Neural networks-based camera pose estimation systems rely on fine tuning very large networks to regress the camera position and orientation with very complex training procedure. In this paper, we explore the following question: do we need to fine tune and train such complex networks to reach the desired accuracy? We show that we can reach comparable or better accuracy for the single image indoor localization systems with using only one layer of ridge regression and pretrained features of ResNet-50 architecture with training time less than a second on CPU instead of hours of GPU training needed by the state of the art. For outdoor scenes, we show that using only 3 fully connected layers on top of pretrained ResNet50 features without fine-tuning can perform well compared to the state of the art with only minutes of training. For more complexity reduction, we show that downsampling the pretrained ResNet-50 features by more than 10 times using principal component analysis (PCA) has a little effect on the performance but can save both training time and storage space.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Linear-PoseNet: A Real-Time Camera Pose Estimation System Using Linear Regression and Principal Component Analysis


    Contributors:


    Publication date :

    2020-11-01


    Size :

    866398 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Spacecraft Pose Estimation using Principal Component Analysis and a Monocular Camera

    Shi, Jian-Feng / Ulrich, Steve / Ruel, Stephane | AIAA | 2017


    Aerial Geo-Localisation for MAVs using PoseNet

    Cabrera-Ponce, Aldrich A. / Martinez-Carranza, J. | IEEE | 2019


    Dynamic random regression forests for real-time head pose estimation

    Ying, Y. | British Library Online Contents | 2013


    Camera-Selecting Device-Edge Co-Inference for Real-Time Multi-Camera 3D Pose Estimation

    Du, Zhuohang / Huang, Xumin / Wu, Yuan et al. | IEEE | 2023


    Efficient real time OD matrix estimation based on Principal Component Analysis

    Djukic, Tamara / Flotterod, Gunnar / van Lint, Hans et al. | IEEE | 2012