CHU-SONG CHENShih, S.-W.S.-W.ShihHsieh, C.-C.C.-C.HsiehTang, C.-Y.C.-Y.TangYu, C.-G.C.-G.YuCheng, Y.-C.Y.-C.ChengYI-PING HUNG2020-06-112020-06-111998https://scholars.lib.ntu.edu.tw/handle/123456789/500496https://www.scopus.com/inward/record.uri?eid=2-s2.0-3042610754&doi=10.1145%2f293701.293702&partnerID=40&md5=174c3cdb6ea3cbbc67f6e8b36b37b697A systematic approach for integrating virtual objects into real images is developed in this paper. We propose the P3P-ICP method to solve the camera pose estimation problem. A robust tracking method is developed via the combination of the LMedS technique and the P3P-ICP method. With the 3D models and the robust tracking methods, we can determine the camera poses associated with each frame in the image sequence. Knowing the camera poses for each image frame, we can then integrate virtual objects into a video segment. © 1998 ACM.Augmented reality; Computer graphics; Computer vision[SDGs]SDG9Cameras; Computer graphics; Computer vision; Image processing; Virtual reality; 3D models; Camera pose estimation; Image frames; Image sequence; Real images; Robust tracking methods; Video segments; Virtual objects; Augmented realityconference paper10.1145/293701.2937022-s2.0-3042610754