Predicting Out-of-View Feature Points for Model-Based Camera Pose Estimation

被引:0
|
作者
Moolan-Feroze, Oliver [1 ]
Calway, Andrew [1 ]
机构
[1] Univ Bristol, Dept Comp Sci, Merchant Venturers Bldg, Bristol BS8 1UB, Avon, England
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work we present a novel framework that uses deep learning to predict object feature points that are out-of-view in the input image. This system was developed with the application of model-based tracking in mind, particularly in the case of autonomous inspection robots, where only partial views of the object are available. Out-of-view prediction is enabled by applying scaling to the feature point labels during network training. This is combined with a recurrent neural network architecture designed to provide the final prediction layers with rich feature information from across the spatial extent of the input image. To show the versatility of these out-of-view predictions, we describe how to integrate them in both a particle filter tracker and an optimisation based tracker. To evaluate our work we compared our framework with one that predicts only points inside the image. We show that as the amount of the object in view decreases, being able to predict outside the image bounds adds robustness to the final pose estimation.
引用
收藏
页码:82 / 88
页数:7
相关论文
共 50 条
  • [1] Accurate Single View Model-Based Head Pose Estimation
    Martins, Pedro
    Batista, Jorge
    [J]. 2008 8TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE & GESTURE RECOGNITION (FG 2008), VOLS 1 AND 2, 2008, : 831 - 836
  • [2] Model-Based Pose Estimation by Consensus
    Jorstad, Anne
    Burlina, Philippe
    Wang, I-Jeng
    Lucarelli, Dennis
    DeMenthon, Daniel
    [J]. ISSNIP 2008: PROCEEDINGS OF THE 2008 INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS, AND INFORMATION PROCESSING, 2008, : 569 - 574
  • [3] Vision-based pose estimation algorithm with four coplanar feature points via an incident-ray-based camera model
    Zhang, Zimiao
    Wang, Zhiwu
    Zhang, Shihai
    Fu, Anqi
    [J]. JOURNAL OF OPTICAL TECHNOLOGY, 2021, 88 (08) : 445 - 453
  • [4] Camera pose estimation algorithm involving weighted measurement uncertainty of feature points based on rotation parameters
    Wei, Liang
    Huo, Ju
    [J]. APPLIED OPTICS, 2023, 62 (09) : 2200 - 2206
  • [5] Model-Based Adaptive Pose Coordinated Control Between Feature Points of Two Rigid Bodies
    Sun, Liang
    Wang, Jun
    Jiang, Jingjing
    [J]. 2022 34TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2022, : 388 - 393
  • [6] A comparative study on model-based pose estimation of flying objects with different feature descriptors
    Tang Hui-jun
    Wen Jia
    Ma Cai-wen
    Zhou Ren-kui
    [J]. INTERNATIONAL SYMPOSIUM ON PHOTOELECTRONIC DETECTION AND IMAGING 2011: SPACE EXPLORATION TECHNOLOGIES AND APPLICATIONS, 2011, 8196
  • [7] Robotic Grasping With Multi-View Image Acquisition and Model-Based Pose Estimation
    Lin, Huei-Yung
    Liang, Shih-Cheng
    Chen, Yu-Kai
    [J]. IEEE SENSORS JOURNAL, 2021, 21 (10) : 11870 - 11878
  • [8] Statistical Model-Based Face Pose Estimation
    戈新良
    杨杰
    李冯
    王华华
    [J]. Transactions of Tianjin University, 2007, (02) : 152 - 156
  • [9] Camera pose estimation and corresponding points matching based on rotation search
    Wang P.
    Fu H.
    Xu G.
    [J]. Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica, 2023, 44 (02):
  • [10] Model-based spacecraft pose estimation and motion prediction using a photonic mixer device camera
    Tzschichholz, Tristan
    Ma, Lei
    Schilling, Klaus
    [J]. ACTA ASTRONAUTICA, 2011, 68 (7-8) : 1156 - 1167