• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1026-1034
• /
• 2021

Tire wear and defect are important factors for safe driving condition. These defects are generally inspected by some specialized experts or very expensive equipments such as stereo depth camera and depth gauge. In this paper, we propose tire safety vision inspector based on deep neural network (DNN). The status of tire wear is categorized into three: 'safety', 'warning', and 'danger' based on depth of tire tread. We propose an attention mechanism for emphasizing the feature of tread area. The attention-based feature is concatenated to output feature maps of the last convolution layer of ResNet-101 to extract more robust feature. Through experiments, the proposed tire wear classification model improves 1.8% of accuracy compared to the existing ResNet-101 model. For detecting the tire defections, the developed tire defect detection model shows up-to 91% of accuracy using the Mask R-CNN model. From these results, we can see that the suggested models are useful for checking on the safety condition of working tire in real environment.

• Journal of the Optical Society of Korea
• /
• v.19 no.4
• /
• pp.390-396
• /
• 2015

We propose a partial occlusion removal method for computational integral imaging reconstruction (CIIR) based on the usage of the exemplar based inpainting technique. The proposed method is an improved version of the original linear inpainting based CIIR (LI-CIIR), which uses the inpainting technique to fill in the data missing region. The LI-CIIR shows good results for images which contain objects with smooth surfaces. However, if the object has a textured surface, the result of the LI-CIIR deteriorates, since the linear inpainting cannot recover the textured data in the data missing region well. In this work, we utilize the exemplar based inpainting to fill in the textured data in the data missing region. We call the proposed method the neighboring elemental image exemplar based inpainting (NEI-exemplar inpainting) method, since it uses sources from neighboring elemental images to fill in the data missing region. Furthermore, we also propose an automatic occluding region extraction method based on the use of the mutual constraint using depth estimation (MC-DE) and the level set based bimodal segmentation. Experimental results show the validity of the proposed system.

• The Journal of Fisheries Business Administration
• /
• v.47 no.3
• /
• pp.1-14
• /
• 2016

The purpose of this research paper is to segment seafood market and find the factor and process that divide the segment market. Cluster analysis and in-depth interview was performed to identify meaningful segment market. The result of the research found three segment market such as seafood integration familiarity group, domestic seafood familiarity group, seafood unfamiliarity group. Seafood integration familiarity group is active consumer that consume both domestic and imported seafood at home. This group have high preference and familiarity about seafood. Seafood familiarity group purchase imported seafood for the reason that imported seafood is cheaper than domestic seafood and have similar quality level. Domestic seafood familiarity group consume mostly domestic seafood and not purchase imported seafood for the reason that imported seafood have low quality and safety. This group have high preference and familiarity about seafood. Seafood unfamiliarity group is low preference group about seafood and seldom eat at home. This study found that the main factor that divide segment market is seafood familiarity that formed by experiencing seafood in youth and seafood familiarity is main factor that determine consumption degree of seafood at home.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8B
• /
• pp.1469-1476
• /
• 2000

We have to consider the drain current as consisting of two components the vertical electric field and the longitudinal electric field because the drain current is almost totally due to the presence of drift in strong inversion of n-MOS FET. Especially the mobility of electrons in the inversion layer is smaller than the bulk mobility because the vertical electric field component that is generated by the effect of the gate voltage is perpendicular to the direction of normal current flow. By the multi-box segmentation technical method that are proposed in this paper we calculated the inversion layer depth and analyzed the vertical electric field component which has an large influence on mobility model.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.163-170
• /
• 2013

In general, images of outdoor scenes often contain degradation due to dust, water drop, haze, fog, smoke and so on, as a result they cause the contrast reduction and color fading. Haze removal is not easier problem due to the inherent ambiguity between the haze and the underlying scene. So, we propose a novel method to solve single scene dehazing problem using the region segmentation based on graph algorithm that has used a gradient value as a cost function. We segment the scene into different regions according to depth-related information and then estimate the global atmospheric light. The medium transmission can be directly estimated by the threshold function of graph-based segmentation algorithm. After estimating the medium transmission, we can restore the haze-free scene. We evaluated the degree of the visibility restoration between the proposed method and the existing methods by calculating the gradient of the edge between the restored scene and the original scene. Results on a variety of outdoor haze scene demonstrated the powerful haze removal and enhanced image quality of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.135-144
• /
• 2018

