• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.372-378
• /
• 2015

Background subtraction is the first processing stage in video surveillance. It is a general term for a process which aims to separate foreground objects from a background. The goal is to construct and maintain a statistical representation of the scene that the camera sees. The output of background subtraction will be an input to a higher-level process. Background subtraction under dynamic environment in the video sequences is one such complex task. It is an important research topic in image analysis and computer vision domains. This work deals background modeling based on modified adaptive Gaussian mixture model (GMM) with three temporal differencing (TTD) method in dynamic environment. The results of background subtraction on several sequences in various testing environments show that the proposed method is efficient and robust for the dynamic environment and achieves good accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.681-686
• /
• 2003

In this paper, we propose an algorithm to extract valid planar regions from stereo images for visual navigation of mobile robots. The algorithm is based on the difference image between the stereo images obtained by applying Homography matrix between stereo cameras. Illegal planar regions are filtered out by the use of labeling of the difference images and filtering of invalid blobs using the size of each blob. Also, illegal large planar regions such as walls are removed by adopting a weighted low-pass filtering of the difference image using the past difference images. The algorithms are experimented successfully by the use of stereo camera system built in a mobile robot and a PC-based real-time vision system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.224-241
• /
• 2015

Multiview plus depth (MVD) videos are widely used in free-viewpoint TV systems. The best-known technique to determine depth information is based on stereo vision. In this paper, we propose a novel local stereo matching algorithm which is radiometric invariant. The key idea is to use a combined matching cost of intensity and gradient based similarity measure. In addition, we realize an adaptive cost aggregation scheme by constructing an adaptive support window for each pixel, which can solve the boundary and low texture problems. In the disparity refinement process, we propose a four-step post-processing technique to handle outliers and occlusions. Moreover, we conduct stereo reconstruction tests to verify the performance of the algorithm more intuitively. Experimental results show that the proposed method is effective and robust against local radiometric distortion. It has an average error of 5.93% on the Middlebury benchmark and is compatible to the state-of-art local methods.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2000.04a
• /
• pp.129-133
• /
• 2000

It is reasonable to use the stereo vision and image processing technique to digitize 3D coordinates of grid points and to evaluate surface strains on a sheet metal parts. However this method has its intrinsic problems such as the difficulty in enhancement of bad images inevitable error due to digital image resolution of camera and frame grabber unreliability of strains and thickness evaluated from coarse grid on the corner area with large curvature and the limitation of the area that can be measured at a time. Therefore it is still hard to measure strain distribution over the entire surface of a medium,- or large-sized stamped part at a time even by using an automated strain measurement system. In this study the curvature correction algorithm based on the grid refinement and the geometry assembling algorithm based on the global error minimization (GEM) scheme are suggested. Several applications are presented to show the reliability and efficiency of these algorithms.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.4
• /
• pp.107-115
• /
• 2008

Accurate extraction of traversable region is a critical issue for autonomous navigation of unmanned ground vehicle(UGV). This paper introduces enhanced extraction of traversable region by combining scene clustering with 3D world modeling using CCD(Charge-Coupled Device)/IR(Infra Red) image. Scene clustering is developed with K-means algorithm based on CCD and IR image. 3D world modeling is developed by fusing CCD and IR stereo image. Enhanced extraction of traversable regions is obtained by combining feature of extraction with a clustering method and a geometric characteristic of terrain derived by 3D world modeling.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1473-1480
• /
• 2018

The extraction and recognition of human motion characteristics need to combine biometrics to determine and judge human behavior in the movement and distinguish individual identities. The so-called biometric technology, the specific operation is the use of the body's inherent biological characteristics of individual identity authentication, the most noteworthy feature is the invariance and uniqueness. In the past, the behavior recognition technology based on the single characteristic was too restrictive, in this paper, we proposed a mixed feature which combined global silhouette feature and local optical flow feature, and this combined representation was used for human action recognition. And we will use the KTH database to train and test the recognition system. Experiments have been very desirable results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.4869-4874
• /
• 2011

