COMPARISON OF DEEP LEARNING TECHNIQUES FOR DETECTION OF DOORS IN INDOOR ENVIRONMENTS
Abstract
In indoor environments, the detection of doors (open, semi-opened, and closed) is a crucial task for a variety of fields such as robotics, computer vision, and architecture. The studies that are addressed the door detection problem can be divided into three major categories: 1) closed doors via visual data, 2) open doors via range data, and 3) open, semi-opened, and closed doors via point cloud data. Although some successful studies have been proposed being detected doors via visual and range data under specific circumstances, in this study, we exploited point cloud data due to its ability to describe the 3D characteristic of scenes. The main contribution of this study is two-fold. Firstly, we mainly intended to discover the potential of point-based deep learning architectures such as PointNet, PointNet++, Dynamic Graph Convolutional Neural Network (DGCNN), PointCNN, and Point2Sequence, in contrast to previous studies that generally defined a set of rules depending on the type of door and characteristics of the data, Secondly, the OGUROB DOORS dataset is constructed, which contains point cloud data captured in the GAZEBO simulation environment in different robot positions and orientations. We used precision, recall, and F1-score metrics to analyze the merit and demerit aspects of these architectures. Also, some visual results were given to describe the characteristics of these architectures. The test results showed that all architectures are capable of classifying open, semi-opened, and closed doors over 98% accuracy.
Keywords
Door Detection , Point Cloud Data , Deep Learning , Door Dataset
Kaynakça
- Andreopoulos, A. & Tsotsos, J. K. (2008). Active vision for door localization and door opening using playbot: A computer controlled wheelchair for people with mobility impairments. In 2008 Canadian Conference on Computer and Robot Vision, 3-10, Windsor, Canada.
- Arduengo, M., Torras, C. & Sentis, L. (2019). Robust and Adaptive Door Operation with a Mobile Robot, arXiv, 1902.09051.
- Bayram, K., Kolaylı, B., Solak, A., Tatar, B., Turgut, K. ve Kaleci, B. (2019). 3B Nokta Bulutu Verisi ile Bölge Büyütme Tabanlı Kapı Bulma Uygulaması. Türkiye Robotbilim Konferansı, 139-145, İstanbul, Turkiye.
- Beraldo G., Termine E., Menegatti E. (2019). Shared-Autonomy Navigation for Mobile Robots Driven by a Door Detection Module. In: Alviano M., Greco G., Scarcello F. (eds) AI*IA 2019 – Advances in Artificial Intelligence. AI*IA 2019. Lecture Notes in Computer Science, vol 11946. Springer, Cham. doi: https://doi.org/10.1007/978-3-030-35166-3_36
- Bersan, D., Martins, R., Campos M. & Nascimento, E. R. (2018). Semantic Map Augmentation for Robot Navigation: A Learning Approach Based on Visual and Depth Data, 2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE), João Pessoa, Brazil, 45-50. doi: 10.1109/LARS/SBR/WRE.2018.00018
- Borgsen, S. M. Z., Schöpfer, M., Ziegler, L. & Wachsmuth, S. (2014). Automated Door Detection with a 3D-Sensor. Canadian Conference on Computer and Robot Vision, 276-282, Montreal, QC, Canada.
- Budroni, A. & Böhm, J. (2010). Automatic 3D modelling of indoor manhattan-world scenes from laser data. Proceedings of the International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 38(Part 5), 115-120.
- Burhanpurkar, M., Labbe, M., Guan, C., Michaud, F. & Kelly, J. (2017). Cheap or Robust? The practical realization of self-driving wheelchair technology. IEEE International Conference on Rehabilitation Robotics (ICORR), 1079–1086, London, UK.
- Chao, P., Kao, C. Y., Ruan, Y. S., Huang, C. H. & Lin, Y. L. (2019). Hardnet: A low memory traffic network, ArXiv, vol. abs/1909.00948.
- Chen, W., Qu, T., Zhou, Y., Weng, K., Wang, G. & Fu, G. (2014). Door recognition and deep learning algorithm for visual based robot navigation. In 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014), 1793-1798, Bali, Indonesia.