Soft sensors are a valuable alternative to the traditional hardware sensors, which are indispensable in configuration of modern systems.
They are often used in process industry, but other applications are possible. This paper describes a possible application of soft sensor for faulty measurement detection and reconstruction in urban traffic. One of the key indicators of traffic control quality in urban traffic control(UTC) systems is the queue length. With the exception of some expensive surveillance equipment, the queue length itself cannot be measured directly. Many methods that estimate the queue length from detector measurements are used in engineering practice, ranging from simple to elaborate ones. The proposed method is a soft sensor based on Gaussian process (GP)~model of the traffic queue length in a traffic cross-section. The resultant soft sensor detects single measurement outliers as well as longer lasting faults and replaces the faulty measurements with model prediction.