The present invention provides an improved method of pedestrian dead reckoning (PDR) and device for performing PDR. An image of the environment to be traversed by the pedestrian is used to define states associated with the PDR environment. The image is utilized to constrain error in the estimated location of the pedestrian. Pairs of states are identified and the characteristics of the defined states are utilized to define the probabilities of transitioning between states of the pair. Possible pedestrian events which may be observed are also defined and for each pair of states, the possibility of detecting an event given the state transition is determined. After detecting a series of events, the transition probabilities and the event probabilities are utilized to determine a state probability that the pedestrian is in a particular state at each particular time. Utilizing these state probabilities an estimated location is provided at each time.