0623_ Flocking in ML + using server

-

 

* Works to do today


1. 논문 Review 한 편 ( spatial / Real time / ... 관련 AR )

2. Flocking ML로 보내기

3. 라즈베리파이 사용 준비

4. ML 서버 연결하는거 더 공부하기


1. (conference)

markerless augmented reality, augmented reality worldbuilding, augmented reality using GPS

https://link.springer.com/chapter/10.1007/978-981-15-0947-6_57

Abstract

Our article discusses existing methods in marker-based and markerless augmented reality and their evolution over time. Markers are the most optimal solution to solve the problem of calculating the pose for augmented reality and do not require powerful devices. Its simplicity, robustness and efficiency have a great advantage; the objects to detect are provided to the application and require to be always visible by the sensor. On the other hand, markerless augmented reality detects objects or characteristic points of a scene without any prior knowledge of the environment. This mechanism is more difficult to implement because it implements algorithms that are expensive in terms of computation time. The appearance and improvement of new devices have made it possible to exploit this technology and to detach from the presence of a marker in a scene and emerge to markerless methods.


    1. Background : 마커는 증강현실에서 위치 문제를 해결하기 위한 최적의 솔루션

    2. Problem : 그렇지만 마커가 항상 센서에 잡혀야 한다는 단점이 있다.

    3. Solution 마커 또는 환경에 대한 사전 지식 없이 물체 또는 특징을 감지한다.

    4. Result / Finding : 

    5. Contribution



Distant augmented reality: Bringing a new dimension to user experience using drones

https://www.sciencedirect.com/science/article/abs/pii/S2212054818300390?via%3Dihub

Abstract

Augmented Reality (AR) is a live view that blends real world images with virtual information such as 3D models or sounds. AR is used to virtually reconstruct the ancient buildings of cultural heritage sites. Such sites can be presented to tourist groups in the form they were built in the past. AR can be implemented using mobile phones, tablets or smart glasses. Here, we present a new dimension to AR for cultural heritage using drones. We name it “Distant Augmented Reality”. The goal of this study is to augment video imagery acquired using drones with 3D models of the Roman Baths which is an important cultural heritage site in Turkey. For this purpose, two different tracking techniques were implemented: GPS based drone tracking and monocular camera based scene tracking. With these two techniques drone position and orientation was detected and tracked for augmenting the 3D model of the baths.


https://www.researchgate.net/profile/Tomohiro-Fukuda-2/publication/317170655_OUTDOOR_MAKER-LESS_AUGMENTED_REALITY_SYSTEM_FOR_VISUALIZING_A_BUILDING_MODEL_AND_ITS_INFORMATION_USING_SIMULTANEOUS_LOCALIZATION_AND_MAPPING/links/5928b03d458515e3d466a44e/OUTDOOR-MAKER-LESS-AUGMENTED-REALITY-SYSTEM-FOR-VISUALIZING-A-BUILDING-MODEL-AND-ITS-INFORMATION-USING-SIMULTANEOUS-LOCALIZATION-AND-MAPPING.pdf

OUTDOOR MARKERLESS AUGMENTED REALITY A System for Visualizing Building Models Using Simultaneous Localization and Mapping 


Abstract. In this study, an Augmented Reality (AR) system is developed to be used for visualizing design projects of buildings. In such design projects, it is desirable to enable design stakeholders visualizing the outcomes of different design options to reduce the resistance and hesitation towards new design challenges. The research proposes an outdoor mark-er-less AR using Simultaneous Localization and Mapping (SLAM) for the AR tracking. Our proposed system performs reconstruction and localization steps in real-time, as opposed to similar methods in which the reconstruction step is done offline. A case study has been performed for a de-sign scenario of buildings. The case study verified the performance of visualization and tracking. 

    1. Background : 설계 단계에서 건물의 설계 결과를 시각화하는 AR 시스템을 만들 것이다.

    2. Problem : 야외에서 높은 정밀도를 가지는 AR 추적기술이 필요하다. GPS, 마커 등의 방식이 가능하지만, 도심에서의 GPS 정확도가 높지 않고 마커는 사용자의 이동성을 제한하며 대형 마커를 설치할 때 문제가 생긴다. 

    3. Solution : SLAM(Simultaneous Localization and Mapping)을 사용하는 Markerless AR을 사용해 문제를 해결하였다. 

    4. Result / Finding : SLAM을 통하여 Markerless Outdoor AR 시스템이 가능하다는 것을 확인하였다.

    5. Contribution : 



2. 

https://drive.google.com/drive/folders/1bPECedEByy2_aalqP6D95Sy_2obCutZR?usp=sharing


댓글

댓글 쓰기

이 블로그의 인기 게시물

0817 : Hand Tracking

-
  * 지난 주 요약 1. 큐브 2. 비둘기 3. 손 트레킹 * 이번 주 할 일 1. 비둘기 밥주기 canIGrab 랑 canIPlace 기능이 뭔지 까먹었어,,. using System.Collections ; using System.Collections.Generic ; using UnityEngine ; using UnityEngine.XR.MagicLeap ; public class HandTrackScript : MonoBehaviour { public enum HandPoses { Ok, Finger, Thumb, OpenHand, Pinch, NoPose }; public HandPoses pose = HandPoses.NoPose; public Vector3[] pos; public GameObject sphereThumb, sphereIndex, sphereWrist, ObjectToPlace; private MLHandTracking.HandKeyPose[] _gestures; bool canIPlace = false ; bool canIGrab = false ; public GameObject selectedGameObject; private void Start () { MLHandTracking.Start(); _gestures = new MLHandTracking.HandKeyPose[ 5 ]; _gestures[ 0 ] = MLHandTracking.HandKeyPose.Ok; _gestures[ 1 ] = MLHandTracking.HandKeyPose.Finger; _gestures[ 2 ] = MLHandTracking.HandKeyPose.O...
자세한 내용 보기

0701_Using server in Unity

-
 * works to do  1. 튜토리얼 영상 #2 완성 2. 튜토리얼 영상 #3 만들기(커리큘럼 짜기) 3. 서버 연결 PHP로 시도하기 4. x,y,z,value 데이터 받아서 시각화하는 프로그램 만들기 5. Data visualization  관련 논문/연구 찾아보기 6. 해외 연구실 찾아보기 * works to do today 1. 튜토리얼 영상 #2 완성 2. 유니티 서버 연결 PHP로 시도하기 3. Data visualization 관련 논문/연구 찾아보기 + 스크랩 4. 온습도 데이터로 visualization 모델 만들어보기 5. 관련 해외 연구실 찾아보기  Personal Augmented Reality for Information Visualization on Large Interactive Displays In this work we propose the combination of large interactive displays with personal head-mounted Augmented Reality (AR) for information visualization to facilitate data exploration and analysis. Even though large displays provide more display space, they are challenging with regard to perception, effective multi-user support, and managing data density and complexity. To address these issues and illustrate our proposed setup, we contribute an extensive design space comprising first, the spatial alignment of display, visualizations, and objects in AR space. Next, w...
자세한 내용 보기