• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.7
• /
• pp.83-91
• /
• 2004

The determination of camera position and orientation from known correspondences of 3D reference points and their images is known as pose estimation in computer vision or space resection in photogrammetry. This paper discusses estimation of transform parameters using the pattern matching method with 2D images only. In general, the 3D reference points or lines are needed to find out the 3D transform parameters, but this method is applied without the 3D reference points or lines. It uses only two images to find out the transform parameters between two image. The algorithm is simulated using Visual C＋＋ on Windows 98.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1056-1059
• /
• 2020

최근 드론과 1인 미디어 시장의 성장으로, 영상 촬영 분야에서의 드론 산업이 활발하게 발전되고 있다. 본 논문에서는 딥러닝 기반 다중 객체 인식 기술인 Openpose를 활용하여 인물촬영을 위한 음성인식 드론 제어 시스템을 제안한다. 해당 시스템은 자연어 처리된 음성명령어를 통해 드론이 각 촬영 객체에 대한 회전, 초점변화 등 실제 영상촬영기법에 사용되는 다수의 동작을 수행할 수 있도록 한다. 최종적으로 96.2%의 정확도로 음성명령에 따라 동작을 수행하는 것을 확인할 수 있다. 이는 누구나 전문적 지식이나 경험 없이 음성만으로 쉽게 드론을 제어할 수 있을 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.31-34
• /
• 2022

본 논문에서는 손목 부착형 웨어러블(Wearable) RGB 카메라를 통해 취득한 손 이미지에 최적화된 손 자세 추정모델과 학습방법을 제안한다. 최근 의료분야에서 활발하게 인공지능이 사용되고 있으며 그 중 이미지 인식을 중심으로 하는 진단 분야[1]가 괄목할만한 성과를 보인다. 본 연구에서는 웨어러블 카메라를 통해 얻은 손 자세를 활용하여 질병 진단에 적용할 계획이다. 또한, 본 연구수행을 통해 질병진단에 필요한 데이터 측정비용 절감 및 개인 맞춤형 진단서비스를 제공할 것으로 기대된다.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.597-606
• /
• 2010

This paper describes a real-time camera tracking framework specifically designed to track a monocular camera in an AR workspace. Typically, the Kalman filter is often employed for the camera tracking. In general, however, tracking performances of conventional methods are seriously affected by unpredictable situations such as ambiguity in feature detection, occlusion of features and rapid camera shake. In this paper, a recursive Bayesian sampling framework which is also known as the particle filter is adopted for the camera pose estimation. In our system, the camera state is estimated on the basis of the Gaussian distribution without employing additional uncertainty model and sample weight computation. In addition, the camera state is directly computed based on new sample particles which are distributed according to the true posterior of system state. In order to verify the proposed system, we conduct several experiments for unstable situations in the desktop AR environments.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.11 s.188
• /
• pp.58-67
• /
• 2006

Due to the variety of signal processing and complicated mathematical analysis, it is not easy to accomplish 3D bin-picking with non-contact sensor. To solve this difficulties the reliable signal processing algorithm and a good sensing device has been recommended. In this research, 3D laser scanner and CCD camera is applied as a sensing device respectively. With these sensor we develop a two-step bin-picking method and reliable algorithm for the recognition of 3D bin object. In the proposed bin-picking, the problem is reduced to 2D intial recognition with CCD camera at first, and then 3D pose detection with a laser scanner. To get a good movement in the robot base frame, the hand eye calibration between robot's end effector and sensing device should be also carried out. In this paper, we examine auto-calibration technique in the sensor calibration step. A new thinning algorithm and constrained hough transform is also studied for the robustness in the real environment usage. From the experimental results, we could see the robust bin-picking operation under the non-aligned 3D hole object.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.614-623
• /
• 2011

We propose a real-time tracking algorithm for an augmented reality (AR) system for TV broadcasting. The tracking is initialized by detecting the object with the SURF algorithm. A multi-scale approach is used for the stable real-time camera tracking. Normalized cross correlation (NCC) is used to find the patch correspondences, to cope with the unknown and changing lighting condition. Since a zooming camera is used, the focal length should be estimated online. Experimental results show that the focal length of the camera is properly estimated with the proposed online calibration procedure.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.536-538
• /
• 2006

The most important factor of mobile robot is to build a map for surrounding environment and estimate its localization. This paper proposes a real-time localization and map building method through 3-D reconstruction using scale invariant feature from monocular camera. Mobile robot attached monocular camera looking wall extracts scale invariant features in each image using SIFT(Scale Invariant Feature Transform) as it follows wall. Matching is carried out by the extracted features and matching feature map that is transformed into absolute coordinates using 3-D reconstruction of point and geometrical analysis of surrounding environment build, and store it map database. After finished feature map building, the robot finds some points matched with previous feature map and find its pose by affine parameter in real time. Position error of the proposed method was maximum. 8cm and angle error was within $10^{\circ}$.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.7
• /
• pp.545-551
• /
• 2016

Surface temperature of supersonic wind tunnel model was measured using an infrared thermography technique. To measure the temperature quantitatively, various calibration techniques such as blackbody calibration which converts detected camera signal to temperature, distortion correction due to the camera lens and an imbalance of camera pose, and emissivity calibration which considers viewing angles to the model surface, were employed. Throughout the study, for the quantitative as well as qualitative surface temperature measurement, it was verified that the distortion correction must be considered even for the use of two-dimensional model in aerodynamics testing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.2044-2059
• /
• 2022

Recent works have shown that the geometric constraint can be harnessed to boost the performance of CNN-based camera localization. However, the existing strategies are limited to imposing image-level constraint between pose pairs, which is weak and coarse-gained. In this paper, we introduce a pixel-level epipolar geometry constraint to vanilla localization framework without the ground-truth 3D information. Dubbed EpiLoc, our method establishes the geometric relationship between pixels in different images by utilizing the epipolar geometry thus forcing the network to regress more accurate poses. We also propose a variant called EpiSingle to cope with non-sequential training images, which can construct the epipolar geometry constraint based on a single image in a self-supervised manner. Extensive experiments on the public indoor 7Scenes and outdoor RobotCar datasets show that the proposed pixel-level constraint is valuable, and helps our EpiLoc achieve state-of-the-art results in the end-to-end camera localization task.