The problem of step counting has been considered for personal navigation while walking and using mobile sensors with low accuracy. Three primary approaches to computing the acceleration vector magnitude in time domain have enabled step counting. When analyzing data from mobile phone sensors for various pedestrian kinds, environmental factors, and their mobility patterns, several methodologies were compared. Except for the approach of normalized auto-correlation based step counting, which only processes short distances, the walking trajectories have been chosen to be long enough (at least 100 meters) to produce statistically representative results. The specifications for a specific step counting system have been developed.