• 한국산업융합학회 논문집
• /
• 제24권6_1호
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.

• 한국HCI학회논문지
• /
• 제2권2호
• /
• pp.35-43
• /
• 2007

본 논문은 특징검출(feature detection)과 특징해석(feature description) 기법을 이용하여, 영상 매칭 (matching)과 인식(recognition)에 필요한 다양한 파라미터의 변화에 따른 인식률의 차이를 분석하기 위한 실험 내용을 다룬다. 본 논문에서는 영상의 특징분석과 매칭프로세스를 위해, Lowe의 SIFT(Scale-Invariant Transform Feature)를 이용하며, 영상에서 나타나는 특징을 검출하고 해석하여 특징 데이터베이스로 구축한다. 특징 데이터베이스는 구글 어스를 통해 획득한 위성영상으로부터 50여개 건물에 대해 구축되는데, 이는 각 건물 영상으로부터 추출된 특징 점들의 좌표와 128차원의 벡터의 값으로 이루어진 특징 해석데이터로 저장된다. 구축된 데이터베이스는 각 건물에 대한 정보가 태그의 형식으로 함께 저장되는데, 이는 카메라로부터 획득한 입력영상과의 비교를 통해 입력영상이 가리키는 지역 내에 존재하는 건물에 대한 정보를 제공하는 역할을 한다. 실험은 영상 매칭과 인식과정에서 작용하는 내-외부적 요소들을 제시하고, 각 요소의 상태변화에 따라 인식률의 차이를 비교하는 방법으로 진행되었으며, 본 연구의 최종적인 시스템은 모바일기기의 카메라를 이용하여 카메라가 촬영하고 있는 지도상의 객체를 인식하고, 해당 객체에 대한 기본적인 정보를 제공할 수 있다.

• 한국지능시스템학회논문지
• /
• 제7권2호
• /
• pp.34-42
• /
• 1997

본 논문은 산업분야의 군사적으로 많이 사용되고 있는 planar shape의 인식을 스펙트럼 분석기를 이용하여 FFT 스펙트럼으로부터 추출된 3차원 특징 벡터와 신경회로망인 fuzzy ARTMAP을 이용하여 시도되었다. 외곽선 정보를 추출하여 이를 원점으로 이동시키고 각 경계점들과 원점들과의 유클리드 거리를 구하여 이를 다시 FFT스펙트럼과 스펙트럼 분석기를 통하여 3차원 특징 벡터를 추출하였다. 이 3차원 데이터는 이동, 회전, 크기에 무관한 값으로 fuzzy ARTMAP에 입력값으로 사용하였다. Fuzzy ARTMAP은 두개의 fuzzy ART 모듈을 가지고 있으며 위에서 구한 특징 벡터들에 의해 학습되고 실험되어 진다.본 논문에 포함된 실험은 4개의 비행기와 4개의 산업부품을 이용하여 잡음이 섞인 shape의 인식에 있엇 제시된 방법이 좋은 인식률을 기록함을 보여주고 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.73-76
• /
• 2001

It is well-known that the convergence rate gets worse when an input signal to an adaptive filter is correlated. In this paper we propose a new adaptive filtering algorithm that makes the convergence rate highly improved even for highly correlated input signals. By introducing an orthogonal constraint between successive input signal vectors, we overcome the slow convergence problem caused by the correlated input signal. Simulation results show that the proposed algorithm yields highly improved convergence speed and excellent tracking capability under both time-invariant and time varying environments, while keeping both computation and implementation simple.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.375-378
• /
• 2000

In this paper, we propose a novo] content-based image retrieval system using both Hidden Markov Model(HMM) and an improved chain code. The Gaussian Mixture Model(GMM) is applied to statistically model a color information of the image, and Deterministic Annealing EM(DAEM) algorithm is employed to estimate the parameters of GMM. This result is used to segment the given image. We use an improved chain code, which is invariant to rotation, translation and scale, to extract the feature vectors of the shape for each image in the database. These are stored together in the database with each HMM whose parameters (A, B, $\pi$) are estimated by Baum-Welch algorithm. With respect to feature vector obtained in the same way from the query image, a occurring probability of each image is computed by using the forward algorithm of HMM. We use these probabilities for the image retrieval and present the highest similarity images based on these probabilities.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2008년도 제39차 동계학술발표논문집 16권2호
• /
• pp.49-54
• /
• 2009

