Robust Object Tracking Using an Adaptive Color Model

In this paper we present a new robust face tracking method based on the condensation algorithm that uses a sampling based density representation. A two-dimensional color model is used to approximate the face color. We modified the condensation algorithm to provide color adaptability to the abrupt change of illumination and to the tracking of differently colored people. According to the face size and location uncertainty, the searching range is automatically determined and it makes the algorithm extremely robust and efficient. The tracker operates at real-time and actively controls a camera pan-tilt in order to locate a person's face in the center of the image. Experimental results show the algorithm's robustness to the agile motion of face and to the dramatic change of illumination in the presence of complex background.

Authors

• Gi-jeong Jang
• In-So Kweon

Keywords

• Robustness
• Lighting
• Cameras
• Uncertainty
• Application software
• Human computer interaction
• Computational efficiency
• Computer science
• Sampling methods
• Tracking
• Adaptive Model
• Color Model
• Robust Tracking
• Robust Object Tracking
• Condensation
• Imaging Center
• Illumination Changes
• Central Face
• Presence Of Background
• Facial Color
• Personal Face
• Face Size
• Time Step
• Maximum Likelihood Estimation
• Unimodal
• Skin Color
• Color Space
• Posterior Density
• Motion Model
• Difference Map
• Color Histogram
• Face Position
• Update Phase
• Prediction Phase
• Sum Of Measures
• Texture Map
• Portion Of Region