• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.813-816
• /
• 2008

In this research we present a method to reconstruct the casting flow simulation result as a 3D model and visualize it on a VR display. First, numerical analysis of heat flow is performed using an existing commercial CAE simulation software. In this process the shape of the original design model is approximated to a regular rectangular grid. The filling ratio and temperature of each voxel are recorded iteratively by predefined number of steps starting from pouring the melted metal into a mold until it is entirely filled. Next we reconstruct the casting by voxels using the simulation result as an input. The color of voxel is determined by mapping the colors to temperature and filling ratio at each step as the flow proceeds. The reconstructed model is visualized on the Projection Table which is one of horizontal-type VR display. It provides active stereoscopic images.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1255-1255
• /
• 2001

The study used 356 veal calf meat samples received from Finland (n=16), France (n=109), Italy (n=81) and The Netherlands (n=150). Calves were raised under experimental protocols that compared feeding and housing practices normally used in each county to treatments aiming at improving animal welfare. Samples were taken at the $8^{th}$ rib of Longissimus thoracis muscle 24h after slaughter, They were kept refrigerated ( $2-4^{\circ}C$) under vacuum package for 6d and then frozen ($-20^{\circ}C$) until meat quality evaluation. Measurements included pH, color (Hunter Lab system), shear force, chemical composition (DM, Ash, Ether Extract, collagen and haematin content), weight and area cooking losses and a sensory evaluation by a group of panelists. A sample of meat was ground with a blade mill and scanned in duplicate between 1100 and 1498 nm (FOSS NIR Systems 5000). WinISI software was used to develop a discriminating equation using NIR spectra (SNV-detrend, derivative=1, gap=4nm, smooth=4nm). The Proc ANOVA and DISCRIM of SAS were used for all the laboratory determinations. County of production had a significant (P<0.01) effect on all the parameters. However, discriminant analysis using any or few laboratory parameters resulted in great errors of county classification. A more accurate (98.8%) classification was obtained only when using all the laboratory parameters. NIRS classified correctly 354 of the 356 samples (99.4%). Provided with a larger data set, NIRS could be used to identify country of production of veal meat.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.492-500
• /
• 2012

In this paper, improved contour region coding method is proposed to accomplish better depth map coding performance. First of all, in order to use correlation between color video and depth map, a structure in SVC is applied to 3DVC. This can reduce bit-rate of the depth map while supporting the video to be transferred via various collection of network. As the depth map is mainly used to synthesize videos from different views, corrupted contour region can damage the overall quality of video. We hereby adapt a new differential quantization method when separating the contour region. The experimental results show that the proposed method can improve video quality by 0.06~0.5dB which translate the bit rate saving by 0.1~1.15%, when compared to the reference software.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1415-1429
• /
• 2019

Nowadays object tracking process becoming one of the most challenging task in Computer Vision filed. A CSR-DCF (channel spatial reliability-discriminative correlation filter) tracking algorithm have been proposed on recent tracking benchmark that could achieve stat-of-the-art performance where channel spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process with only two simple standard features, HoGs and Color names. However, there are some cases where this method cannot track properly, like overlapping, occlusions, motion blur, changing appearance, environmental variations and so on. To overcome that kind of complications a new modified version of CSR-DCF algorithm has been proposed by integrating deep learning based object detection and CSRT tracker which implemented in OpenCV library. As an object detection model, according to the comparable result of object detection methods and by reason of high efficiency and celerity of Faster RCNN (Region-based Convolutional Neural Network) has been used, and combined with CSRT tracker, which demonstrated outstanding real-time detection and tracking performance. The results indicate that the trained object detection model integration with tracking algorithm gives better outcomes rather than using tracking algorithm or filter itself.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2949-2955
• /
• 2015

Recently, with the sharp increase of digital visual media such as photographs, animations, and digital videos, it has been necessary to generate mosaic blocks in a static or dynamic image intentionally or unintentionally. In this paper, we suggest a new method for detecting mosaic blocks contained in a color image using boundary features. The suggested method first extracts Canny edges in the image and finds candidate mosaic blocks with the boundary features of mosaic blocks. The method then determines real mosaic blocks after filtering out non-mosaic blocks using geometric features like size and elongatedness features. Experimental results show that the proposed method can detect mosaic blocks robustly rather than other methods in various types of input images.

