Abstract
In this paper, the problem of how to estimate the distance between an infrared emitter diode (IRED) and a camera from pixel grey-level intensities is examined from a practical standpoint. Magnitudes that affect grey level intensity were defined and related to the zero frequency component from the FFT image. A general model was also described and tested for distance estimation over the range from 420 to 800 cm using a differential methodology. Method accuracy is over 3%.
Highlights
Artificial vision is widely used in robotics applications
Later, when the method for distance estimation using FFT has been fully developed, it will be possible to carry out fusion of this data with data obtained from the geometric calibration of cameras in order to improve generation of the variables and parameters involved in pose and location of the mobile incorporating the infrared emitter diode (IRED)
A priori, a direct proportionality between grey level intensities, light source intensities, camera exposure time and inverse square distance is assumed. This statement can be obtained if radiometry is applied to model the image formation and the inverse square distance law is taken into account [9]
Summary
Artificial vision is widely used in robotics applications. One of the most important tasks in this area is robot positioning. Of the kind of projection used to model the vision system, only 2-D robot positioning can be carried out when using a single camera. Additional information can be extracted from pixel-grey level intensities in order to obtain redundancy for the positioning task, using a geometrical camera model. Later, when the method for distance estimation using FFT has been fully developed, it will be possible to carry out fusion of this data with data obtained from the geometric calibration of cameras in order to improve generation of the variables and parameters involved in pose and location of the mobile incorporating the IRED. Under the conditions described above, the distance between the IRED and the camera could present a solution to obtaining the third dimension lost in projection based models. - the sensorial system is complementary to other methods, facilitating ease of data fusion; etc
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
