• 센서학회지
• /
• 제33권2호
• /
• pp.98-104
• /
• 2024

This study proposes a method to overcome the limited detection range of short-baseline stereo cameras (SBSCs). The proposed method includes two steps: (1) predicting an unscaled initial depth using monocular depth estimation (MDE) and (2) adjusting the unscaled initial depth by a scale factor. The scale factor is computed by triangulating the sparse visual keypoints extracted from the left and right images of the SBSC. The proposed method allows the use of any pre-trained MDE model without the need for additional training or data collection, making it efficient even when considering the computational constraints of small platforms. Using an open dataset, the performance of the proposed method was demonstrated by comparing it with other conventional stereo-based depth estimation methods.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집C
• /
• pp.426-431
• /
• 2001

When we use various multimedia programs such as 3D-game, visual conference, dial-pad phone by internet service, we make use of headset generally. As internet system is magnified more and more, a demand of headset will be increasing continuously. Because microphone was fixed by headset, it has many inconveniences for using headset. For these reasons, new concept headset is needed nowadays. Main idea of development of headset is very the automatic operation system of microphone. There are many process variables in appling new technology to the conventional headset. They can be solved by using axiomatic approach method which is very useful design method for designing new products. Its main character is scientific and analytical. The goal of this research is to design and manufacture a new headset model with axiomatic design method. In this paper, a new concept headset was presented by mapping the relation between functional requirements and design parameters.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.25-28
• /
• 2003

Fractal mathematics is being highlighted as a research method for classification of image. But the application of Fractal dimension(FB) has been required the complicated calculation method because of its complex repetition progressing. In this paper, it has been developed the new approach method to express the Fractal Dimension(FB) for aging level calculation and estimation system of outside insulator using special image processing algorithm. As a result after FD testing, the recognized aging estimation of FD has a very characteristics compared to the conventional visual inspection.

• 한국멀티미디어학회논문지
• /
• 제20권10호
• /
• pp.1619-1627
• /
• 2017

Image hashing has been successfully applied for the problems associated with the protection of intellectual property, management of large database and indexation of content. For a reliable hashing system, improving hash matching accuracy is crucial. In order to improve the hash matching performance, we propose an asymmetric hash matching method using the psychovisual threshold, which is the maximum amount of distortion that still allows the human visual system to identity an image. A performance evaluation over sets of image distortions shows that the proposed asymmetric matching method effectively improves the hash matching performance as compared with the conventional Hamming distance.

• Journal of information and communication convergence engineering
• /
• 제7권4호
• /
• pp.539-544
• /
• 2009

An estimation of 3D velocity field including occluded parts without maxing tracer to the fluid had not only never been proposed but also impossible by the conventional computer vision algorithm. In this paper, we propose a new method of three dimensional optical flow of the fluid based on physical model, where some boundary conditions are given from a priori knowledge of the flow configuration. Optical flow is obtained by minimizing the mean square errors of a basic constraint and the matching error terms with visual data using Euler equations. Here, Navier-Stokes motion equations and the differences between occluded data and observable data are employed as the basic constrains. we verify the effectiveness of our proposed method by applying our algorithm to simulated data with partly artificially deleted and recovering the lacking data. Next, applying our method to the fluid of observable surface data and the knowledge of boundary conditions, we demonstrate that 3D optical flow are obtained by proposed algorithm.

• 한국지능시스템학회논문지
• /
• 제8권5호
• /
• pp.39-44
• /
• 1998

이동 로봇의 운행을 위해서 이동 로봇의 절대 위치를 결정하는 것이 중요하다. 본 논문에서는 신경회로망을 이용하여 랜드마크의 영상을 통해 이동 로봇의 위치를 결정하는 방법을 제안한다. 픽셀의 불확시한 값, 부정확한 카메라 조정과 렌즈의 왜곡으로 인해 이동 로봇의 위치를 결정에 있어서 위치 오차가 생기게 된다. 이러한 오차를 줄이기 위해서 BPNN(Back Propagation Neural Network)를 사용하는 방법을 제안한다. 기존의 방법과 비교하여 우수성을 보여주기 위해서 실험결과를 보여준다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1875-1878
• /
• 2003

This paper Proposes a wavelet-based video compression method to improve compressed images using modification of wavelet coefficients. In conventional wavelet-based compression methods, bigger coefficients are transmitted early according to the significance of the coefficients. In this reason, when some coefficients which have more significance but are not bigger are not transmitted, image degradation occurs. The Proposed method considered two human visual characteristics. First, human eyes are more sensitive to the change of middle frequency which represents abrupt change of brightness than that of high frequency which expresses fine region. Second, human eyes are more dull to color component than luminance respectively. By adjusting the coefficients of wavelet transformed signals and allocating more bits for compression to the luminance signal, higher compression could be achieved.

• 대한임베디드공학회논문지
• /
• 제10권2호
• /
• pp.101-108
• /
• 2015

In this paper, a robust traffic light detection method is proposed by using vision sensor and DGPS(Difference Global Positioning System). The conventional vision-based detection methods are very sensitive to illumination change, for instance, low visibility at night time or highly reflection by bright light. To solve these limitations in visual sensor, DGPS is incorporated to determine the location and shape of traffic lights which are available from traffic light database. Furthermore the geometric relationship between traffic light and vision sensor is used to locate the traffic light in the image by using DGPS information. The empirical results show that the proposed method improves by 51% in detection rate for night time with marginal improvement in daytime environment.

• Journal of Multimedia Information System
• /
• 제4권2호
• /
• pp.65-73
• /
• 2017

This paper proposes a method to improve the image quality by designing Unsharp Mask Filter (UMF) based on Retinex theory which controls the frequency pass characteristics adaptively. Conventional unsharp masking technique uses blurring image to emphasize sharpness of image. Unsharp Masking(UM) adjusts the original image and sigma to obtain a high frequency component to be emphasized by the difference between the blurred image and the high frequency component to the original image, thereby improving the contrast ratio of the image. In this paper, we design a Unsharp Mask Filter(UMF) that can process the contrast ratio improvement method of Unsharp Masking(UM) technique with one filtering. We adaptively process the contrast ratio improvement using Unsharp Mask Filter(UMF). We propose a method based on Retinex theory for adaptive processing. For adaptive filtering, we control the weights of Unsharp Mask Filter(UMF) based on the human visual system and output more effective results.

• 로봇학회논문지
• /
• 제5권3호
• /
• pp.262-269
• /
• 2010

This paper presents a probabilistic head tracking method, mainly applicable to face recognition and human robot interaction, which can robustly track human head against various variations such as pose/scale change, illumination change, and background clutters. Compared to conventional particle filter based approaches, the proposed method can effectively track a human head by regularizing the sample space and sequentially weighting multiple visual cues, in the prediction and observation stages, respectively. Experimental results show the robustness of the proposed method, and it is worthy to be mentioned that some proposed probabilistic framework could be easily applied to other object tracking problems.