• Title/Summary/Keyword: Landmark Recognition

Search Result 66, Processing Time 0.018 seconds

Real-time Control System for Mobile Robots and Path Tracking Control Algorithm (이동로봇의 실시간 주행제어를 위한 제어시스템 설계 및 경로 추종제어 방법)

  • 고경철;조형석
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.17 no.6
    • /
    • pp.1497-1508
    • /
    • 1993
  • Real-time mobile robot controllers usually have been designed focused on control theory without paying attention to the importance of system integration. This paper demonstrates that autonomous mobile robots require a real-time controller with a wide range of capabilities in addition to control theory. An architectural frame work supporting these capabilities has been designed in actual hardware environments. Individual modules such as a path planner, a path tracking controller, position estimators, wheel controllers and other cruical elements have been successfully integrated into the control system using this frame work. The overall performance of the system was investigated via a series of tracking experiments with a prototype mobile robot named LCAR deveoped in the laboratory. The context of the research involves the architecture, its implementation and experimental results.

A 3D Face Reconstruction and Tracking Method using the Estimated Depth Information (얼굴 깊이 추정을 이용한 3차원 얼굴 생성 및 추적 방법)

  • Ju, Myung-Ho;Kang, Hang-Bong
    • The KIPS Transactions:PartB
    • /
    • v.18B no.1
    • /
    • pp.21-28
    • /
    • 2011
  • A 3D face shape derived from 2D images may be useful in many applications, such as face recognition, face synthesis and human computer interaction. To do this, we develop a fast 3D Active Appearance Model (3D-AAM) method using depth estimation. The training images include specific 3D face poses which are extremely different from one another. The landmark's depth information of landmarks is estimated from the training image sequence by using the approximated Jacobian matrix. It is added at the test phase to deal with the 3D pose variations of the input face. Our experimental results show that the proposed method can efficiently fit the face shape, including the variations of facial expressions and 3D pose variations, better than the typical AAM, and can estimate accurate 3D face shape from images.

Three-dimensional Model Generation for Active Shape Model Algorithm (능동모양모델 알고리듬을 위한 삼차원 모델생성 기법)

  • Lim, Seong-Jae;Jeong, Yong-Yeon;Ho, Yo-Sung
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.43 no.6 s.312
    • /
    • pp.28-35
    • /
    • 2006
  • Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

Enhancing the performance of the facial keypoint detection model by improving the quality of low-resolution facial images (저화질 안면 이미지의 화질 개선를 통한 안면 특징점 검출 모델의 성능 향상)

  • KyoungOok Lee;Yejin Lee;Jonghyuk Park
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.2
    • /
    • pp.171-187
    • /
    • 2023
  • When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

Mountainous Landscape Management Value by Landscape Recognition (경관인식에 따른 산지경관 관리 가치 연구)

  • Min, Su-Hui;Jang, Hyo-Jin;Jeung, Yoon-Hee;Song, Jung-Eun
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.46 no.3
    • /
    • pp.70-78
    • /
    • 2018
  • Recently, the conservation of mountainous landscape and compensation for diverse demands for mountain areas such as leisure, recreation and welfare are under discussion. The purpose of this study is to investigation the perception of mountainous landscapes by those who view and recognize the landscapes and to estimate economic value by estimating the willingness to pay for the management of mountainous landscapes. This study will provide data for the management of mountainous landscapes. As a result of comparing the perception between the territorial landscape and the mountain landscape, the mountain scenery was 3.96, the management level satisfaction was 3.28, and the management necessity was 4.38, which was higher than the national landscape, while the national landscape was satisfactory but the management level was insufficient. Jeju Island (39.0%) and Gangwon (38.6%) were chosen as the most scenic areas with beautiful forest and mountainous landscape resources. The aesthetic characteristics of the vast skyline of mountain scenery, the background of the area, and the mountainous landscape that forms the landmark were evaluated highly. And, it is considered that consciousness of mountainous landscape management is heightened by 86.8% of respondents, who positively answered the Mountainous Landscape Visual Impact Assessment before the development project. The per capita payment amount for mountainous landscape management was calculated to be 3,742 won and, based on the number of visitors to the mountain National Parks in 2016, it is estimated to have an economic value of about 169.5 billion won. Policymakers have limitations in the mountainous landscape management policies of the administrative subject. Establishing a consensus on the importance and necessity of landscape management by diagnosing the status of public perception is expected to help create more effective policy direction and implement strategies for the management of these areas.

Analysis of the Inter- and Intra-treatment Isocenter Deviations in Pelvic Radiotherapy With Small Bowel Displacement System (Small Bowel Displacement System을 이용한 골반부 방사선조사에서 치료간 및 치료중 중심점 위치변동에 관한 분석)

  • Kim Moon Kyung;Kim Dae Yong;Ahn Yong Chan;Huh Seung Jae;Lim Do Hun;Shin Kyung Hwan;Lee Kyu Chan
    • Radiation Oncology Journal
    • /
    • v.18 no.2
    • /
    • pp.114-119
    • /
    • 2000
  • Purpose : To evaluate the e지ent and frequency of the inter- and intra-treatment isocenter deviations of the whole pelvis radiation field in using small bowel displacement system (SBDS). Methods and Materials : Using electronic portal imaging device (EPID), 302 postero-anterior 232 lateral portal images were prospectively collected from 11 patients who received pelvic radiation therapy (7 with cervix cancer and 4 with rectal cancer). All patients were treated in prone position with SBDS under the lower abdomen. Five metallic fiducial markers were placed on the image detection unit for the recognition of the isocenter and magnification. After aligning the bony landmarks of the EPID images on those of the reference image, the deviations of the isocenter were measured in right-left (RL), cranio-caudal (CC), and PA directions. Results : The mean inter-treatment deviation of the isocenter in each RL, CC, and PA direction was 1.2 mm ($\pm$ 1.6 mm), 1.0 mm ($\pm$3.0 mm), and 0.9 mm ($\pm$4.4 mm), respectively. Inter-treatment isocenter deviations over 5 mm and 10 mm in RL, CC, and PA direction were 2, 12, 24$\%$, and 0, 0, 5$\%$, respectively. Maximal deviation was detected in PA direction, and was 11.5 mm. The mean intratreatment deviation of the isocenter in RL, CC, and PA direction was 0 mm ($\pm$0.9 mm), 0.1 mm ($\pm$ 1.9mm), and 0 mm ($\pm$1.6 mm), respectively. All intra-treatment isocenter deviations over 5 mm in each direction were 0, 1, 1$\pm$, respectively. Conclusions : As the greatest and the most frequent inter-treatment deviation of the isocenter was along the PA direction, it is recommended to put more generous safety margin toward the PA direction on the lateral fields if clinically acceptable in pelvic radiotherapy with SBDD.

  • PDF