Publications / 2017 Proceedings of the 34rd ISARC, Taipei, Taiwan

Low-latency Vision-based Fiducial Detection and Localization for Object Tracking

Ansu Man Singh, Quang Ha, David K Wood and Mark Bishop
Pages 706-711 (2017 Proceedings of the 34rd ISARC, Taipei, Taiwan, ISBN 978-80-263-1371-7, ISSN 2413-5844)

Real-time vision systems are widely-used in construction and manufacturing industries. The significant proportion of computational resources of such systems is used in fiducial identification and localisation for the tracking of the motion of moving targets. The requirement of the identification systems is to localise a pattern in the image captured by the vision system precisely, accurately, and with a minimum available computation time. In this regard, this paper presents a class of patterns and, accordingly, an algorithm to fulfil the mentioned requirement. Here, the patterns are designed using circular patches of concentric circles (Figure 1) to increase the probability of detection and reduce cases of false detection. In the detection algorithm, the image captured by the vision system is first scaled down for computationally-effective processing. The scaled image is then separated by filtering only the colour components which are made up of outer circular patches in the pattern. A blob detection algorithm is then implemented for the detection of inner circular patches. The inner circles are then localised in the image by using the colour information obtained. Finally, the localised pattern along with the camera and distortion matrix of the vision system is applied in a Perspective-n-Point solving algorithm to estimate orientation and position of the fiducial in the global coordinate system. Our system shows significant enhancement in performance of fiducial detection and identification and achieves the latency of less than ten milliseconds. Thus, it can be used in many real-world applications of infrastructure monitoring that involve high-speed real-time vision systems.

Keywords: Fiducial tracking, marker detection