Faster Visual-Based Localization with Mobile-PoseNet

被引：3
作者：
Cimarelli, Claudio [1 ]
Cazzato, Dario [1 ]
Olivares-Mendez, Miguel A. [1 ]
Voos, Holger [1 ]
机构：
[1] Univ Luxembourg, Interdisciplinary Ctr Secur Reliabil & Trust SnT, 29 Ave JF Kennedy, L-1855 Luxembourg, Luxembourg
来源：
COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019, PT II | 2019年 / 11679卷
关键词：
Deep learning; Convolutional Neural Networks; 6-DoF pose estimation; Visual-Based Localization; UAV;
D O I：
10.1007/978-3-030-29891-3_20
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Precise and robust localization is of fundamental importance for robots required to carry out autonomous tasks. Above all, in the case of Unmanned Aerial Vehicles (UAVs), efficiency and reliability are critical aspects in developing solutions for localization due to the limited computational capabilities, payload and power constraints. In this work, we leverage novel research in efficient deep neural architectures for the problem of 6 Degrees of Freedom (6-DoF) pose estimation from single RGB camera images. In particular, we introduce an efficient neural network to jointly regress the position and orientation of the camera with respect to the navigation environment. Experimental results show that the proposed network is capable of retaining similar results with respect to the most popular state of the art methods while being smaller and with lower latency, which are fundamental aspects for real-time robotics applications.
引用
收藏
页码：219 / 230
页数：12
相关论文
共 40 条
[11]  
Han Y, 2017, 2017 IEEE INTERNATIONAL CONFERENCE ON CYBERNETICS AND INTELLIGENT SYSTEMS (CIS) AND IEEE CONFERENCE ON ROBOTICS, AUTOMATION AND MECHATRONICS (RAM), P644, DOI 10.1109/ICCIS.2017.8274853
[12]  
He K., 2015, IEEE I CONF COMP VIS, P1026, DOI DOI 10.1109/ICCV.2015.123
[13]  
Hochreiter S, 1997, Neural Computation, V9, P1735
[14]   Metrics for 3D Rotations: Comparison and Analysis [J].
Huynh, Du Q. .
JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2009, 35 (02) :155-164
[15]  
Irschara A, 2009, PROC CVPR IEEE, P2591, DOI 10.1109/CVPRW.2009.5206587
[16]  
Josephson K, 2009, PROC CVPR IEEE, P2411
[17]   SOLUTION FOR BEST ROTATION TO RELATE 2 SETS OF VECTORS [J].
KABSCH, W .
ACTA CRYSTALLOGRAPHICA SECTION A, 1976, 32 (SEP1) :922-923
[18]  
Kendall A., 2017, P IEEE C COMPUTER V, P5974
[19]   Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics [J].
Kendall, Alex ;
Gal, Yarin ;
Cipolla, Roberto .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :7482-7491
[20]  
Kendall H, 2015, TLS-TIMES LIT SUPPL, P6
1234