• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.525-530
• /
• 2022

Although the iterative closest point (ICP) algorithm has been widely used to align two point clouds, ICP tends to fail when the initial orientation of the two point clouds are significantly different. In this paper, when two triangular meshes A and B have significantly different initial orientations, we present an algorithm to align them. After obtaining weighted centroids for meshes A and B, respectively, vertices that are likely to correspond to each other between meshes are set as feature points using the distance from the centroid to the vertices. After rotating mesh B so that the feature points of A and B to be close each other, RMSD (root mean square deviation) is measured for the vertices of A and B. Aligned meshes are obtained by repeating the same process while changing the feature points until the RMSD is less than the reference value. Through experiments, we show that the proposed algorithm aligns the mesh even when the ICP and Go-ICP algorithms fail.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.134-141
• /
• 2014

Mobile robots use various sensors for navigation such as wheel encoder, vision sensor, sonar, and laser sensors. Dead reckoning is used with wheel encoder, resulting in the accumulation of positioning errors. For that reason wheel encoder can not be used alone. Too much information of vision sensors leads to an increase in the number of features and complexity of perception scheme. Also Sonar sensor is not suitable for positioning because of its poor accuracy. On the other hand, laser sensor provides accurate distance information relatively. In this paper we propose to extract the angular information from the distance information of laser range finder and use the Kalman filter that match the heading and distance of the laser range finder and those of wheel encoder. For laser scanner with one feature point error may increase much when the feature point is variant or jumping to a new feature point. To solve the problem, we propose to use two feature points and show that the positioning error can be reduced much.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.190-193
• /
• 2000

In this paper, we investigate the distribution of classification accuracies of multiclass problems in the feature space and analyze performances of the conventional feature extraction algorithms. In order to find the distribution of classification accuracies, we sample the feature space and compute the classification accuracy corresponding to each sampling point. Experimental results showed that there exist much better feature sets that the conventional feature extraction algorithms fail to find. In addition, the distribution of classification accuracies is useful for developing and evaluating the feature extraction algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.3
• /
• pp.317-327
• /
• 2016

The extraction of significant feature points from a video is directly associated with the suggested method's function. In particular, the occlusion regions in trees or people, or feature points extracted from the background and not from objects such as the sky or mountains are insignificant and can become the cause of undermined matching or recognition function. This paper classifies the feature points required for building recognition by using multi-frames in order to improve the recognition function(algorithm). First, through SIFT(scale invariant feature transform), the primary feature points are extracted and the mismatching feature points are removed. To categorize the feature points in occlusion regions, RANSAC(random sample consensus) is applied. Since the classified feature points were acquired through the matching method, for one feature point there are multiple descriptors and therefore a process that compiles all of them is also suggested. Experiments have verified that the suggested method is competent in its algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6C
• /
• pp.492-496
• /
• 2012

This paper presents a decoding technique for speech recognition using uncertainty information from feature compensation method to improve the speech recognition performance in the low SNR condition. Traditional feature compensation algorithms have difficulty in estimating clean feature parameters in adverse environment. Those algorithms focus on the point estimation of desired features. The point estimation of feature compensation method degrades speech recognition performance when incorrectly estimated features enter into the decoder of speech recognition. In this paper, we apply the uncertainty information from well-known feature compensation method, such as IMM, to the recognition engine. Applied technique shows better performance in the Aurora-2 DB.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.1
• /
• pp.58-63
• /
• 2020

This paper proposes the method for improving the localization accuracy of the mobile robot based on the stereo camera. To restore the position information from stereo images obtained by the stereo camera, the corresponding point which corresponds to one pixel on the left image should be found on the right image. For this, there is the general method to search for corresponding point by calculating the similarity of pixel with pixels on the epipolar line. However, there are some disadvantages because all pixels on the epipolar line should be calculated and the similarity is calculated by only pixel value like RGB color space. To make up for this weak point, this paper implements the method to search for the corresponding point simply by calculating the gap of x-coordinate when the feature points, which are extracted by feature extraction and matched by feature matching method, are a pair and located on the same y-coordinate on the left/right image. In addition, the proposed method tries to preserve the number of feature points as much as possible by finding the corresponding points through the conventional algorithm in case of unmatched features. Because the number of the feature points has effect on the accuracy of the localization. The position of the mobile robot is compensated based on 3-D coordinates of the features which are restored by the feature points and corresponding points. As experimental results, by the proposed method, the number of the feature points are increased for compensating the position and the position of the mobile robot can be compensated more than only feature extraction.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.173-179
• /
• 2014

Today, a surgery for cataract of Korean society frequently come to operation. A method for treating cataracts have been developed in various ways. Widely used method is a method to use the artificial lens and replace it with the existing lens. The surgery can be inserted exactly according to the angle and points that are calculated in advance in the intraocular lens insertion is important. However, The lens insertion point can delete or blur the display due to such factors as foreign material coming out of the eye during surgery. Therefore, The lens insertion point needs a method of tracking the image processing by receiving the camera images in real time display method. In this paper, we propose a feature point tracking method by using template matching and buffer. a simulation results show that our ideas can track a feature point of the intraocular lens insertion.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.297-298
• /
• 2013

본 논문에서는 IR 영상추적을 위하여 가린 표적의 실제 중심을 예측하는 추적창 조절(target window adjustment) 기법을 제시한다. 대표적 분할 추적(patch tracking) 방식인 특징점 추적(feature point tracking)은 표적의 중심과 특징점을 coupling하여 가린 표적의 실제 중심을 예측할 수 있으나, 형상 정보가 적은 영상에서 표적의 ROI(Region of Interest)는 특징점의 분포만으로는 구할 수 없다. 본 논문에서는 상관추적의 추적창 조절 기법과 특징점 추적의 coupling 기법을 결합하여 표적이 장애물에 가리는 경우에도 안정적인 추적창을 유지한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.297-301
• /
• 2005

In this paper, we propose a method to estimate camera motion parameter based on invariant point features. Typically, feature information of image has drawbacks, it is variable to camera viewpoint, and therefore information quantity increases after time. The LM(Levenberg-Marquardt) method using nonlinear minimum square evaluation for camera extrinsic parameter estimation also has a weak point, which has different iteration number for approaching the minimal point according to the initial values and convergence time increases if the process run into a local minimum. In order to complement these shortfalls, we, first propose constructing feature models using invariant vector of geometry. Secondly, we propose a two-stage calculation method to improve accuracy and convergence by using homography and LM method. In the experiment, we compare and analyze the proposed method with existing method to demonstrate the superiority of the proposed algorithms.

• KIEE International Transaction on Systems and Control
• /
• v.12D no.1
• /
• pp.7-11
• /
• 2002

In this study, fur the shape-based image retrieval, a method using local differential invariants is proposed. This method calculates the differential invariant feature vector at every feature point extracted by Harris comer point detector. Then through vector quantization using LBG algorithm, all feature vectors are represented by a codebook index. All images are indexed by the histogram of codebook index, and by comparing the histograms the similarity between images is obtained. The proposed method is compared with the existing method by performing experiments for image database including various 1100 trademarks.