• Journal of KIISE:Software and Applications
• /
• v.29 no.12
• /
• pp.957-965
• /
• 2002

Garbage collection in the CLDC typically employs a stop-the-world GC algorithm which is performing a complete garbage collection when needed. This technique is unsuitable for the interactive Java embedded system because this can lead to long and unpredictable delays. In this paper, We present a garbage collection algorithm which reduces the average delay time and supports the interactive environment. Our garbage collector is composed of the allocator and the collector. The allocator determines the allocation position of free-list according to object size, and the collector uses an incremental mark-sweep algorithm. The garbage collector is called periodically by the thread scheduling policy and the allocator allocates the objects of marked state during collection cycle. Also, we introduce a color toggle mechanism that changes the meaning of the bit patterns at the end of the collection cycle. We compared the performance of our implementation with stop-the-world mark-sweep GC. The experimental results show that our algorithm reduces the average delay time and that it provides uniformly low response times.

• Journal of KIISE:Software and Applications
• /
• v.26 no.12
• /
• pp.1519-1530
• /
• 1999

오늘날 멀티미디어 정보의 양이 매우 빠른 속도로 증가함에 따라 멀티미디어 데이타베이스에 대한 효율적인 관리는 더욱 중요한 의미를 가지게 되었다. 게다가 영상과 같은 비 문자형태의 데이타에 대한 사용자들의 내용기반 검색욕구 증가로 인해 비디오 인덱싱에 대한 관심은 더욱 고조되고 있다. 따라서 본 논문에서는 우선적으로 분할된 샷 경계면에서 추출된 대표 프레임과 정지 영상 데이타베이스로부터 유사 영상과 유사 대표 프레임을 검색할 수 있는 환경을 제공한다. 우선적으로 영상에 의한 질의는 기존에 주로 사용되어온 색상 히스토그램방식을 탈피하여 본 논문에서 제안하는 CS와 GS방식을 이용하여 색상 및 방향성 정보도 고려하도록 설계하였다. 또한 얼굴에 의한 질의는 대표 프레임으로부터 얼굴 영역을 추출해 내고 얼굴의 경계선 값 및 쌍 직교 웨이블릿 변환에 의해 얻어진 2개의 특징값을 이용하여 유사 인물이 포함된 대표 프레임을 검색해 내도록 설계하였다. Abstract There is a rapid increase in the use of digital video information in recent years, it becomes more important to manage multimedia databases efficiently. There is a big concern about video indexing because users require content-based image retrieval. In this paper, we first propose query-by-image system environment which allows to retrieve similar images from the chosen representative frames or images from the image databases. This algorithm considers not only the discretized color histogram but also the proposed directional information called CS & GS method. Finally, we designe another query environment using query-by-face. In this system , user selects a people in the representative frame browser and then system extracts a face region from that frame. After that system retrieves similar representative frames using 2 features, edge information and biorthogonal wavelet transform.

• 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 KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.712-721
• /
• 2010

This paper proposes a new fire-flame detection method using probabilistic membership function of visual features and Fuzzy Finite Automata (FFA). First, moving regions are detected by analyzing the background subtraction and candidate flame regions then identified by applying flame color models. Since flame regions generally have continuous and an irregular pattern continuously, membership functions of variance of intensity, wavelet energy and motion orientation are generated and applied to FFA. Since FFA combines the capabilities of automata with fuzzy logic, it not only provides a systemic approach to handle uncertainty in computational systems, but also can handle continuous spaces. The proposed algorithm is successfully applied to various fire videos and shows a better detection performance when compared with other methods.