Elsevier

Applied Soft Computing

Volume 32, July 2015, Pages 250-265
Applied Soft Computing

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

https://doi.org/10.1016/j.asoc.2015.03.011Get rights and content

Highlights

  • New interaction system in real environments by means of a laser pointer.

  • New approach using a self-adjusting focus of attention that increases the results.

  • The paper can detect the laser spot in a real environment.

  • The system uses: genetic fuzzy systems and genetic programming to self-adjust the FOA.

Abstract

This paper presents a new algorithm capable of improving the accuracy level of a laser pointer detector used within an interactive control device system. A genetic programming based approach has been employed to develop a focus of attention algorithm, which works cooperatively with a genetic fuzzy system. The idea is to improve the detection of laser-spots depicted on images captured by video cameras working on home environments. The new and more accurate detection system, in combination with an environment control system, allows to send correct orders to home devices. The algorithm is capable of eradicating false offs, thus preventing devices to autonomously activate/deactivate appliances when orders have not been really signalled by users. Moreover, by adding self-adjusting capabilities with a genetic fuzzy system the computer vision algorithm focuses its attention on a narrower area of the image. Extensive experimental results show that the combination of the focus of attention technique with dynamic thresholding and genetic fuzzy systems improves significantly the accuracy of the laser-spot detection system while maintaining extremely low false off rates in comparison with previous approaches.

Section snippets

Introducction

Human beings feature both the desire and need to control the environment, probably as a result of attempting to improve their quality of life. For example, in prehistory when fire taming could mean a difference between life and death; later on history while managing and manipulating natural resources as in agriculture; and more recently with the arrival of the technological society where a plethora of electronic devices are nowadays part of our life.

Today, every conventional-home features tens

Releated works

In the literature, different environment control systems have already been described; see [4], [6], [16], [17], [18], [19], [20], [21], [22]. Note that, a large set of previous works, where different techniques are used, are based on laser pointers; see Table 1. In those works, the goal is to interact with a projection screen by means of the laser pointer. In our previous works, we attempt to extend similar capabilities in such a way of enhancing the interaction with devices considering a

Classical vision techniques

We describe here some of the classic computer vision techniques we have employed as our base case for comparison. 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].

System description

In order to provide with a home environment laser-pointer interactive system, we need a number of modules that cooperate to achieve the desired functionality. Although the main goal of this paper is to improve the laser-spot detection system, we provide here a summary of the whole system including their components and relationships. In particular, the system includes a tool that helps the system to adapt to new environments by providing the location of controllable devices. We consider that the

Focus of attention and its application for the improvement of a laser-spot detection system

Although other approaches were followed to improve the results achieved by the described techniques; see [6], [7], [8], [9], [10], [11], [12], TM was always the base for the feature extraction process. It was noteworthy that every time that a new method was proposed an improvement was attained; nevertheless, we remark that TM was the main source of false negatives that persistently deteriorated the results. Hence, this algorithm tends to find, under certain conditions, images sections that do

FOA experimental design

Before presenting the results, we must consider that FOA uses a GP based algorithm as a self-adjusting process. It is therefore necessary to provide a large set of examples to achieve a correct training process while obtaining the best results. The set consists of 480 images, selected from 990 images acquired with a real system operating in a home environment. The images used by the self-adjusting process are only those containing the laser spot. Thus, the applied images have the following

Conclusions

This paper shows the interest of a self-adjusting the GP-based focus of attention technique when working in collaboration with classical computer vision techniques and genetic fuzzy systems for a specific problem: the accurate detection of laser spots. The main goal is to offer a reliable user interface with standard domotic systems based on laser pointers and video cameras, which are capable of detecting user actions and sending the appropriate orders to devices.

Previous works showed us that

Acknowledgements

This work has been supported by the Seventh Framework Programme of the European Union through the Marie Curie International Research Staff Scheme, FP7-PEOPLE-2013-IRSES, Grant 612689 ACoBSEC, Spanish Ministry of Science and Innovation under project TIN2011-28627-C04-03, regional government “Gobierno de Extremadura, Consejería de Economía-Comercio e Innovación” and FEDER, project GRU10029. This work is also sponsored by CONACyT México through the project 155045 – “Evolución de Cerebros

References (76)

  • M. Begum et al.

