FIDUCIAL MARKERS EVALUATION USING ONBOARD CAMERA OF SERVOSILA ENGINEER MOBILE ROBOT IN INDOOR SETTINGS

Abstract

Modern tasks of special areas of robotics, including search and rescue operations in urban
areas, face a number of obstacles to mobile robotics, where the automatic performance of various functions
by mobile robots remains a key task. One of the important requirements for the algorithms and
software of the robot is the possibility of autonomous decision-making and automatic performance by
the robot of various functions, both low and high levels based on the embedded algorithms and information
received from the on-board sensors of the robot. To date, the most common on-board robot sensors
are cameras of various types, due to their technical capabilities and lower cost relative to lidars
and other sensors that provide visual information in the form of digital images. Camera calibration is a
necessary process for extracting accurate information from digital images. This process is necessary to
obtain an exact correspondence between the three-dimensional object space and the pixel space of the
image, for the possibility of subsequent use of computer vision algorithms, aggregation, and information
processing. Calibration of digital cameras is an integral part of a number of practical tasks of machine
vision such as navigation of mobile robotic systems, medicine, reconstruction of dense and sparse threedimensional
maps of the environment, video surveillance and visual inspection, visual simultaneous
localization and mapping, etc. The urgency of the problem of camera calibration is defined by the presence
of many different methods of calibration and calibration templates. Each individual solution is
suitable only for special conditions, e.g., lack of lighting, bad weather conditions, the presence of thirdparty
objects blocking visibility, etc. In most cases, each calibration method uses a specific calibration
pattern. Camera calibration is usually associated with the use of special calibration templates. They
allow to achieve the most accurate results due to a previously known geometric structure. Currently, the
procedure for camera calibrating of robotic systems is carried out in laboratory conditions using the
classic “chessboard” method. In addition, there are only a few alternative approaches that are in their infancy state both in Russia and abroad. On the other hand, research into camera calibration methods
continues and new alternatives for camera calibration are emerging. One of the new directions is the
use of fiducial marker systems as a reference object. A variety of parameters such as the size of the calibration
template, the dimension of the calibration data set, the distribution of distances from the camera
to objects on the stage, etc. creates a vast area for experimental testing of optimal camera calibration
parameters. This paper presents a research of automatic camera calibration using fiducial marker systems
(FMS), which are located on the surface of the robot. Based on the results of virtual experiments
with FMS in the Gazebo simulation environment of the robotic operating system ROS, two different
types of FMS were selected that are optimal relative to other types of FMS covered by our previous
studies in terms of the resistance of FMS to systematic occlusion of the marker area and the effect of
marker size on quality of its recognition. The selected FMS were tested using the onboard camera of the
Russian mobile robot Servosila Engineer in indoor settings to assess the correlation of results in virtual
and real environments.