• The Journal of Korea Robotics Society
• /
• v.10 no.3
• /
• pp.139-145
• /
• 2015

This paper proposed a method of cooperative control of three mobile robots for carrying an object placed on a floor together. Each robot moves to the object independently from its location to a pre-designated location for grasping the object stably. After grasping the common object, the coordination among the robots has been achieved by a master-slave mode. That is, a trajectory planning has been done for the master robot and the distances form the master robot to the two slave robots have been kept constant during the carrying operation. The localization for mobile robots has been implemented using the encoder data and inverse kinematics since the whole system does not have the slippage as much as a single mobile robot. Before the carrying operation, the lifting operations are implemented using the manipulators attached on the top of the mobile robots cooperatively. The real cooperative lifting and carrying operations are implanted to show the feasibility of the master-slave mode control based on the kinematics using the mobile manipulators developed for this research.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.6
• /
• pp.107-116
• /
• 2015

In compliance with digital device growth, the proliferation of high-tech computers, the availability of high quality and inexpensive video cameras, the demands for automated video analysis is increasing, especially in field of intelligent monitor system, video compression and robot vision. That is why object tracking of computer vision comes into the spotlight. Tracking is the process of locating a moving object over time using a camera. The consideration of object's scale, rotation and shape deformation is the most important thing in robust object tracking. In this paper, we propose a robust object tracking scheme using Random Forest. Specifically, an object detection scheme based on region covariance and ZNCC(zeros mean normalized cross correlation) is adopted for estimating accurate object location. Next, the detected region will be divided into five regions for random forest-based learning. The five regions are verified by random forest. The verified regions are put into the model pool. Finally, the input model is updated for the object location correction when the region does not contain the object. The experiments shows that the proposed method produces better accurate performance with respect to object location than the existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1524-1532
• /
• 2012

The calibration method using the existing environmental characteristics is to correct taking advantage of the data that is followed Judgement on the environment. If a decision is not made on the environmental judgement, the use of traditional methods may increase rather than errors. In this paper, UWB-based localization system is utilized. We propose Location Correction Algorithm which is available on if you can not make a judgment about any circumstances for location estimation system. Reference Points was selected to observe the characteristics of the localization system. This paper searched the characteristics of the localization system in LOS environment and NLOS environment, and used data correcting the location information of the moving object by combining the two environmental characteristics. The Location Correction Algorithm is applied to the location measured from the location estimation system. This algorithm corrects for the location information of the object. As a result, the location accuracy improvement were observed.

• Journal of Korea Multimedia Society
• /
• v.16 no.5
• /
• pp.619-628
• /
• 2013

In this paper, we describe a strongly improved tracking method using combination of CAMshift and Kalman filter algorithm. CAMshift algorithm doesn't consider the object's moving direction and velocity information when it set the search windows for tracking. However if Kalman filter is combined with CAMshift for setting the search window, it can accurately predict the object's location with the object's present location and velocity information. By using this prediction before CAMshift algorithm, we can track fast moving objects successfully. Also in this research, we show better tracking results than conventional approaches which make use of single color information by using both color information of HSV and YCrCb simultaneously. This modified approach obtains more robust color segmentation than others using single color information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1117-1123
• /
• 2021

Object recognition is to identify the location and class of a specific object by analyzing the given image when a specific image is input. One of the fields in which object recognition technology is actively applied in recent years is autonomous vehicles, and this paper describes the trend of image-based object recognition artificial intelligence technology in autonomous vehicles. The image-based object detection algorithm has recently been narrowed down to two methods (a single-step detection method and a two-step detection method), and we will analyze and organize them around this. The advantages and disadvantages of the two detection methods are analyzed and presented, and the YOLO/SSD algorithm belonging to the single-step detection method and the R-CNN/Faster R-CNN algorithm belonging to the two-step detection method are analyzed and described. This will allow the algorithms suitable for each object recognition application required for autonomous driving to be selectively selected and R&D.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.52 no.2
• /
• pp.61-67
• /
• 2003

This paper describes a development of magnetic tomography system using two poles perpendicular magnetic field. In the system, the relative permeabilities of the object are detected by Hall sensors located along with tube circumference. The signals according to the size and position of the object could be separated in case the relative permeability of the object are over 10. Moreover, the size and location of the object could be determined in real time.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1179-1186
• /
• 2022

Building Information Modeling (BIM) is widely used to efficiently share, utilize and manage information generated in every phase of a construction project. Recently, mixed reality (MR) technologies have been introduced to more effectively utilize BIM elements. This study deals with the haptic interactions between humans and BIM elements in MR to improve BIM usability. As the first step in interacting with virtual objects in mixed reality, we challenged moving a virtual object to the desired location using finger-pointing. This paper presents the procedure of developing a haptic interface system where users can interact with a BIM object to move it to the desired location in MR. The interface system consists of an MR-based head-mounted display (HMD) and a mobile application developed using Unity 3D. This study defined two segments to compute the scale factor and rotation angle of the virtual object to be moved. As a result of testing a cuboid, the user can successfully move it to the desired location. The developed MR-based haptic interface can be used for aligning BIM elements overlaid in the real world at the construction site.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.47-48
• /
• 2022

The positioning technology that measures the position of a person or object is a key technology to deal with the location of the real coordinate system or converge the real and virtual worlds, such as digital twins, augmented reality, virtual reality, and autonomous driving. In estimating the location of a person or object at an indoor construction site, there are restrictions that it is impossible to receive location information from the outside, the communication infrastructure is insufficient, and it is difficult to install additional devices. Therefore, this study tested the direct sparse odometry algorithm, one of the visual Simultaneous Localization and Mapping (vSLAM) that estimate the current location and surrounding map using only image information, at an indoor construction site and analyzed its applicability as an indoor positioning technology. As a result, it was found that it is possible to properly estimate the surrounding map and the current location even in the indoor construction site, which has relatively few feature points. The results of this study can be used as reference data for researchers related to indoor positioning technology for construction sites in the future.

• The Journal of Information Systems
• /
• v.14 no.3
• /
• pp.17-22
• /
• 2005

Location management is very important in location-based services to provide services to the mobile users like banking, city guides and many more. Ubiquitous and mobile devices are the source of data in location management and its significant operations are update and search method. Some studies to improve these were presented by using optimal sequential paging, location area scheme and hierarchical database scheme. In addition, not all location services have the same access methods on data and it lead to difficulties of providing services. A proposed location management of multi-agent architecture is presented in this study. It shows the coordination of the agents on the distributed database of location-based services. The proposal focuses on the location management of the mobile object presented in a hierarchical search and update. Also, it uses a nearest neighbor technique for efficient search method of mobile objects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.204-211
• /
• 2020

In this paper, we propose an optimal deep learning network architecture for main object location detection through weak supervised learning. The proposed network adds convolution blocks for improving the localization accuracy of the main object through weakly-supervised learning. The additional deep learning network consists of five additional blocks that add a composite product layer based on VGG-16. And the proposed network was trained by the method of weakly-supervised learning that does not require real location information for objects. In addition, Grad-CAM to compensate for the weakness of GAP in CAM, which is one of weak supervised learning methods, was used. The proposed network was tested through the CUB-200-2011 data set, we could obtain 50.13% in top-1 localization error. Also, the proposed network shows higher accuracy in detecting the main object than the existing method.