The travel demand matrix, also known as origin-destination matrix (OD matrix), is an effective and efficient instrument in urban planning as well as managing traffic. Given their nature and extent of operation, usually, direct methods of estimating the matrix impose very high costs in terms of both time and human resources. Thus, over the past three decades, numerous attempts have been made to propose alternative methods of estimating and observing the OD matrix. One of these methods is the use of information collected by traffic sensors. In this thesis, it has been attempted to consider two problems: the first one is OD matrix estimation on congested networks in large scale networks and the second one is OD matrix observation on uncongested networks. Regarding to OD matrix estimation, using traffic counts on some links the Bayesian inference approach which is the most popular methods for estimating the OD matrix is used.