The domestic pigsty environment is highly vulnerable to the spread of respiratory diseases such as foot-and-mouth disease because of the small space. In order to manage this issue, a variety of studies have been conducted to automatically analyze behavior of individual pigs in a pig pen through a video surveillance system using a camera. Even though it is required to correctly segment touching pigs for tracking each pig in complex situations such as aggressive behavior, detecting the correct boundaries among touching pigs using Kinect's depth information of lower accuracy is a challenging issue. In this paper, we propose a segmentation method using motion information of the touching pigs. In addition, our proposed method can be applied for detecting tracking errors in case of tracking individual pigs in the complex environment. In the experimental results, we confirmed that the touching pigs in a pig farm were separated with the accuracy of 86%, and also confirmed that the tracking errors were detected accurately.

• Smart Media Journal
• /
• v.3 no.1
• /
• pp.52-62
• /
• 2014

Prevalence of common three-dimensional display progresses, increasing the demand for three-dimensional content. Starting from the year 2010 to meet increasing 2D to 3D conversion is insufficient to meet demand content was presented as an alternative. But, Convert 2D to 3D stereo effect only emphasizes content production as a three-dimensional visual fatigue and the degradation of the Quality problems are pointed out. In this study, opened in 2011 'Scenes Guan', the 13 selected Scene is made of the three-dimensional transform the content and the Quality of the transformation applied to the Depth-Map is a visual representation of three-dimensional fatigue and, the adequacy of whether the expert has group interviews and surveys were conducted. Many of the changes are applied to the motion picture of the three-dimensional configurations of Depth-Map conversion technology used in many ways before and after the analysis of the relationship of cascade configurations to create a depth map to the stage. Experiments, presented in this study is a three-dimensional configuration of Depth-Map transformation can lower the production of a three-dimensional visual fatigue and improve the results obtained for a reasonable place was more than half of the experiment accepted the expert group to show a positive reaction were. The results of this study with a rapid movement to convert 2D images into 3D images of applying Depth-map configuration cascade manner to reduce the visual fatigue, to increase the efficiency, and has a three-dimensional perception is the result derived.

• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.255-264
• /
• 2011

In this paper, we propose a forward vehicle detection algorithm using column detection and bird's-eye view mapping based on stereo vision. The algorithm can detect forward vehicles robustly in real complex traffic situations. The algorithm consists of the three steps, namely road feature-based column detection, bird's-eye view mapping-based obstacle segmentation, obstacle area remerging and vehicle verification. First, we extract a road feature using maximum frequent values in v-disparity map. And we perform a column detection using the road feature as a new criterion. The road feature is more appropriate criterion than the median value because it is not affected by a road traffic situation, for example the changing of obstacle size or the number of obstacles. But there are still multiple obstacles in the obstacle areas. Thus, we perform a bird's-eye view mapping-based obstacle segmentation to divide obstacle accurately. We can segment obstacle easily because a bird's-eye view mapping can represent the position of obstacle on planar plane using depth map and camera information. Additionally, we perform obstacle area remerging processing because a segmented obstacle area may be same obstacle. Finally, we verify the obstacles whether those are vehicles or not using a depth map and gray image. We conduct experiments to prove the vehicle detection performance by applying our algorithm to real complex traffic situations.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2014

The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.60-65
• /
• 2013

In this paper, we propose a high-resolution disparity map generation method using a low-resolution time-of-flight (TOF) depth camera and color camera. The TOF depth camera is efficient since it measures the range information of objects using the infra-red (IR) signal in real-time. It also quantizes the range information and provides the depth image. However, there are some problems of the TOF depth camera, such as noise and lens distortion. Moreover, the output resolution of the TOF depth camera is too small for 3D applications. Therefore, it is essential to not only reduce the noise and distortion but also enlarge the output resolution of the TOF depth image. Our proposed method generates a depth map for a color image using the TOF camera and the color camera simultaneously. We warp the depth value at each pixel to the color image position. The color image is segmented using the mean-shift segmentation method. We define a cost function that consists of color values and segmented color values. We apply a weighted average filter whose weighting factor is defined by the random walk probability using the defined cost function of the block. Experimental results show that the proposed method generates the depth map efficiently and we can reconstruct good virtual view images.