ROUGH COMPRESSED DOMAIN CAMERA POSE ESTIMATION THROUGH OBJECT MOTION

被引：2

作者：

Kaes, Christian ^{[1
]}

Nicolas, Henri ^{[1
]}

机构：

[1] Univ Bordeaux 1, LaBRI, F-33405 Talence, France

来源：

2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 | 2009年

关键词：

Compressed domain; camera pose estimation; object distance estimation; DISTANCE ESTIMATION;

D O I：

10.1109/ICIP.2009.5413832

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present an unsupervised method to estimate the camera orientation angle on monocular video scenes in the H.264 compressed domain. The method is based on the presence of moving objects in the scene. We start by estimating the global camera motion based on the motion vectors present in the stream, detect and track moving objects and estimate their relative distance to the camera by analyzing the temporal evolution of the objects' dimensions. The evolution of the motion compensated, vertical positions of key points within moving objects are used to infer the extrinsic orientation angle of the camera.

引用

页码：3481 / 3484

页数：4

共 50 条

[21] Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection
Yamashita, Kohei
Lepetit, Vincent
Nishino, Ko
COMPUTER VISION - ECCV 2024, PT LXV, 2025, 15123 : 360 - 376
[22] CONVOLUTIONAL NEURAL NETWORK FOR CAMERA POSE ESTIMATION FROM OBJECT DETECTIONS
Shalnov, E. V.
Konushin, A. S.
INTERNATIONAL WORKSHOP PHOTOGRAMMETRIC AND COMPUTER VISION TECHNIQUES FOR VIDEO SURVEILLANCE, BIOMETRICS AND BIOMEDICINE, 2017, 42-2 (W4): : 1 - 6
[23] Pose estimation for one-dimensional object with general motion
Liu, Jinbo
Song, Ge
Zhang, Xiaohu
INTERNATIONAL SYMPOSIUM ON OPTOELECTRONIC TECHNOLOGY AND APPLICATION 2014: IMAGE PROCESSING AND PATTERN RECOGNITION, 2014, 9301
[24] Motion-based video object tracking in the compressed domain
Ritch, Mark
Canagarajah, Nishan
2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 3097 - 3100
[25] Compressed domain moving object segmentation in local motion scene
2005, Science Press, Beijing, China (27):
[26] Motion Estimation in Measurement Domain for Compressed Video Sensing
Guo, Jie
Song, Bin
Liu, Haixiao
Qin, Hao
2014 IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (CIT), 2014, : 441 - 445
[27] Visual-inertial object tracking: Incorporating camera pose into motion models
Shahbazi, Mohammad
Mirtajadini, Seyed Hojat
Fahimi, Hamidreza
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 229
[28] Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images
Sock, Juil
Kasaei, S. Hamidreza
Lopes, Luis Seabra
Kim, Tae-Kyun
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, : 2228 - 2235
[29] Industry robotic motion and pose recognition method based on camera pose estimation and neural network
Wang, Ding
Xie, Fei
Yang, Jiquan
Lu, Rongjian
Zhu, Tengfei
Liu, Yijian
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2021, 18 (03):
[30] Real-time object motion estimation based on frequency domain matching from a single camera
Tumurbaatar T.
Kim T.
Spatial Information Research, 2016, 24 (4) : 463 - 473

← 1 2 3 4 5 →