A fuzzy weighted mean method on a 2D shape recognition system is introduced in this paper. The bispectrum based on third order cumulant is applied to the contour sequence of each image for the extraction of a feature vector. This bispectral feature vector, which is invariant to shape translation, rotation and scale, represents a 2D planar image. However, to obtain the best performance, it should be considered certain criterion on the calculation of weights for the fuzzy weighted mean method. Therefore, a new method to calculate weights using means by differences of feature values and their variances with the maximum distance from differences of feature values. is developed. In the experiments, the recognition results with fifteen dimensional bispectral feature vectors, which are extracted from 11.808 aircraft images based on eight different styles of reference images, are compared and analyzed.

• ETRI Journal
• /
• 제38권3호
• /
• pp.502-509
• /
• 2016

Feature detection and description are key ingredients of common image processing and computer vision applications. Most existing algorithms focus on robust feature matching under challenging conditions, such as inplane rotations and scale changes. Consequently, they usually fail when the scene is blurred by camera shake or an object's motion. To solve this problem, we propose a new feature description algorithm that is robust to image blur and significantly improves the feature matching performance. The proposed algorithm builds a feature descriptor by considering the integral projection along four angular directions ($0^{\circ}$, $45^{\circ}$, $90^{\circ}$, and $135^{\circ}$) and by combining four projection vectors into a single highdimensional vector. Intensive experiment shows that the proposed descriptor outperforms existing descriptors for different types of blur caused by linear motion, nonlinear motion, and defocus. Furthermore, the proposed descriptor is robust to intensity changes and image rotation.

• 대한전자공학회논문지SP
• /
• 제45권2호
• /
• pp.90-94
• /
• 2008

적응 필터의 입력 신호의 상관도 (correlation)가 클 경우 LMS 알고리즘의 수렴 속도는 상당히 느려지게 된다. 본 논문에서는 입력 신호의 상관도가 높은 상황에서 수렴 속도를 향상시킬 수 있는 적응 필터링 알고리즘을 제안한다. 입력 신호에 대하여 직교성을 가지도록 변환을 인위적으로 가하여 LMS 알고리즘의 한계를 극복한다. 제안한 알고리즘의 성능 향상은 시스템식별 모델을 통하여 그 수렴 속도의 개선을 확인하며 또한 시변 환경 하에서 적응 필터의 시변 추적 능력을 통해 보여 진다.

• 한국정밀공학회지
• /
• 제16권10호
• /
• pp.194-202
• /
• 1999

A method for pattern recognition based on wavelet transform is proposed in this paper. The boundary of the object to be recognized includes shape information for object of machine parts. The contour is first represented using a one-dimensional signal and normalized about translation, rotation and scale, then is used to build the wavelet transform representation of the object. Wavelets allow us to decompose a function into multi-resolution hierarchy of localized frequency bands. The recognition of 2-dimensional object based on the wavelet is described to analyze the shape of analysis technique; the discrete wavelet transform(DWT). The feature vectors obtained using wavelet analysis is classified using a multi-layer neural network. The results show that, compared with the use of fourier descriptors, recognition using wavelet is more stable and efficient representation. And particularly the performance for objects corrupted with noise is better than that of other method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2930-2932
• /
• 2000

In this paper. a robust gesture recognition system is designed and implemented to explore the communication methods between human and computer. Hand gestures in the proposed approach are used to communicate with a computer for actions of a high degree of freedom. The user does not need to wear any cumbersome devices like cyber-gloves. No assumption is made on whether the user is wearing any ornaments and whether the user is using the left or right hand gestures. Image segmentation based upon the skin-color and a shape analysis based upon the invariant moments are combined. The features are extracted and used for input vectors to a radial basis function networks(RBFN). Our "Puppy" robot is employed as a testbed. Preliminary results on a set of gestures show recognition rates of about 87% on the a real-time implementation.