• Journal of the Semiconductor & Display Technology
• /
• v.11 no.4
• /
• pp.49-55
• /
• 2012

This paper proposes an efficient method of object identification and localization for image recognition. The new proposed algorithm utilizes correlogram back-projection in the YCbCr chromaticity components to handle the problem of sub-region querying. Utilizing similar spatial color information enables users to detect and locate primary location and candidate regions accurately, without the need for additional information about the number of objects. Comparing this proposed algorithm to existing methods, experimental results show that improvement of 21% was observed. These results reveal that color correlogram is markedly more effective than color histogram for this task. Main contribution of this paper is that a different way of treating color spaces and a histogram measure, which involves information on spatial color, are applied in object localization. This approach opens up new opportunities for object detection for the use in the area of interactive image and 2-D based augmented reality.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.882-884
• /
• 2003

We present an application of digital video images for object tracking. In order to track a fixed object, which was shoot on a moving vehicle, this study develops a shape-based matching algorithm to implement the tracking task. Because the shape-based matching algorithm has scale and rotation invariant characteristics, therefore it can be used to calculate the similarity between two variant shapes. An experiment is performed to track the ship object in the open sea. The result shows that the proposed method can track the object in the video images even the shape change largely.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.48-53
• /
• 2004

In this paper, the task-oriented optimal configuration in the sense of Velocity and Force manipulability measure of manipulator mounted on ROV is considered. Manipulability is a quantitative measure of manipulator's capability obtained under the limits of joint velocities or torques. The base arrangements and optimal joint configuration of manipulator, that maximize the manipulability measure under the constraints of given task, are investigated. With the two types of base arrangements of manipulator, workspace analysis is carried out to investigate merits and demerits of each arrangement on the view of manipulability measure. To find optimal joint configuration for a given task with each arrangement, the SQP(Sequential Quadratic Programming) optimization are performed. Weighted linear combination of velocity and force manipulability measure is object function for SQP optimization. The kinematic parameters of Dual Orion manipulator which will be mounted on KORDI ROV are used for simulation.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.7
• /
• pp.69-77
• /
• 1998

In this paper, a controller is designed for efficient controlling of video data with object-oriented feature. The need of controlling video data in an object unit is on the rise for the reason of rapidly growing demand for high-quality video services. We propose a programmable architecture with stack buffers which can minimize a scheduling overhead by having separate buffes for genral data and return addresses. The buffers are veyr useful for move and copy operations for multitasking and task switching. The controller offers extended instructions that process several data types including 32bit integrer type. Operation speed of the controller is from 77MHz to 44MHz.

• Journal of the Korea Institute of Building Construction
• /
• v.8 no.4
• /
• pp.71-77
• /
• 2008

Earthwork is very equipment-intensive task and researches related to automated excavation have been conducted. There is an issue to secure the safety for an automated excavating system. Therefore, this paper focuses on how to improve safety for semi- or fully-automated backhoe excavation. The primary objective of this research is to develop the core technology for automated object detection in excavation work. In order to satisfy the research objective, a diverse sensing technologies are investigated and analysed in terms of functions, durability, and reliability. The authors developed detecting algorithm for the objects using laser sensor and verified its performance by several tests. The results of this study would be the basis for developing the automated object detection system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.743-744
• /
• 2016

Object tracking in video sequences is a challenging task and has various applications. Particle filtering has been proven very successful for non-Gaussian and non-linear estimation problems. In this study, we first try to develop a color-based particle filter. In this approach, the color distributions of video frames are integrated into particle filtering. Color distributions are applied because of their robustness and computational efficiency. The model of the particle filter is defined by the color information of the tracked object. The model is compared with the current hypotheses of the particle filter using the Bhattacharyya coefficient. The proposed tracking method directly incorporates the scale and motion changes of the objects. Experimental results have been presented to show the effectiveness of our proposed system.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.158-164
• /
• 2008

This study was conducted for raising the considering the dynamical context of mobile phone use environment in the mobile-phone research. For this I identified the characteristic of the mobile phone use. The first characteristic is that the mobile phone is the context sensitive device. Also, it reflects the user's life pattern because it is the very personal device. I defined the context of mobile phone use with the basis on this identification of those characteristics. I referenced the definition, 'situational context', defining the mobile phone use context. Also, I set up the research scope within the user task that is influential from the situational context, I named this kind of task as the 'contextual task'. I developed the Contextual Task Model in this study. I named the model as the 'ESR Model'. The reason that I developed this contextual task model is that this model can help novice designers and designers unfamiliar with an application domain understand the user behavior and user centered design. And also this model can be effective to communicate each other, I identified the user's contextual tasks three kinds of model. First, the Extend Model includes user tasks that related to extending from user physical working space to the virtual level. Second model is Synchronize Model, which includes issues that lesson the blocking when use several functions at a time or sequentially. Third model is Replace Model, which is come from the characteristic of user life pattern to use the mobile phone. Finally, I proposed an application of this model, CIQ. Through the process to make CIQ I proved the effectiveness of this ESR Model.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.10
• /
• pp.3038-3047
• /
• 1996

In telerobot systems, visual servoing of a task object for a slave arm with an eye-in-hand has drawn an interesting attention. As such a task ingenerally conducted in an unstructured environment, it is very difficult to define the inverse feature Jacobian matrix. To overcome this difficulty, this paper proposes an auto-tuning fuzzy rule-based visual servo algorithm. In this algorithm, a visual servo controller composed of fuzzy rules, receives feature errors as inputs and generates the change of have position as outputs. The fuzzy rules are tuned by using steepest gradient method of the cost function, which is defined as a quadratic function of feature errors. Since the fuzzy rules are tuned automatically, this method can be applied to the visual servoing of a slave arm in real time. The effctiveness of the proposed algorithm is verified through a series of simulations and experiments. The results show that through the learning procedure, the slave arm and track object in real time with reasonable accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3104-3120
• /
• 2017

The intelligent monitoring system has been successfully applied in many fields such as: monitoring of production lines, transportation, etc. Smart surveillance systems have been developed and proven effective in some specific areas such as monitoring of human activity, traffic, etc. Most of critical application monitoring systems involve object tracking as one of the key steps. However, task of tracking of moving object is not easy. In this paper, the authors propose a method to implement human object tracking in outdoor environment based on human features in shearlet domain. The proposed method uses shearlet transform which combines the human features with context-sensitiveness in order to improve the accuracy of human tracking. The proposed algorithm not only improves the edge accuracy, but also reduces wrong positions of the object between the frames. The authors validated the proposed method by calculating Euclidean distance and Mahalanobis distance values between centre of actual object and centre of tracked object, and it has been found that the proposed method gives better result than the other recent available methods.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.