Modern transportation systems are highly depend on quality and complete source of data for traffic state identification, prediction and forecasting processes. Due to device (sensor, camera, and detector) failures, communication problems, some sources inevitably miss the data, which leads to the degradation of traffic data quality. Data pre processing is an important one for transport related applications. Imputation is the process of finding missing data and make available as complete data. Both Spatial and temporal information has been a high impact on impute the traffic data. In this paper deep learning based stacked denoise autoencoder (one autoencoder at a time) is proposed to impute the traffic data with less computational complexity and high performance. Experimental results demonstrate that autoencoder performs well in random corruption aspect with less complexity.