Active tracking

This work describes a method for real-time motion detection using an active camera mounted on a pan/tilt platform. Image mapping is used to align images of different viewpoints so that static camera motion detection can be applied. In the presence of camera position noise, the image mapping is inexact and compensation techniques fail. The use of morphological filtering of motion images is explored to desensitize the detection of algorithm in inaccuracies in background compensation. Two motion detection techniques are examined, and experiments to verify the methods are presented. The system successfully extracts moving edges from dynamic images, even when the pan/tilt angles between successive frames are as large as 3/spl deg/.

Authors

• Don Murray
• Anup Basu

Keywords

• Cameras
• Motion detection
• Tracking
• Computer vision
• Filtering
• Animals
• Application software
• Service robots
• Robot vision systems
• Telecommunication computing
• Activity Tracker
• Inaccuracy
• Camera Position
• Camera Motion
• Morphological Filtering
• Denoising
• Reference Frame
• Binary Image
• Position Error
• Magnitude Of Error
• Position Estimation
• Image Edge
• Pixel Position
• Spatial Derivatives
• Principal Plane
• Temporal Derivative
• Regional Motion
• Angular Error
• Subtraction Images
• Pinhole Camera Model
• Error Compensation
• Edge Strength
• Camera Rotation
• Compensation Algorithm
• Camera Orientation
• Angular Velocity
• Spatial Information