Next Article in Journal
Technique for Evaluating the Security of Relational Databases Based on the Enhanced Clements–Hoffman Model
Previous Article in Journal
A Durable PVDF/PFOTES-SiO2 Superhydrophobic Coating on AZ31B Mg Alloy with Enhanced Abrasion Resistance Performance and Anti-Corrosion Properties
Article

Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach

1
Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany
2
Mindgarage, Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany
3
German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
4
Department of Computer Science, Luleå University of Technology, 971 87 Luleå, Sweden
*
Authors to whom correspondence should be addressed.
Academic Editor: Mauro Lo Brutto
Appl. Sci. 2021, 11(23), 11174; https://doi.org/10.3390/app112311174
Received: 5 October 2021 / Revised: 19 November 2021 / Accepted: 22 November 2021 / Published: 25 November 2021
Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is challenging. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Prior datasets for object detection in floor plan images are either publicly unavailable or contain few samples. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10,000 images to address this issue. Our proposed method conveniently exceeds the previous state-of-the-art results on the SESYD dataset with an mAP of 98.1%. Moreover, it sets impressive baseline results on our novel SFPI dataset with an mAP of 99.8%. We believe that introducing the modern dataset enables the researcher to enhance the research in this domain. View Full-Text
Keywords: object detection; Cascade Mask R-CNN; floor plan images; deep learning; transfer learning; dataset augmentation; computer vision object detection; Cascade Mask R-CNN; floor plan images; deep learning; transfer learning; dataset augmentation; computer vision
Show Figures

Figure 1

MDPI and ACS Style

Mishra, S.; Hashmi, K.A.; Pagani, A.; Liwicki, M.; Stricker, D.; Afzal, M.Z. Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach. Appl. Sci. 2021, 11, 11174. https://doi.org/10.3390/app112311174

AMA Style

Mishra S, Hashmi KA, Pagani A, Liwicki M, Stricker D, Afzal MZ. Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach. Applied Sciences. 2021; 11(23):11174. https://doi.org/10.3390/app112311174

Chicago/Turabian Style

Mishra, Shashank, Khurram A. Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, and Muhammad Z. Afzal. 2021. "Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach" Applied Sciences 11, no. 23: 11174. https://doi.org/10.3390/app112311174

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop