• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.43-48
• /
• 2018

This study was conducted to reproduce digital colour based on the lightness of the background and size of the colour stimulus so that colour can be similarly perceived under different conditions. With the evolution of display technologies, display devices of various sizes can now reproduce more accurate colour and enhanced images, thus affecting the overall quality of display images. This study reproduced digital colour by considering the visual characteristics of the digital media environment. To accomplish this, we developed a colour appearance model which distinguishes the properties of foveal and peripheral vision. The proposed model is based on existing research on the lightness of the background and size of the colour stimulus. Based on experimental results, an analysis of variance was performed in order to develop the colour appearance model. The algorithm and modelling were verified based on the proposed model. In addition, to apply this model to display technologies, a practical colour control system and a method for handling complex input images were developed. Through this research, colour conversion errors which might occur when the input image is converted to fit a specific display size are resolved from the perspective of the human visual system. As a result, more accurate colour can be displayed and enhanced images can be reproduced.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of fish pathology
• /
• v.26 no.2
• /
• pp.59-64
• /
• 2013

This study aimed to develop an algorithm to determine the optimal injection position in olive flounder, Paralichthys olivaceus when a vaccine is injected into the fish by using a vision-based automatic equipment measruing the total length (TL), width and weight of the fish. Over a 5-month period, 500 olive flounders were examined to analyze the relation of the fish size and to the shape and location of its abdomen, using radiography, a ruler plate and scale. There were significant correlations between the TL and the shape and location of the abdomen. The abdomen was located 0.232TL - 2.7221 mm ($R^2$=0.8787) from the end of the mouth of the fish. The height and width of the abdomen in the fish were 0.1292TL + 1.8768 mm ($R^2$=0.7935) and 0.183TL-5.9791 mm ($R^2$=0.8641), respectively. The injection point in the abdominal region avoiding organs was determined by calculating the center of gravity of the abdomen volume. This can be expressed as g (0.2759TL - 2.0965, 0.1295TL - 4.2325) on the basis of TL line coordinates. The injection point by the expressed coordinates had errors for the x and y axes as 12.15 mm and 8.28 mm, respectively. These were enough to use the algorithm to injection for the equipment. This automated method to determine the position of any part in the fish can also be used for other purposes, for example, intramuscular injection or auto-tagging of fish.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.837-839
• /
• 2012

When the for occurred, the driver does not get the vision is has difficult on driving. In this case, the probability of occurrence of accidents are very high level. To reduce accidents, this system provide drivers with the safety of ensure to measures that a service inform current situation. in this paper, the crash occur in fog to prevent accident using vehicle safety system to give a alarm and control. The proposed system is installed on the outside of the vehicle, humidity, and ambient light sensors inside the car from the information collected by the system controller for the detection of fog conditions using video equipment and then finally the fog occurs if you do not get the driver's field of events is causing the system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1591-1596
• /
• 1991

The present paper describes a method of recognizing a polyhedron employing the notion of network constraint analysis. Typical difficulties in three-dimensional object recognition, other than shading, reflection, and hidden line problems, include the case where appearances of an object vary according to observation points and the case where an object to be recognized is occluded by other objects placed in its front, resulting in incomplete information on the object shape. These difficulties can, however, be solved to a large extent, by taking account of certain local constraints defined on a polyhedral shape. The present paper assumes a model-based vision employing an appearance-oriented model of a polyhedron which is provided by placing it at the origin of a large sphere and observing it from various positions on the surface of the sphere. The model is actually represented by the sets of adjacent faces pairs of the polyhedron observed from those positions. Since the shape of a projected face gives constraint to that of its adjacent face, this results in a local constraint relation between these faces. Each projected face of an unknown polyhedron on an acquired image is examined its match with those faces in the model, producing network constraint relations between faces in the image and faces in the model. Taking adjacency of faces into consideration, these network constraint relations are analyzed. And if the analysis finally provides a solution telling existence of one to one match of the faces between the unknown polyhedron and the model, the unknown polyhedron is understood to be one of those memorized models placed in a certain posture. In the performed experiment, a polyhedron was observed from 320 regularly arranged points on a sphere to provide its appearance model and a polyhedron with arbitrarily postured, occluded, or imposed another difficulty was successfully recognized.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.345-354
• /
• 2005

