Articles producció científica> Enginyeria Informàtica i Matemàtiques

Reliable Scene Recognition Approach for Mobile Robots with Limited Resources Based on Deep Learning and Neuro-Fuzzy Inference

  • Identification data

    Identifier: imarina:9283520
    Authors:
    Singh APandey PPuig DNandi GCAbdel-Nasser M
    Abstract:
    Indoor scene recognition is complex due to the commonality shared between different spaces. Still, when it comes to robotics applications, the uncertainty increases due to illumination change, motion blur, interruption due to external light sources, and cluttered environments. Most existing fusion approaches do not consider the uncertainty, and others have a high computational cost that may not suit robots with limited resources. To mitigate these issues, this paper proposes a reliable indoor scene recognition approach for mobile robots with limited resources based on robust deep convolutional neural networks (CNNs) feature extractors and neuro-fuzzy inference to consider the uncertainty of the data. All CNN feature extractors are pre-trained on the Imagenet dataset and used in the manner of transfer learning. The performance of our fusion method has been assessed on a customized MIT-67 dataset and for real-time processing on a Locobot robot. We also compare the proposed method with two standard fusion methods-Early Feature Fusion (EFF) and Weighted Average Late Fusion (WALF). The experimental results demonstrate that our method achieves competitive results with a precision of 94%, and it performs well on the Locobot robot with a speed of 3.1 frames per second.
  • Others:

    Author, as appears in the article.: Singh A; Pandey P; Puig D; Nandi GC; Abdel-Nasser M
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Abdelnasser Mohamed Mahmoud, Mohamed / Puig Valls, Domènec Savi / Singh, Aditya
    Keywords: Transfer learning Neuro-fuzzy Indoor scene recognition Fusion Deep learning Cnns transfer learning neuro-fuzzy deep learning cnns
    Abstract: Indoor scene recognition is complex due to the commonality shared between different spaces. Still, when it comes to robotics applications, the uncertainty increases due to illumination change, motion blur, interruption due to external light sources, and cluttered environments. Most existing fusion approaches do not consider the uncertainty, and others have a high computational cost that may not suit robots with limited resources. To mitigate these issues, this paper proposes a reliable indoor scene recognition approach for mobile robots with limited resources based on robust deep convolutional neural networks (CNNs) feature extractors and neuro-fuzzy inference to consider the uncertainty of the data. All CNN feature extractors are pre-trained on the Imagenet dataset and used in the manner of transfer learning. The performance of our fusion method has been assessed on a customized MIT-67 dataset and for real-time processing on a Locobot robot. We also compare the proposed method with two standard fusion methods-Early Feature Fusion (EFF) and Weighted Average Late Fusion (WALF). The experimental results demonstrate that our method achieves competitive results with a precision of 94%, and it performs well on the Locobot robot with a speed of 3.1 frames per second.
    Thematic Areas: Engineering, electrical & electronic Electrical and electronic engineering Computer science, artificial intelligence
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: mohamed.abdelnasser@urv.cat domenec.puig@urv.cat
    Author identifier: 0000-0002-1074-2441 0000-0002-0562-4205
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.iieta.org/journals/ts/paper/10.18280/ts.390418
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Trait Signal. 39 (4): 1255-1265
    APA: Singh A; Pandey P; Puig D; Nandi GC; Abdel-Nasser M (2022). Reliable Scene Recognition Approach for Mobile Robots with Limited Resources Based on Deep Learning and Neuro-Fuzzy Inference. Trait Signal, 39(4), 1255-1265. DOI: 10.18280/ts.390418
    Article's DOI: 10.18280/ts.390418
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2022
    Publication Type: Journal Publications
  • Keywords:

    Computer Science, Artificial Intelligence,Electrical and Electronic Engineering,Engineering, Electrical & Electronic
    Transfer learning
    Neuro-fuzzy
    Indoor scene recognition
    Fusion
    Deep learning
    Cnns
    transfer learning
    neuro-fuzzy
    deep learning
    cnns
    Engineering, electrical & electronic
    Electrical and electronic engineering
    Computer science, artificial intelligence
  • Documents:

  • Cerca a google

    Search to google scholar