People counter based on fusion of reflected light intensities from an infrared sensor array

An effective low-cost solution to determine characteristic features of objects from a simple infrared diode array, working on the reflection light scanner principle and using the fusion of amplitude information to detect and characterize objects, has been designed. Essentially, two arrays of several emitter-receiver pairs are mounted on opposite sides of the area of observation (e.g. a conveyer, doorway etc.), enabling the estimation of the size of a moving object in different dimensions and its reflection coefficient. The results show that from simple light intensity measurements, a variety of objects can be reliably recognised. As an example, the problem of determining the number of persons traversing doorways is addressed. With the proposed array processing, people can be recognised correctly and are well separable from other echoes (motion of hands etc.), making the performance far more reliable than that of ordinary light barriers.

[1]  Antonio Albiol,et al.  Real-time high density people counter using morphological tools , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Billur Barshan,et al.  Differentiation and localization of target primitives using infrared sensors , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Paolo Dario,et al.  A low-cost, composite sensor array combining ultrasonic and infrared proximity sensors , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[4]  Paul J. Besl,et al.  Active, optical range imaging sensors , 1988, Machine Vision and Applications.

[5]  L. Korba,et al.  Active infrared sensors for mobile robots , 1994 .

[6]  Nicola J. Ferrier,et al.  Using infrared sensors and the Phong illumination model to measure distances , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).