TITLE:
Human Detection by Robotic Urban Search and Rescue Using Image Processing and Neural Networks
AUTHORS:
Fahed Awad, Rufaida Shamroukh
KEYWORDS:
Urban Search and Rescue, Human-Robot Interaction, Autonomous Systems, Intelligent Interface, Neural Networks
JOURNAL NAME:
International Journal of Intelligence Science,
Vol.4 No.2,
April
16,
2014
ABSTRACT:
This paper proposes a new approach for detecting human survivors in destructed
environments using an autonomous robot. The proposed system uses a passive
infrared sensor to detect the existence of living humans and a low-cost camera
to acquire snapshots of the scene. The images are fed into a feed-forward
neural network, trained to detect the existence of a human body or part of it
within an obstructed environment. This approach requires a relatively small
number of images to be acquired and processed during the rescue operation,
which considerably reduces the cost of image processing, data transmission, and
power consumption. The results of the conducted experiments demonstrated that
this system has the potential to achieve high performance in detecting living
humans in obstructed environments relatively quickly and cost-effectively. The
detection accuracy ranged between 79% and 91% depending on a number of factors
such as the body position, the light intensity, and the relative color matching
between the body and the surrounding environment.