Analysis of Data Augmentation Techniques for Mobile Robots Localization by Means of Convolutional Neural Networks

被引：1

作者：

Jose Cespedes, Orlando ^{[1
]}

Cebollada, Sergio ^{[1
,2
]}

Jose Cabrera, Juan ^{[1
]}

Reinoso, Oscar ^{[1
,2
]}

Paya, Luis ^{[1
]}

机构：

[1] Miguel Hernandez Univ, Inst Engn Res, Elche, Spain

[2] Valencian Grad Sch & Res Network Artificial Intel, Valencia, Spain

来源：

ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, AIAI 2023, PT I | 2023年 / 675卷

关键词：

Mobile Robotics; Omnidirectional Vision; Hierarchical Localization; Deep Learning; Data Augmentation;

D O I：

10.1007/978-3-031-34111-3_42

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This work presents an evaluation regarding the use of data augmentation to carry out the rough localization step within a hierarchical localization framework. The method consists of two steps: first, the robot captures an image and it is introduced into a CNN in order to estimate the room where it was captured (rough localization). After that, a holistic descriptor is obtained from the network and it is compared with the descriptors stored in the model. The most similar image provides the position where the robot captured the image (fine localization). Regarding the rough localization, it is essential that the CNN achieves a high accuracy, since an error in this step would imply a considerable localization error. With this aim, several visual effects were separately analyzed in order to know their impact on the CNN when data augmentation is tackled. The results permit designing a data augmentation which is useful for training a CNN that solves the localization problem in real operation conditions, including changes in the lighting conditions.

引用

页码：503 / 514

页数：12

共 12 条

[1] Pedestrian detection for UAVs using cascade classifiers with Meanshift [J].

Aguilar, Wilbert G. ;

Luna, Marco A. ;

Moya, Julio F. ;

Abad, Vanessa ;

Parra, Humberto ;

Ruiz, Hugo .

2017 11TH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING (ICSC), 2017, :509-514

[2] A CNN Regression Approach to Mobile Robot Localization Using Omnidirectional Images [J].

Ballesta, Monica ;

Paya, Luis ;

Cebollada, Sergio ;

Reinoso, Oscar ;

Murcia, Francisco .

APPLIED SCIENCES-BASEL, 2021, 11 (16)

[3]

Cabrera J.J., 2022, SN Computer Science, V3, P271

[4] Development and use of a convolutional neural network for hierarchical appearance-based localization [J].

Cebollada, S. ;

Paya, L. ;

Jiang, X. ;

Reinoso, O. .

ARTIFICIAL INTELLIGENCE REVIEW, 2022, 55 (04) :2847-2874

[5]

Kopitkov D, 2018, IEEE INT C INT ROBOT, P7795, DOI 10.1109/IROS.2018.8594506

[6] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[7]

Perez L, 2017, Arxiv, DOI arXiv:1712.04621

[8] From Coarse to Fine: Robust Hierarchical Localization at Large Scale [J].

Sarlin, Paul-Edouard ;

Cadena, Cesar ;

Siegwart, Roland ;

Dymczyk, Marcin .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :12708-12717

[9] A survey on Image Data Augmentation for Deep Learning [J].

Shorten, Connor ;

Khoshgoftaar, Taghi M. .

JOURNAL OF BIG DATA, 2019, 6 (01)

[10]

Szegedy C, 2015, PROC CVPR IEEE, P1, DOI 10.1109/CVPR.2015.7298594

← 1 2 →