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of SA diagnoses in public health sectors. Therefore, ECG-based methods for SA detection have been proposed to automate the PSG procedure and reduce its discomfort. We propose a preprocessing method to convert the one-dimensional time series of ECG into two-dimensional images using the Gramian Angular Field (GAF) algorithm, extract temporal features, and use a two-dimensional convolutional neural network for classification. The results of this study demonstrated that the proposed method can perform SA detection with specificity, sensitivity, accuracy, and area under the curve (AUC) of 88.89%, 81.50%, 86.11%, and 0.85, respectively. Our experimental results show that SA is successfully classified by extracting preprocessing transforms with temporal features.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.89-95
• /
• 2023

In recent decades, human action recognition (HAR) has demonstrated potential applications in sports analysis, human-robot interaction, and large-scale signage content. In this paper, spatial temporal attention graph convolutional network (STAGCN)-based HAR system is proposed. Spatioal-temmporal features of skeleton sequences are assigned different weights by STAGCN, enabling the consideration of key joints and viewpoints. From simulation results, it has been shown that the performance of the proposed model can be improved in terms of classification accuracy in the NTU RGB+D dataset.