10-12-2012, 02:00 PM
REAL TIME IMPLEMENTATION OF HUMAN-ROBOT INTERACTION FOR SWARM APPLICATIONS
ROBOT SLIDE.ppt (Size: 1.56 MB / Downloads: 50)
Robotics
Robots
Electro-mechanical machines
Computer controlled device
Can work like humans
ASIMO, nano robots, swarm robots, industrial robots, military robots, mobile and servicing robots
Robotics
Applications
Swarm Robotics
Swarm robotics is a new approach for coordinating a large number of relatively small robots.
Main inspiration is from the observation of insects.
Robots are being integrated into working tasks to replace humans.
Miniaturation and cost are key features.
simple and cheap robot.
Requirements: robustness, effectiveness, low cost, flexibility, scalability etc.
Human Robot Interaction
Interaction between people and robots.
Gestures are used for human-robot interaction.
Gestures can originate from any body motion.
Commonly from face/hand.
Gesture recognition-understand human body language.
Help human to interact with machines without any mechanical devices.
Hand Detection
Hand detection
Detection of hand in an image, background objects are avoided for feature extraction.
Skin color is the key component.
Detecting skin and non-skin.
Detecting image pixels and regions that contains skin-tone color.
Background is controlled.
Appearance depends on illumination conditions.
Two phases
Training phase
Detection phase
Detection Phase
Two steps
Converting the image into some color space that was used in training phase.
Classifying each pixel using the skin classifier to either skin or non-skin.
RGB color space
Skin classifier
Variety of classification techniques.
Any pixel which color falls inside the skin color class boundary is labeled as skin.
Conclusion
Hand detection and feature extraction removes noise from the image.
System performance and accuracy will increase.
Swarm robots movement can be controlled through gestures.