• 로봇학회논문지
• /
• 제3권4호
• /
• pp.263-269
• /
• 2008

Visual odometry is a popular approach to estimating robot motion using a monocular or stereo camera. This paper proposes a novel visual odometry scheme using a stereo camera for robust estimation of a 6 DOF motion in the dynamic environment. The false results of feature matching and the uncertainty of depth information provided by the camera can generate the outliers which deteriorate the estimation. The outliers are removed by analyzing the magnitude histogram of the motion vector of the corresponding features and the RANSAC algorithm. The features extracted from a dynamic object such as a human also makes the motion estimation inaccurate. To eliminate the effect of a dynamic object, several candidates of dynamic objects are generated by clustering the 3D position of features and each candidate is checked based on the standard deviation of features on whether it is a real dynamic object or not. The accuracy and practicality of the proposed scheme are verified by several experiments and comparisons with both IMU and wheel-based odometry. It is shown that the proposed scheme works well when wheel slip occurs or dynamic objects exist.

• 생물환경조절학회지
• /
• 제1권1호
• /
• pp.37-51
• /
• 1992

Quantizing and extracting visual features of mushroom(Lentinus edodes L.) are crucial to the sorting and grading automation, the growth state measurement, and the dried performance indexing. A computer image processing system was utilized for the extraction and measurement of visual features of front and back sides of the mushroom. The image processing system is composed of the IBM PC compatible 386DK, ITEX PCVISION Plus frame grabber, B/W CCD camera, VGA color graphic monitor, and image output RGB monitor. In this paper, an automatic thresholding algorithm was developed to yield the segmented binary image representing skin states of the front and back sides. An eight directional Freeman's chain coding was modified to solve the edge disconnectivity by gradually expanding the mask size of 3$\times$3 to 9$\times$9. A real scaled geometric quantity of the object was directly extracted from the 8-directional chain element. The external shape of the mushroom was analyzed and converted to the quantitative feature patterns. Efficient algorithms for the extraction of the selected feature patterns and the recognition of the front and back side were developed. The developed algorithms were coded in a menu driven way using MS_C language Ver.6.0, PC VISION PLUS library fuctions, and VGA graphic functions.

• International Journal of Contents
• /
• 제11권3호
• /
• pp.47-53
• /
• 2015

Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.

• 인지과학
• /
• 제14권3호
• /
• pp.1-11
• /
• 2003

정지/운동하는 배경자극들 속에서 정지/운동하는 표적을 탐지하는 데 있어서 표적 유형과 망막 이심율의 효과를 알아보기 위해서 두 가지 실험을 수행하였다. 두 실험 모두 시각탐색과제를 사용하였다. 망막 이심율은 1.6$^{\circ}$ 단위로 커지는 5개의 동심원으로 구분하였으며, 표적은 배경자극과 방위차원에서 차이나는 방위 표적과 세부특정에서 차이나는 세부특정 표적이었다. 실험 l에서는 표적과 배경자극이 모두 정지되어있는 상황에서의 탐색을 다루었다. 그 결과 표적 유형과 망막 이심율 사이에 상호작용이 있었다. 정지상황에서 방위 표적은 망막 이심율의 영향을 별로 받지 않는 반면에, 세부특정 표적은 망막 이율이 증가함에 따라서 탐지시간이 일관성 있게 증가하였다. 표적과 배경자극이 모두 운동하는 상황인 실험 2 에서도 둘 사이의 상호작용이 나타냈으나, 그 이유는 실험 1과 극적인 대조를 이루었다. 즉, 운 동 상황에서 방위 표적은 망막 이심율이 증가함에 따라서 탐지시간이 일관성 있게 감소하는 반면, 세부 특징 표적은 망막 이심율의 영향을 거의 받지 않았다. 두 실험의 결과를 항공기나 자동차의 운동과 같은 현실상황과 관련된 합의와 문제점 그리고 향후 연구방향을 논의하였다.

• 한국콘텐츠학회논문지
• /
• 제4권1호
• /
• pp.18-23
• /
• 2004

본 논문에서는 공간주파수 특성과 다중 해상도 특성을 모두 갖는 웨이브릿 변환을 이용하여 각 대역의 특성에 맞는 비주얼 특징을 추출하고 이를 내용기반 영상 검색에 이용하는 새로운 방법을 제시하였다. 웨이브릿 변환된 영상의 최저주파 대역은 원 영상의 근사한 형태로 공간 정보를 충분히 활용할 수 있다. 이를 위해 웨이브릿 계수값과 각 계수간의 공간 정보를 모두 고려한 퍼지 동질성(FH : Fuzzy Homogeneity)를 이용하여 L개의 특징 벡터를 추출하였고, 나머지 고주파 대역의 에너지 값을 이용하여 3개의 특징 벡터를 추출하여 이를 영상 데이터베이스에 저장한다. 질의 시에는 L개의 FH 벡터 중 가장 크기가 큰 10개의 값과 3개의 고주파 대역의 에너지 값을 이용하여 가장 유사한 영상을 검색하였다. 90개의 텍스쳐 영상을 사용해 실험한 결과 좋은 정확성을 보였다.

• 한국항해학회지
• /
• 제15권3호
• /
• pp.25-33
• /
• 1991

One of the main uses for ship simulators is I the field of port design, and an increasing number of simulators, of vary in degree s of fidelity, are being used for this purpose. An essential feature of all such simulators is their visual scene, which must be of sufficient fidelity to convey the key visual cues adequately. This paper examines the ability of a number of experienced mariners to perceive speeds and distances correctly using Computer Generated Imagery visual scenes of different fidelity, compared with their performance at sea.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.145-148
• /
• 1996

In moving object tracking based on the visual sensory feedback, a prerequisite is to determine which feature or which object is to be tracked and then the feature or the object identification precedes the tracking. In this paper, we focus on the object identification not image feature identification. The target identification is realized by finding out corresponding line segments to the hypothesized model segments of the target. The key idea is the combination of the Mahalanobis distance with the geometrica relationship between model segments and extracted line segments. We demonstrate the robustness and feasibility of the proposed target identification algorithm by a moving vehicle identification and tracking in the video traffic surveillance system over images of a road scene.

• 대한음성학회지:말소리
• /
• 제44호
• /
• pp.83-92
• /
• 2002

Speech recognition performance is severly degraded under noisy envrionments. One approach to cope with this problem is audio-visual speech recognition. In this paper, we discuss the experiment results of bimodal speech recongition based on enhanced speech feature vectors using lip information. We try various kinds of speech features as like linear predicion coefficient, cepstrum, log area ratio and etc for transforming lip information into speech parameters. The experimental results show that the cepstrum parameter is the best feature in the point of reconition rate. Also, we present the desirable weighting values of audio and visual informations depending on signal-to-noiso ratio.

• 반도체디스플레이기술학회지
• /
• 제12권2호
• /
• pp.57-61
• /
• 2013

This paper presents adaptive neuro-fuzzy inference based defect detection method for various defect types, such as micro-crack, fingerprint and contamination, in heterogeneously textured surface of polycrystalline solar wafers. Polycrystalline solar wafer consists of various crystals so the surface of solar wafer shows heterogeneously textures. Because of this property the visual inspection of defects is very difficult. In the proposed method, we use local binary feature and fuzzy reasoning for defect detection. Experimental results show that our proposed method achieves a detection rate of 80%~100%, a missing rate of 0%~20% and an over detection (overkill) rate of 9%~21%.

• 로봇학회논문지
• /
• 제17권4호
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.