Multi-Modal Variational Faster R-CNN for Improved Visual Object Detection in Manufacturing

Panagiotis Mouzenidis, Antonios Louros, Dimitrios Konstantinidis, Kosmas Dimitropoulos, Petros Daras, Theofilos Mastos

ICCVW 2021 pp. 2587-2594

doi:10.1109/ICCVW54120.2021.00292 /iccvw/2021/mouzenidis2021iccvw-multimodal/

Abstract

Visual object detection is a critical task for a variety of industrial applications, such as robot navigation, quality control and product assembling. Modern industrial environments require AI-based object detection methods that can achieve high accuracy, robustness and generalization. To this end, we propose a novel object detection approach that can process and fuse information from RGB-D images for the accurate detection of industrial objects. The proposed approach utilizes a novel Variational Faster R-CNN algorithm that aims to improve the robustness and generalization ability of the original Faster R-CNN algorithm by employing a VAE encoder-decoder network and a very powerful attention layer. Experimental results on two object detection datasets, namely the well-known RGB-D Washington dataset and the QCONPASS dataset of industrial objects that is first presented in this paper, verify the significant performance improvement achieved when the proposed approach is employed.

ICCVW Semantic Scholar

Cite

Text

Mouzenidis et al. "Multi-Modal Variational Faster R-CNN for Improved Visual Object Detection in Manufacturing." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00292

Markdown

[Mouzenidis et al. "Multi-Modal Variational Faster R-CNN for Improved Visual Object Detection in Manufacturing." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/mouzenidis2021iccvw-multimodal/) doi:10.1109/ICCVW54120.2021.00292

BibTeX

@inproceedings{mouzenidis2021iccvw-multimodal,
  title     = {{Multi-Modal Variational Faster R-CNN for Improved Visual Object Detection in Manufacturing}},
  author    = {Mouzenidis, Panagiotis and Louros, Antonios and Konstantinidis, Dimitrios and Dimitropoulos, Kosmas and Daras, Petros and Mastos, Theofilos},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {2587-2594},
  doi       = {10.1109/ICCVW54120.2021.00292},
  url       = {https://mlanthology.org/iccvw/2021/mouzenidis2021iccvw-multimodal/}
}