Vision guided mobile robot navigation: The vision-guided mobile robot navigation algorithm uses a geometric map of the environment created by model-based reasoning and Kalman filtering. The robot will be capable of autonomously navigating in hallways using vision for self-location and collision avoidance.
Person tracking with a mobile robot: Person tracking with a mobile robot is an important research topics in the machine vision area. Mobile robots can follow people intelligently in a crowded area. The skin segmentation and face detection algorithms will be used for identifying the target to be tracked.
Tracking Multiple Objects Using Particle Filter: Object tracking through a temporal sequence of images is a challenging problem. Tracking is the propagation of shape and motion estimates over time, driven by a temporal stream of observations. The noisy observations that arise in realistic problems demand a robust approach involving propagation of probability distributions over time. Modest levels of noise may be treated satisfactorily using Gaussian densities, and this is achieved effectively by Kalman filtering. More pervasive noise distributions as commonly arise in visual background clutter; demand a more powerful, non-Gaussian approach. A more robust solution to this tracking problem can be obtained with the Condensation (Conditional Density Propagation) algorithm. The Condensation algorithm overcomes the pitfall of the Kalman filtering by allowing the probability density representation to be multi-modal, and therefore capable of simultaneously maintaining multiple hypotheses about the true state of the target. This allows recovery from brief moments in which the background features appear to be more target-like (and therefore a more probable hypothesis) than the features of the true object being tracked. The recovery takes place as subsequent time-steps in the image sequence provide reinforcement for the hypothesis of the true target state, while the hypothesis for the false target is not reinforced and therefore gradually diminishes.