• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.260-263
• /
• 1996

THe Purpose of this paper is to match the feature point of man-made structure and to obtain the DEM which are occluded in a image plane. We use the trinocular matching with epipolar lines and planes. If an occlusion appears at one of the trinocular images, the DEM mapping is used to estimate the height of feature points in it.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.429-432
• /
• 2021

스마트 기기와 애플리케이션의 테스트를 위해 빠르고 정확하게 스마트 기기 화면 상에서 테스트가 필요한 위치를 추출해야 한다. 필요한 위치를 추출할 때 스마트 기기 화면과 테스트할 수 있는 영역의 매칭 방식을 사용하는데 이를 위해 이미지의 변형이 발생해도 원하는 영역의 matching point 을 빠르고 정확하게 추출하는 feature matching 방식의 D2-Net 의 feature extraction 모델과 fitting algorithm 을 변경하였다.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.234-242
• /
• 2019

In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into $33{\times}33$ size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.13 no.2
• /
• pp.299-307
• /
• 1995

The extraction of distinct points such as corner points and circular features is a basic procedure in digital photogrammetry and computer vision. This paper describes the extraction of image features from the raw images (gray value images), especially Forstner interest corner points. The mathematical model of the Forstner interest operator as well as the behavior in the presence of noise are investigated. Experiments with real images prove the feasibility of the Forstner interest operator in the field of Digital Photogrammetry.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.150-152
• /
• 2003

Laser scanned lidar data record 3D surface information in detail. Exploring valuable spatial information from lidar data is a prerequisite task for its applications, such as DEM generation and 3D building model reconstruction. However, the inherent spatial information is implicit in the abundant, densely and randomly distributed point cloud. This paper proposes a novel method to organize point cloud data, so that further analysis or feature extraction can proceed based on a well organized data model. The principle of the proposed algorithm is to segment point cloud into 3D planes. A split and merge segmentation based on the octree structure is developed for the implementation. Some practical airborne and ground lidar data are tested for demonstration and discussion. We expect this data organization could provide a stepping stone for extracting spatial information from lidar data.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.1
• /
• pp.64-75
• /
• 2010

This study introduces a complete feature map building method of sonar sensors for mobile robots. This method enhances the reality of feature maps by extracting even circle features as well as line and point features from sonar data. Edge features are, moreover, generated by combining line features close to circle features extracted around comer sites. The uncertainties of the specular reflection phenomenon and wide beam width of sonar data can be, therefore, reduced through this map building method. The experimental results demonstrate a practical validity of the proposed method in those environments.

• Phonetics and Speech Sciences
• /
• v.1 no.4
• /
• pp.111-117
• /
• 2009

In this paper, a new speech endpoint detector in noisy environment is proposed. According to the previous research, the energy feature in the speech region is easily distinguished from that in the speech absent region. In conventional method, the endpoint can be found by applying the edge detection filter that finds the abrupt changing point in feature domain. However, since the frame energy feature is unstable in noisy environment, the accurate edge detection is not possible. Therefore, in this paper, the novel feature extraction method based on spectrum envelop pattern is proposed. Then, the edge detection filter is applied to the proposed feature for detection of the endpoint. The experiments are performed in the car noise environment and a substantial improvement was obtained over the conventional method.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.529-535
• /
• 2020

As the main technology of the 4th industrial revolution, immersive 360-degree video contents are drawing attention. The market size of immersive 360-degree video contents worldwide is projected to increase from $6.7 billion in 2018 to approximately $70 billion in 2020. However, most of the immersive 360-degree video contents are distributed through illegal distribution networks such as Webhard and Torrent, and the damage caused by illegal reproduction is increasing. Existing 2D video industry uses copyright filtering technology to prevent such illegal distribution. The technical difficulties dealing with immersive 360-degree videos arise in that they require ultra-high quality pictures and have the characteristics containing images captured by two or more cameras merged in one image, which results in the creation of distortion regions. There are also technical limitations such as an increase in the amount of feature point data due to the ultra-high definition and the processing speed requirement. These consideration makes it difficult to use the same 2D filtering technology for 360-degree videos. To solve this problem, this paper suggests a feature point extraction and identification technique that select object identification areas excluding regions with severe distortion, recognize objects using deep learning technology in the identification areas, extract feature points using the identified object information. Compared with the previously proposed method of extracting feature points using stitching area for immersive contents, the proposed technique shows excellent performance gain.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.1
• /
• pp.118-125
• /
• 2016

This study evaluates the performance of image to patient registration algorithm by using stereo vision and CT image for facial region surgical navigation. For the process of image to patient registration, feature extraction and 3D coordinate calculation are conducted, and then 3D CT image to 3D coordinate registration is conducted. Of the five combinations that can be generated by using three facial feature extraction methods and three registration methods on stereo vision image, this study evaluates the one with the highest registration accuracy. In addition, image to patient registration accuracy was compared by changing the facial rotation angle. As a result of the experiment, it turned out that when the facial rotation angle is within 20 degrees, registration using Active Appearance Model and Pseudo Inverse Matching has the highest accuracy, and when the facial rotation angle is over 20 degrees, registration using Speeded Up Robust Features and Iterative Closest Point has the highest accuracy. These results indicate that, Active Appearance Model and Pseudo Inverse Matching methods should be used in order to reduce registration error when the facial rotation angle is within 20 degrees, and Speeded Up Robust Features and Iterative Closest Point methods should be used when the facial rotation angle is over 20 degrees.

• Journal of Multimedia Information System
• /
• v.4 no.1
• /
• pp.39-42
• /
• 2017

Communication between human and machine is having been researched from last few decades and still it's a challenging task because human behavior is unpredictable. When it comes on handwritten digits almost each human has their own writing style. Handwritten digit recognition plays an important role, especially in the courtesy amounts on bank checks, postal code on mail address etc. In our study, we proposed an efficient feature extraction system for recognizing single digit number drawn by mouse or by a finger on a screen. Our proposed method combines basic image processing and reading the strokes of a line drawn. It is very simple and easy to implement in various platform as compare to the system which required high system configuration. This system has been designed, implemented, and tested successfully.