Embodiments are provided for deliver multimedia information to a transportation apparatus through a UAV network. After the transportation apparatus enters an area, one or more UAVs may be configured to capture one or more images of an interior of the transportation apparatus. Geographical location of the transportation apparatus can be obtained. Image analysis may be employed to analyze the images to obtain passenger. Based on the geographical information regarding the transportation apparatus, and passenger, specific multimedia information can be determined for presentation to the passenger(s) in the transportation apparatus. The determined multimedia information may include media contents of interest to the passenger(s) and available in the geographical location the transportation apparatus is currently traveling in. The determined multimedia information can be transmitted to transportation apparatus for presentation to the passenger.