Task analysis based on observing hands and objects by vision

In order to transmit, share and store human knowledge, it is important for a robot to be able to acquire task models and skills by observing human actions. Since vision plays an important role for observation, we propose a technique for measuring the position and posture of objects and hands in 3-dimensional space at high speed and with high precision by vision. Next, we show a framework for the analysis and description of a task by using an object functions as elements.

Authors

• Yoshihiro Sato
• Keni Bernardin
• Hiroshi Kimura
• Katsushi Ikeuchi

Keywords

• Humans
• Shape
• Robot sensing systems
• Orbital robotics
• Robotics and automation
• Histograms
• Solid modeling
• Position measurement
• Velocity measurement
• Extraterrestrial measurements
• Objective Function
• High Speed
• 3D Space
• Object Position
• Hand Position
• Description Task
• Input Image
• Points In Space
• Color Images
• Kalman Filter
• Event Detection
• Depth Images
• Geometric Model
• Range Of Sensors
• Template Matching
• Human Hand
• Color Model
• Image Histogram
• Object Regions
• Hand Shape
• Hand Region
• Eigenspace
• Color Histogram
• Speed Of The Object
• World Coordinate System
• 2-dimensional Images