    Integrated fuzzy logic and genetic algorithmic approach for simultaneous localization and mapping of mobile robots

    Appl. Soft Comput.

    (2008)
  • O. Cordón et al.

    A genetic learning process for the scaling factors, granularity and contexts of the fuzzy rule-based system data base

    Inf. Sci.

    (2001)
  • Z. Bien et al.

    LARES: an intelligent sweet home for assisting the elderly and the handicapped

  • Z.Z. Bien et al.

    User-friendly interaction/interface control of intelligent home for movement-disabled people

  • Peine Alexander

    Understanding the dynamics of technological configurations: a conceptual framework and the case of smart homes

    Technol. Forecast. Soc. Change

    (2009)
  • E. Clemente et al.

    Self-adjusting focus of attention by means of GP for improving a laser point detection system

  • F. Chávez et al.

    An independent and non-intrusive laser pointer environment control device system

  • F. Chávez et al.

    Hybrid laser pointer detection algorithm based on template matching and fuzzy rule-based systems for domotic control in real home environments

    Appl. Intell.

    (2010)
  • F. Chávez et al.

    Environment control for handicapped people by laser pointer and template matching (Spanish)

  • F. Chávez et al.

    Evolutionary tuned of a fuzzy rule-based system for a system control environment by means of a laser pointer (Spanish)

  • F. Chávez et al.

    Evolutionary learning of a laser pointer detection fuzzy system for an environment control system

  • F. Chávez et al.

    Genetic tuning of a laser pointer environment control device system for handicapped people with fuzzy systems

  • F. Chávez et al.

    Automatic laser pointer detection algorithm for environment control device systems based on template matching and genetic tuning of fuzzy rule-based systems

    Int. J. Comput. Intell. Syst.

    (2012)
  • O. Cordón
    (2001)
  • F. Herrera

    Genetic fuzzy systems: taxonomy, current research trends and prospects

    Evol. Intell.

    (2008)
  • M.R. Alam et al.

    A review of smart homes past, present, and future

    IEEE Trans. Syst. Man Cybern. C: Appl. Rev.

    (2012)
  • L. Jiang et al.

    Smart home research

  • R. Kadouche et al.

    Personalization and multi-user management in smart homes for disabled people

    Int. J. Smart Home

    (2009)
  • R. Orpwood et al.

    The design of smart homes for people with dementia user-interface aspects

    Univers. Access Inf. Soc.

    (2005)
  • J. Park et al.

    Intelligent systems and smart homes

    Inf. Syst. Front.

    (2009)
  • K.-H. Park et al.

    Robotic smart house to assist people with movement disabilities

    Auton. Robot.

    (2006)
  • C.C. Kemp et al.

    A point-and-click interface for the real world: laser designation of objects for mobile manipulation

  • C. Kirstein et al.

    Interaction with a projection screen using a camera-tracked laser pointer

  • D.R. Olsen et al.

    Laser pointer interaction

  • H. Seki et al.

    Development of position recording system on structural surface using laser pointer

  • M. Meško et al.

    Laser spot detection

    J. Inf. Control Manage. Syst.

    (2013)
  • S. Watanabe et al.

    Recognition of character drawn on screen with laser pointer

  • N.W. Kim et al.

    Vision based laser pointer interaction for flexible screens

    (2007)
  • Cited by (10)

    • Observer-based method for synchronization of uncertain fractional order chaotic systems by the use of a general type-2 fuzzy system

      2016, Applied Soft Computing Journal
      Citation Excerpt :

      In [23] fuzzy and ant colony optimization based method is presented for wireless sensor networks. The genetic and particle swarm optimization algorithms are used in [24,25], to optimize type-1 fuzzy based controllers. A review of the bio-inspired methods used in the interval type-2 fuzzy controllers is considered in [20].

    View all citing articles on Scopus
    View full text