Abstract
Accurate and reliable door detection comprise a critical cornerstone for nowadays robots aiming to offer advanced features and services. At the same time, the range of robotic platforms for indoor scenarios is continuously expanding, emphasizing on the use of low cost, versatile components able to boost widespread use of such solutions. However, respective door detection algorithms have to address specific challenges such as, not relying on specialized expensive sensors, being able to offer robust and accurate operation based on commodity cameras as well as efficient execution on low resource embedded systems. Driven by aforementioned observations in this paper the design and development of a practical and reliable door detection methodology is presented based solely on typical off the shelf web-camera, while posing minimum requirements on the height or angle it is mounted. Furthermore, a critical contribution of this paper is the experimental evaluation of the developed algorithm on popular embedded systems that are based on Micro Controller Units (MCUs) commonly found on contemporary robotic platforms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Karakaya, S., et al.: Development of a human tracking indoor mobile robot platform. In: 16th International Conference on Mechatronics - Mechatronika 2014, Brno (2014)
Deng, Z-H., et al.: The design and implement of household robot based on android platform. In: 2014 IEEE WARTIA, 29–30 September (2014)
Mahmood, F., et al.: A self-organizing neural scheme for door detection in different environments. Int. J. Comput. Appl. 60(9) (2012)
Murillo, A.C., et al.: Door detection in images integrating appearance and shape cues. In: EEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, USA (2007)
Mehmood, F., et al.: Techniques and approaches in Robocup@Home – a review. In: International Conference on Information and Communication Technologies (ICICT), 12–13 December (2015)
Christopoulos, K., et al.: Designing the next generation of home automation combining IoT and robotic technologies. In: 20th Pan-Hellenic Conference on Informatics (2016)
Hensler, J., Blaich, M., Bittel, O.: Real-time door detection based on adaboost learning algorithm. In: Gottscheber, A., Obdržálek, D., Schmidt, C. (eds.) EUROBOT 2009. CCIS, vol. 82, pp. 61–73. Springer, Heidelberg (2010). doi:10.1007/978-3-642-16370-8_6
Al-Shebani, Q., et al: Embedded door access control systems based on face recognition: a survey. In: 7th ICSPCS, Carrara, VIC, pp. 1–7 (2013)
Eberst, C., et al.: Vision-based door-traversal for autonomous mobile robots. In: Intelligent Robots and Systems, IROS 2000 (2000)
Kragic, D., et al.: Visually guided manipulation tasks. Robot. Auton. Syst. 40(2–3), 193–203 (2002)
Seo, M.-W., Kim, Y.-J., Lim, M.-T.: Door traversing for a vision-based mobile robot using PCA. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS, vol. 3684, pp. 525–531. Springer, Heidelberg (2005). doi:10.1007/11554028_73
Muñoz-Salinas, R., Aguirre, E., García-Silvente, M.: Detection of doors using a genetic visual fuzzy system for mobile robots. Auton. Robot. 21(2), 123–141 (2006)
Monasterio, I., et al.: Learning to traverse doors using visual information. Math. Comput. Simul. 60(3), 347–356 (2002)
Lazkano, E., et al.: On the use of bayesian networks to develop behavior for mobile robots. Robot. Auton. Syst. 55(3), 253–265 (2007)
Viola, P., et al.: Rapid object detection using a boosted cascade of simple features. In: Conference on Computer Vision and Pattern Recognition, IEEE (2001)
University of Auckland in New Zealand, Tools for Haar training. https://www.cs.auckland.ac.nz/~m.rezaei/Tutorials/Haar-Training.zip
Thorsten Ball Opencv Haar Classifier Training. https://github.com/mrnugget/opencv-haar-classifier-training
Object detection Using OpenCV Haar Feature-based Cascade Classifiers, Yan KOËTH. https://github.com/xsyann/detection
Acknowledgment
This study is part of the collaborative project RADIO which is funded by the European Commission under Horizon 2020 Research and Innovation Programme with Grant Agreement Number 643892.
Open Data Access.
All images used as training and test sets throughout this paper are owned by the Embedded System Design and Application Lab (http://esda-lab.cied.teiwest.gr). The training/test sets are offered to the research community for open access (https://github.com/ESDA-LAB/Door-detection) under the requirement to reference properly the current paper whenever they are published, presented or announced.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Spournias, A., Skandamis, T., Antonopoulos, C.P., Voros, N.S. (2017). Door Detection Algorithm Development Based on Robotic Vision and Experimental Evaluation on Prominent Embedded Systems. In: Ronzhin, A., Rigoll, G., Meshcheryakov, R. (eds) Interactive Collaborative Robotics. ICR 2017. Lecture Notes in Computer Science(), vol 10459. Springer, Cham. https://doi.org/10.1007/978-3-319-66471-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-66471-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66470-5
Online ISBN: 978-3-319-66471-2
eBook Packages: Computer ScienceComputer Science (R0)