A mobile manipulator - a serial connection of a mobile robot and a task robot - is a very useful system to achieve various tasks in dangerous environment, because it has the higher performance than a fixed base manipulator in terms of its operational workspace size as well as efficiency. A method for estimating the position of an object in the Cartesian coordinate system based upon the geometrical relationship between the image captured by 2-DOF active camera mounted on mobile robot and the real object, is proposed. With this Position estimation, a method of determining an optimal path for the mobile manipulator from the current position to the position of object estimated by the image information using homogeneous matrices. Finally, the corresponding joint parameters to make the desired displacement are calculated to capture the object through the control of a manipulator. The effectiveness of proposed method is demonstrated by the simulation and real experiments using the mobile manipulator.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.78-84
• /
• 2015

Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.1-5
• /
• 2013

The number of pedestrians is considered essential information which can be used to control a person who makes a entrance or a exit into a building. The number of pedestrians, also, can be used to help to manage pedestrian traffic and the volume of pedestrian flow within the building. Due to the fact there is incorrect detection by occluded, shadows, and illumination, however, difficulty can arise in existing system which is for detection and counts of a person who makes a entrance or a exit into a building. In this paper, it is minimized that the change of illumination and the effect of shadow through the transmitted image from camera which is created and processed with great adaptability. The accuracy of the calculations can be increase as well by using Kalman Filter and Mean-Shift Algorithm in order to avoid overlapped counts. As a result of the test, it is proved that the count method that shows the accuracy of 95.4% should be effective for detection and counts.

• Journal of KIISE:Software and Applications
• /
• v.36 no.2
• /
• pp.122-130
• /
• 2009

Conventional approaches for car number plate detection have dealt with those input images having similar sizes and simple background acquired under well organized environment. Thus their performance get reduced when input images include number plates with different sizes and when they are acquired under different lighting conditions. To solve these problem, this paper proposes a new scheme that uses the geometrical features of number plates and their topological information with reference to other features of the car. In the first step, those edges constructing a rectangle are detected and several pixels neighboring those edges are selected as the seed pixels for region growing. For region growing, color and intensity are used as the features, and the result regions are merged to construct the candidate for a number plate if their features are within a certain boundary. Once the candidates for the number plates are generated then their topological relations with other parts of the car such as lights are tested to finally determine the number plate region. The experimental results have shown that the proposed method can be used even for detecting small size number plates where characters are not visible.

• Journal of Distribution Science
• /
• v.14 no.8
• /
• pp.153-160
• /
• 2016

Purpose - The current distribution enterprises have realized the necessity for integrated and specialized images in their stores. From those reasons, visual merchandising has been considered as a powerful means towards brand value judgement as well as maximizing both brand and corporate identity. This research intends to study and discuss the current situations in Korean visual merchandising and its future concept setting. Based on the research findings, this paper tries to propose the basic concept for development strategies of visual merchandising in Korean distribution market. Although the studies on visual merchandising in Korean traditional markets have been continued, visual merchandisers have been distorted by display control centers in real situations. Therefore, this study tries to set both current and future concepts in visual merchandising for further discussions and a new complement formulation. Research design, data, and methodology - This study has investigated previous studies with the way of normative study by comparing, organizing concepts and relating terms on visual merchandising. In order to be an exact research, it seems to be more appropriate to analyze this study with a deductive analysis way rather than inductive as for getting the core of visual merchandising. Besides, this study changed the term 'visual merchandising' into 'VMD', and used it as an unified one. Results - Visual merchandising has an important key in retail planning. With focusing on organizing visual merchandising concepts, it should be adequate for domestic circumstances because there are various visual merchandising concepts with different perspectives. Thus, it is necessary to establish a concept including modern and Korean features through previous studies and data. Visual merchandising can be defined as followings. It enhances the value of shop images from visual aspects and conveys brand concepts effectively. Its task is to plan and manage products sales by combining three merchandising domains such as interior, display, and merchandising. Conclusions - There are some limitations on setting academic concepts in visual merchandising due to its features as to be taken in the field focused studies. More meaningful case studies should be performed as an area of future studies. Therefore, it is necessary to perform an effectiveness analysis on empirical visual merchandising state and present the course of development.