Liquid Detection and Instance Segmentation based on Mask R-CNN in Industrial Environment

• Autorzy: Gawdzik Grzegorz , Arkadiusz Orłowski

Identyfikatory

DOI

10.22630/MGV.2023.32.3.10

• Języki publikacji: EN

Abstrakty

EN

The goal of the paper is to present an efficient approach to detect and instantiate liquid spilled in the industrial and industrial-like environments. Motivation behind it is to enable mobile robots to automatically detect and collect samples of spilled liquids. Due to the lack of useful training data of spilled substances, a new dataset with RGB images and masks was gathered. A new application of the Mask-RCNN-based algorithm is proposed which has the functionalities of detecting the spilled liquid and segmenting the image.

Słowa kluczowe

EN

AI; Mask RCNN; liquid detection; dataset

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2023
• Tom: Vol. 32, No. 3/4
• Strony: 193--203
• Opis fizyczny: Bibliogr. 23., rys., tab., wykr.

Twórcy

autor

Gawdzik Grzegorz

• Security and Defense Systems Division, Łukasiewicz Research Network - Industrial Research Institute for Automation and Measurements PIAP, Warsaw, Poland
• Institute of Information Technology, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0002-9089-0224

autor

Arkadiusz Orłowski

• Institute of Information Technology, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0002-6755-1830

Bibliografia

• [1] awsaf49. COCO 2017 Dataset, 2017. https://www.kaggle.com/datasets/awsaf49/coco-2017-dataset, [Accessed: May 2023].
• [2] A.-A. Dalal, Y. Shao, A. Alalimi, and A. Abdu. Mask R-CNN for geospatial object detection. International Journal of Information Technology and Computer Science (IJITCS), 12(5):63-72, 2020. doi:10.5815/ijitcs.2020.05.05.
• [3] G. Gawdzik. Liquid dataset. PIAP Cloud Resources, 2023. https://cloud.piap.pl/index.php/s/ApiXNzt4ZUUSRks, [Accessed: 10 Dec 2023].
• [4] G. Gawdzik. Table of results for all runs of the liquid detection. PIAP Cloud Resources, 2023. https://cloud.piap.pl/index.php/s/cE3mJ8CrCYWUkJ9, [Accessed: 10 Dec 2023].
• [5] K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask R-CNN. In: Proc. 2017 IEEE international Conference on Computer Vision (ICCV), pp. 2980-2988. Venice, Italy, 22-29 Oct 2017. doi:10.1109/ICCV.2017.322.
• [6] W. Jia, Y. Tian, R. Luo, Z. Zhang, J. Lian, et al. Detection and segmentation of overlapped fruits based on optimized Mask R-CNN application in apple harvesting robot. Computers and Electronics in Agriculture, 172:105380, 2020. doi:10.1016/j.compag.2020.105380.
• [7] H. Jung, B. Lodhi, and J. Kang. An automatic nuclei segmentation method based on deep convolutional neural networks for histopathology images. BMC Biomedical Engineering, 1:24, 2019. doi:10.1186/s42490-019-0026-8.
• [8] T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, et al. Detection Evaluation. In: COCO. Common Objects in Context [10]. [Accessed: Dec 2023]. https://cocodataset.org/#detection-eval.
• [9] T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, et al. Microsoft COCO: Common Objects in Context. arXiv, 2015. ArXiv.1405.0312. doi:10.48550/arXiv.1405.0312.
• [10] T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, et al., eds. COCO. Common Objects in Context, 2020. [Accessed May 2023], https://cocodataset.org.
• [11] Anaconda, Inc. Conda Documentation, 2023. https://docs.conda.io, [Accessed: 10 Dec 2023].
• [12] CVAT.ai Corporation. CVAT Open Data Annotation Platform, 2023. https://www.cvat.ai, [Accessed: 10 Dec 2023].
• [13] PyTorch Foundation, a project of The Linux Foundation. PyTorch Get Started, 2023. https://pytorch.org/, [Accessed: 10 Dec 2023].
• [14] TorchVision maintainers and contributors. TorchVision: PyTorch’s Computer Vision library. GitHub repository, 2016. https://github.com/pytorch/vision, [Accessed: Jun 2023].
• [15] R. S. Olson, W. La Cava, P. Orzechowski, R. J. Urbanowicz, and J. H. Moore. PMLB: a large benchmark suite for machine learning evaluation and comparison. BioData Mining, 10(36):1-13, 2017. doi:10.1186/s13040-017-0154-4.
• [16] J. van Rijn, J. Vanschoren, B. Bischl, M. Feurer, G. Casalicchio, et al. OpenML Datasets. https://www.openml.org/search?type=data, [Accessed: Dec 2023].
• [17] J. D. Romano, T. T. Le, W. La Cava, J. T. Gregg, D. J. Goldberg, et al. Penn Machine Learning Benchmarks. https://epistasislab.github.io/pmlb/.
• [18] J. D. Romano, T. T. Le, W. La Cava, J. T. Gregg, D. J. Goldberg, et al. PMLB v1.0: an open-source dataset collection for benchmarking machine learning methods. Bioinformatics, 38(3):878-880,
• 2021. doi:10.1093/bioinformatics/btab727.
• [19] J. D. Romano, T. T. Le, W. La Cava, J. T. Gregg, D. J. Goldberg, et al. PMLB v1.0: an open source dataset collection for benchmarking machine learning methods. arXiv, 2021. ArXiv:2012.00058v2. doi:10.48550/arXiv.2012.00058.
• [20] D. Sculley, J. Moser, W. Cukierski, J. Rose, M. O’Connell, et al. Kaggle Datasets, 2023. https://www.kaggle.com/datasets, [Accessed: Jan 2023].
• [21] S. Sibirtsev, S. Zhai, M. Neufang, J. Seiler, and A. Jupke. Mask R-CNN based droplet detection in liquid-liquid systems, Part 2: Methodology for determining training and image processing parameter values improving droplet detection accuracy. Chemical Engineering Journal, 473:144826, 2023. doi:10.1016/j.cej.2023.144826.
• [22] H. Su, S. Wei, M. Yan, C. Wang, J. Shi, et al. Object detection and instance segmentation in remote sensing imagery based on precise Mask R-CNN. In: Proc. 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1454-1457. Yokohama, Japan, 28 Jul - 2 Aug 2019. doi:10.1109/IGARSS.2019.8898573.
• [23] P. Su, J. Joutsensaari, L. Dada, M. A. Zaidan, T. Nieminen, et al. New particle formation event detection with Mask R-CNN. Atmospheric Chemistry and Physics, 22(2):1293-1309, 2022. doi:10.5194/acp-22-1293-2022.