Abstract—In this paper, we explore a new algorithm to detect people with color cameras based on our modified Implicit Shape Model (ISM) implemented for grey scale thermal images. The idea of this approach is to convert a color image to a grey scale image, invert it to appear like a thermal image, and then apply the same algorithm that we used for people detection in thermal images. As the first step, we use the ISM to define the proposed centers of people locations. Then we utilize a novel method to detect people based on the density of the concentrated proposed centers by using an auto generated threshold mechanism. Our method is easy to implement and does not require complicated computations; thus resulting in a considerable increase in the speed performance and decrease in the cost of the required hardware on mobile platforms. We evaluated our system by testing it on three image sets for indoor and three for outdoor scenarios. Our system showed promising results in detecting people on images taken by different types of color cameras under difficult scenarios. This technique is used as the vision system for a rescue assist mobile robot built at Flinders University. 
 

Index Terms—color image, people detection, ISM, rescue robot

Cite: Ali H. A. Aldabbagh, Laith A. H. Al-Shimaysawee, and Nasser Asgari, "A Discriminative Approach for People Detection Using Color Camera for Mobile Robot Platforms," International Journal of Mechanical Engineering and Robotics Research, Vol. 5, No. 2, pp. 103-108, April 2016. DOI: 10.18178/ijmerr.5.2.103-108