Automatic Laser Pointer Detection Algorithm for Environment Control Device Systems Based on Template Matching and Genetic Tuning of Fuzzy Rule-Based Systems

Abstract

In this paper we propose a new approach for laser-based environment device control systems based on the automatic design of a Fuzzy Rule-Based System for laser pointer detection. The idea is to improve the success rate of the previous approaches decreasing as much as possible the false offs and increasing the success rate in images with laser spot, i.e., the detection of a false laser spot (since this could lead to dangerous situations). To this end, we propose to analyze both, the morphology and color of a laser spot image together, thus developing a new robust algorithm. Genetic Fuzzy Systems have also been employed to improve the laser spot system detection by means of a fine tuning of the involved membership functions thus reducing the system false offs, which is the main objective in this problem. The system presented in this paper, makes use of a Fuzzy Rule-Based System adjusted by a Genetic Algorithm, which, based on laser morphology and color analysis, shows a better success rate than previous approaches.

Self-adjusting focus of attention in combination with a genetic fuzzy system for improving a laser environment control device system

“…In our previous works, we attempt to extend similar capabilities in such a way of enhancing the interaction with devices considering a real-home environment. The idea allows users to send orders by projecting laser spots onto home devices in combination with domotic control systems [6,7,[9][10][11][12]23]. Table 1 includes a summary of the previous works employing laser pointer as a pointing device.…”

“…Thresholding [27,28,[32][33][34][35][36] Template matching [6,7,12,[24][25][26] Colour-based techniques [27][28][29][30][31] Camera or display filters [23,[37][38][39][40][41][42][43] Video and camera network [32,34,38,[44][45][46][47][48][49] Hardware-based approaches [30,50] Classical vision techniques in combination with fuzy rule-based systems [5,7,[9][10][11][12] presented in Table 1. Note that it is necessary to analyze the brightness of the image to correctly calculate the threshold value of the laser spot.…”

“…These works are characterized by the difficulty for detecting the laser spot in environments where the light conditions are not favorable. Other classical vision techniques incorporate a well-known algorithm called template matching, see [6,7,12,[24][25][26]. In our problem a laser spot has a peculiar characteristic: it is similar to a circle.…”

“…As described above these techniques have been frequently employed before, (see Table 1), and allows us to compare their behaviours. Moreover, we already considered such techniques in some of our previous works [5][6][7][8][9][10][11][12].…”

“…On the other hand, we also analyzed the replacement of DT by a new soft computing based decision making system in [5,[9][10][11][12] as well as genetic fuzzy systems (GFSs) [13][14][15], which in combination with TM allowed us to provide good accuracy for the problem of laser-spot detection.…”