AI-enabled Parking Vacancy Prediction Framework using Multi-source Data

The shortage of parking spaces is a chronic problem in Hong Kong. This research aims to develop a holistic framework to make use of the multi-source mobility data and predict the short-term parking vacancy for both on-street and garage parking with and without real-time information. The state-of-the-art deep learning models will be employed to fuse the multi-source data and improve the prediction accuracy, and a novel transfer learning approach will be developed to conduct the prediction without real-time vacancy information. 

A website and mobile phone-based parking guidance application will then be developed, and all the parking-related information can be shared with public agencies and private sectors.

The project has received support from the Smart Traffic Fund.

(Smart Traffic Fund is funding initiated by the Transport Department to support local organisations or enterprises for conducting research and application of innovation and technology with the objectives of enhancing commuting convenience, enhancing the efficiency of the road network or road space, and improving driving safety)