1. Detection of Binary Square Fiducial Markers Using an Event Camera
- Author
-
Miguel A. Olivares-Mendez, Hamid Sarmadi, Rafael Medina-Carnicer, Rafael Muñoz-Salinas, [Sarmadi,H, Muñoz-Salinas,R, Medina-Carnicer,R] Instituto Maimónides de Investigación en Biomedicina (IMIBIC), Córdoba, Spain. [Muñoz-Salinas,R, Medina-Carnicer,R] Department of Computing and Numerical Analysis, Córdoba University, Campus de Rabanales, Córdoba, Spain. [Olivares-Mendez,MA] Interdisciplinary Centre for Security, Reliability and Trust (SnT), Space Robotics Research Group, Université du Luxembourg, Kirchberg Campus, Luxembourg City, Luxembourg., [Sarmadi, Hamid] Inst Maimonides Invest Biomed IMIBIC, Cordoba 14004, Spain, [Munoz-Salinas, Rafael] Inst Maimonides Invest Biomed IMIBIC, Cordoba 14004, Spain, [Medina-Carnicer, Rafael] Inst Maimonides Invest Biomed IMIBIC, Cordoba 14004, Spain, [Munoz-Salinas, Rafael] Cordoba Univ, Dept Comp & Numer Anal, Campus Rabanales, Cordoba 14071, Spain, [Medina-Carnicer, Rafael] Cordoba Univ, Dept Comp & Numer Anal, Campus Rabanales, Cordoba 14071, Spain, [Olivares-Mendez, Miguel A.] Univ Luxembourg, Space Robot Res Grp, Interdisciplinary Ctr Secur Reliabil & Trust SnT, Kirchberg Campus, L-1855 Luxembourg, Luxembourg, Spain Ministry of Economy, Industry and Competitiveness, and 'Fonds National de la Recherche' (FNR), Luxembourg
- Subjects
FOS: Computer and information sciences ,Health Care::Environment and Public Health::Environment::Environment, Controlled::Lighting [Medical Subject Headings] ,Vision ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Binary number ,Image sensors ,Information Science::Information Science::Computing Methodologies::Computer Systems::Computers [Medical Subject Headings] ,02 engineering and technology ,Organisms::Eukaryota::Animals::Chordata::Vertebrates::Mammals::Primates::Haplorhini::Catarrhini::Hominidae::Humans [Medical Subject Headings] ,0302 clinical medicine ,Silicon retina ,Brightness ,0202 electrical engineering, electronic engineering, information engineering ,General Materials Science ,Computer vision ,Event camera ,Event (probability theory) ,Image segmentation ,Algoritmos ,Detector ,General Engineering ,Cameras ,Inteligencia artificial ,Image reconstruction ,020201 artificial intelligence & image processing ,Procesamiento de imagen asistido por computador ,Contaminación lumínica ,square binary markers ,lcsh:TK1-9971 ,Algorithms ,General Computer Science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,ArUco markers ,silicon retina ,03 medical and health sciences ,Marcadores fiduciales ,Line segment ,Sistemas de computación ,Image sensor ,Real-time systems ,Information Science::Information Science::Computing Methodologies::Image Processing, Computer-Assisted [Medical Subject Headings] ,business.industry ,Image edge detection ,Light intensity ,Anatomy::Sense Organs::Eye::Retina [Medical Subject Headings] ,RGB color model ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,Artificial intelligence ,Fiducial marker ,business ,Information Science::Information Science::Computing Methodologies::Algorithms [Medical Subject Headings] ,030217 neurology & neurosurgery ,Square binary markers - Abstract
Event cameras are a new type of image sensors that output changes in light intensity (events) instead of absolute intensity values. They have a very high temporal resolution and a high dynamic range. In this paper, we propose a method to detect and decode binary square markers using an event camera. We detect the edges of the markers by detecting line segments in an image created from events in the current packet. The line segments are combined to form marker candidates. The bit value of marker cells is decoded using the events on their borders. To the best of our knowledge, no other approach exists for detecting square binary markers directly from an event camera using only the CPU unit in real-time. Experimental results show that the performance of our proposal is much superior to the one from the RGB ArUco marker detector. The proposed method can achieve the real-time performance on a single CPU thread., Comment: An error in the abstract of the IEEE Access version has been corrected in this version. Link to the IEEE Access paper: https://doi.org/10.1109/ACCESS.2021.3058423
- Published
- 2021