tailieunhanh - Robust and fast algorithm for artificial landmark detection in an industrial environment

In this paper, we have attempted to focus on the continuous transition of the biped mechanism from the single support phase (SSP) to the double support phase (DSP) and vice versa. Three methods have been compared for this purpose. | Journal of Automation and Control Engineering, Vol. 1, No. 2, June 2013 Robust and Fast Algorithm for Artificial Landmark Detection in an Industrial Environment Miguel Pinto, Filipe Santos, A. Paulo Moreira, and Roberto Silva INESC Porto - Institute for Systems and Computer Engineering of Porto, Faculty of Engineering, University of Porto, Porto, Portugal Email: {dee09013, dee09043, amoreira, ee06154}@ Abstract—This paper describes a solution to detect and gather information on artificial landmarks placed in an industrial floor. This solution is composed of an observation module (artificial vision plus a chamber for light conditioning) and a fast algorithm for detecting and extracting landmarks. It is applicable with two types of landmarks, which provide useful information and in the future the solution may be applied in Autonomous Guided Vehicles (AGVs) for locating or path following. The execution time and accuracy results of the detection and extraction algorithm are presented in this paper, when 1 applied in landmarks in good and degraded conditions. Index Terms—Artificial Landmark, Autonomous Guided Vehicle (AGV) I. Artificial implemented in an embebed computing system with real time constrains. Figure 1. Observation Module (camera and chamber) Vision, INTRODUCTION According to David A. Schoenwald [1], autonomous unnamed vehicles (AUVs)” (.) need to understand enough about their surroundings so that they can function with minimal or no input from humans. This implies sensors are needed that are capable of "seeing" terrain (.)”. The fundamental motivation for this work is the development of a sensorial system based on artificial vision which can capture relevant information on artificial landmarks. The information acquired will be useful in the future for the vehicle localisation and for navigation purposes. The presented observation module is composed of a camera inside a chamber, as shown in Fig. 1. The aim with the chamber is to perform