In this paper, we defined constructivism and ontology theory and associate it in Location Based Service ubiquitous learning. And this paper aims to provide a clear vision about location based service (LBS) ubiquitous learning. The typical ubiquitous learning involving the Context Aware Intelligent system was presented. Also the Architecture for learning environment including the key idea and technical concept is being presented in this paper. Guided with these principles and with the advancement of information and communication technology the context-awareness based on Artificial intelligence for Location based Service for ubiquitous Learning was conceptualized. U-learning for Location Based Service is presented here and the concept behind this new learning paradigm. The learning environment architecture which comprises the entire component is illustrated here.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.3
• /
• pp.250-256
• /
• 2012

Unmanned ground vehicles may be operated by remote control unit through the wireless communication or autonomously. However, the autonomous technology is still challenging and not perfectly developed. For some reason or other, the wireless communication is not always available. If wireless communication is abruptly disconnected, the UGV will be nothing but a lump of junk. What was worse, the UGV can be captured by enemy. This paper suggests a method, autonomous return technology with which the UGV can autonomously go back to a safer position along the reverse path. The suggested autonomous return technology for UGV is based on multi-correlated information based DB creation and matching. While SUGV moves by remote-control, the multi-correlated information based DB is created with the multi-sensor information; the absolute position of the trajectory is stored in DB if GPS is available and the hybrid MAP based on the fusion of VISION and LADAR is stored with the corresponding relative position if GPS is unavailable. In multi-correlated information based autonomous return, SUGV returns autonomously based on DB; SUGV returns along the trajectory based on GPS-based absolute position if GPS is available. Otherwise, the current position of SUGV is first estimated by the relative position using multi-sensor fusion followed by the matching between the query and DB. Then, the return path is created in MAP and SUGV returns automatically based on the MAP. Experimental results on the pre-built trajectory show the possibility of the successful autonomous return.

• Journal of Biosystems Engineering
• /
• v.28 no.6
• /
• pp.517-524
• /
• 2003

There have been worldwide research and development efforts to automate various processes of bio-production and those efforts will be expanded with priority given to tasks which require high intensive labor or produce high value-added product and tasks under hostile environment. In the field of bio-production capabilities of the versatility and robustness of automated system have been major bottlenecks along with economical efficiency. This paper introduces a new concept of automation based on tole-operation, which can provide solutions to overcome inherent difficulties in automating bio-production processes. Operator(farmer), computer, and automatic machinery share their roles utilizing their maximum merits to accomplish given tasks successfully. Among processes of greenhouse watermelon cultivation tasks such as pruning, watering, pesticide application, and harvest with loading were chosen based on the required labor intensiveness and functional similarities to realize the proposed concept. The developed system was composed of 5 major hardware modules such as wireless remote monitoring and task control module, wireless remote image acquisition and data transmission module, gantry system equipped with 4 d.o.f. Cartesian type robotic manipulator, exchangeable modular type end-effectors, and guided watermelon loading and storage module. The system was operated through the graphic user interface using touch screen monitor and wireless data communication among operator, computer, and machine. The proposed system showed practical and feasible way of automation in the field of volatile bio-production process.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.916-923
• /
• 2023

Purpose: Looking at the status of fatal accidents in the construction industry in the 2022 Industrial Accident Status Supplementary Statistics, 27.8% of all fatal accidents in the construction industry are caused by construction equipment. In order to overcome the limitations of tours and inspections caused by the enlargement of sites and high-rise buildings, we plan to build a model that can extract construction equipment using computer vision technology and analyze the model's accuracy and field applicability. Method: In this study, deep learning is used to learn image data from excavators, dump trucks, and mobile cranes among construction equipment, and then the learning results are evaluated and analyzed and applied to construction sites. Result: At site 'A', objects of excavators and dump trucks were extracted, and the average extraction accuracy was 81.42% for excavators and 78.23% for dump trucks. The mobile crane at site 'B' showed an average accuracy of 78.14%. Conclusion: It is believed that the efficiency of on-site safety management can be increased and the risk factors for disaster occurrence can be minimized. In addition, based on this study, it can be used as basic data on the introduction of smart construction technology at construction sites.