• ETRI Journal
• /
• 제39권2호
• /
• pp.151-162
• /
• 2017

With the remarkable growth in rich media in recent years, people are increasingly exposed to visual information from the environment. Visual information continues to play a vital role in rich media because people's real interests lie in dynamic information. This paper proposes a novel discrete dynamic swarm optimization (DDSO) algorithm for video object tracking using invariant features. The proposed approach is designed to track objects more robustly than other traditional algorithms in terms of illumination changes, background noise, and occlusions. DDSO is integrated with a matching procedure to eliminate inappropriate feature points geographically. The proposed novel fitness function can aid in excluding the influence of some noisy mismatched feature points. The test results showed that our approach can overcome changes in illumination, background noise, and occlusions more effectively than other traditional methods, including color-tracking and invariant feature-tracking methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2036-2038
• /
• 2001

In this paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using vision system. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Also, we use R,G,B(red, green, blue) color image data and the gray image data to get the highly trust rate of feature point extraction. For this, we propose an algorithm to extract four feature points (eyebrow, eye, nose, mouth) from the face image acquired by the color CCD camera and find some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector(position and distance among the feature points). Finally, we show the practical application possibility of the proposed method.

• 한국멀티미디어학회논문지
• /
• 제5권2호
• /
• pp.158-166
• /
• 2002

본 논문에서는 윤곽선 세그먼트의 양 끝점을 잇는 직선과 곡선의 길이의 비율로 윤곽선 변동율을 정의하고, 이로부터 윤곽선의 형태를 기술하는 방법을 제안하였다. 윤곽선 변동율은 윤곽선 세그먼트로부터 계산되기 때문에 회전이나 크기 변형에 불변하는 윤곽선 세그먼트를 추출해야 한다. 이를 위하여 전체 윤곽선의 길이에 비례하는 상대적인 길이로 윤곽선을 분할하고 윤곽선 상의 모든 점을 분할점으로 하는 중첩된 윤곽선 세그먼트를 이용하였다. 윤곽선 변동율은 윤곽선 세그먼트의 단위 길이에 따라 국소적 또는 전역적인 특징을 나타내므로, 윤곽선 변동율의 분포를 나타내는 특징 벡터로 물체의 형태를 기술하고, 단위 길이별로 특징 벡터를 비교하여 윤곽선 형태의 유사도를 계산한다. 제안된 방법을 구현하여 15종의 물고기 영상에 대하여 회전 및 크기 변형을 가한 총 165개의 영상에 대하여 실험한 결과, 회전 및 크기 변형에 대한 불변성은 물론 정규화된 체인코드 히스토그램(NCCH)과 링 프로젝션(TRP)을 이용한 방법에 비하여 군집화 능력이 우수함을 확인할 수 있었다.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.91-100
• /
• 2023

The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권12호
• /
• pp.525-530
• /
• 2022

두 개의 점군(point cloud)을 정렬(alignment)하기 위해 현재까지 ICP(iterative closest point) 알고리즘이 널리 사용되고 있지만, ICP는 두 점군의 초기 방향이 크게 다를 경우 정렬에 실패하는 경우가 많다. 본 논문에서는 두 개의 삼각형 메쉬 A, B가 서로 크게 다른 초기 방향을 가질 때, 이들을 정렬하는 알고리즘을 제안한다. 메쉬 A, B에 대해 각각 가중치 무게중심(weighted centroid)을 구한 뒤, 무게중심으로부터 정점까지의 거리를 이용하여 메쉬 간에 서로 대응될 가능성이 있는 정점들을 특징점으로 설정한다. 설정된 특징점들이 대응될 수 있도록 메쉬 B를 회전한 뒤, A와 B의 정점들에 대해 RMSD(root mean square deviation)를 측정한다. RMSD가 기준치보다 작은 값을 가질 때까지 특징점을 변경하며 같은 과정을 되풀이하여 정렬된 결과를 얻는다. 실험을 통해 ICP 및 Go-ICP 알고리즘으로 정렬이 실패할 경우에도 제안된 알고리즘으로 정렬이 가능함을 보인다.

• Smart Structures and Systems
• /
• 제25권5호
• /
• pp.631-641
• /
• 2020

To meet the urgent requirements of safety surveillance from civil engineering management authorities, this study proposes a refined and efficient approach to generate full-field high-resolution panorama of construction sites using camera-amounted UAV (Unmanned Aerial Vehicle). GPS (Global Position System) information extraction for pre-registration, feature points filtering for efficient registration and optimal seaming line seeking for fusion are performed in sequence to form the full-field panorama generation framework. Advantages of the proposed method are as follows. First, GPS information can sort images for pre-registration, avoiding inefficient repeated pairwise calculations and matching. Second, the feature points are filtered according to the characteristics of the construction site images to reduce the amount of calculation. The proposed framework is validated on a road construction site and results demonstrate that it can generate an accurate and high-quality full-site panorama for the safety supervision in a much efficient manner.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 하계종합학술대회논문집
• /
• pp.269-272
• /
• 2000

It is need to develop and apply a human pulse diagnosis system providing a quantitative and automatic analysis in the the oriental medicine. In order to analyze quantitatively the characteristic of pulsation, each of points had to be recognized accurately notifying the existence and the position of feature point in the wave form. And getting the period of human pulse. Thus, in this paper, it is proposed the preprocessing method of human pulse and the detection method of period by Wavelet Transformation. The human pulse is seprated from each band through Wavelet Transformation and feature points can be recognized through over the fact, and then the parameter of proposed Mac-Jin parameter is measured. Commonly, Human pulse signal has often various noises which are baseline drift, high frequency noise and so on. So it is significant to remove that noises. Thus, in this paper, the one period of human pulse is deciede and the feature points are detected after doing the preprocessing by wavelet transformation. As a result, it could be confirmed that this method is effective as a real program for the auto-diagnosis of human pulse.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.226-228
• /
• 2021

구글사에서 출시된 ML Kit API의 Pose detection를 사용한 영상기반 낙상 알고리즘을 제안한다. Pose detection 알고리듬을 사용하여 추출된 신체의 33개의 3차원 특징점을 활용하여 낙상을 인식한다. 추출된 특징점을 분석하여 낙상을 인식하는 알고리듬은 k-NN을 사용한다. 영상의 크기와 영상내의 인체의 크기에 영향을 받지 않도록 정규화과정을 거치며 특징점들의 상대적인 움직임을 분석하여 낙상을 인식한다. 본 실험을 위해 사용한 13개의 테스트 영상중 13개의 영상에서 낙상을 인식하여 100%의 성공률을 보였다.

• Smart Structures and Systems
• /
• 제33권2호
• /
• pp.105-118
• /
• 2024

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.

• 한국통신학회논문지
• /
• 제39C권10호
• /
• pp.957-966
• /
• 2014

Video Stabilization For Vehicular Applications Is An Important Method Of Removing Unwanted Shaky Motions From Unstable Videos. In This Paper, An Improved Video Stabilization Method With Image Stitching Has Been Proposed. Scale Invariant Feature Transform (Sift) Matching Is Used To Calculate The New Position Of The Points In Next Frame. Image Stitching Is Done In Every Frame To Get Stabilized Frames To Provide Stable Video As Well As A Better Understanding Of The Previous Frame'S Position And Show The Surrounding Objects Together. The Computational Complexity Of Sift (Scale-Invariant Feature Transform) Is Reduced By Reducing The Sift Descriptors Size And Resticting The Number Of Keypints To Be Extracted. Also, A Modified Matching Procedure Is Proposed To Improve The Accuracy Of The Stabilization.