Choosing a seat for traveling can be a complex evaluation of constraints depending on personal preferences. There are websites that help to choose the best seat in a bus, in a train, or on an airplane. However, these recommendations only consider seat-related factors and not the view from the window. While a scenic view rarely influences the decision for a seat on a plane, it is much more important for train rides and especially for scenic bus tours. Therefore, travel website users often discuss which side offers the best view on a specific trip. We propose an algorithm, which decides on which side of the road the view is the most scenic based on Google Street View images. These results can be used by travelers to choose a seat and by scenic tour providers to balance the scenic views between sides or add options during checkout.

The lack of certain types of geographic data prevents the development of location-aware technologies in a number of important domains. One such type of "unmapped" geographic data is space usage rules (SURs), which are defined as geographically-bound activity restrictions (e.g. "no dogs", "no smoking", "no fishing", "no skateboarding"). Researchers in the area of human-computer interaction have recently begun to develop techniques for the automated mapping of SURs with the aim of supporting activity planning systems (e.g. one-touch "Can I Smoke Here?" apps, SUR-aware vacation planning tools). In this paper, we present a novel SUR mapping technique -- SPtP -- that outperforms state-of-the-art approaches by 30% for one of the most important components of the SUR mapping pipeline: associating a point observation of a SUR (e.g. a 'no smoking' sign) with the corresponding polygon in which the SUR applies (e.g. the nearby park or the entire campus on which the sign is located). This paper also contributes a series of new SUR benchmark datasets to help further research in this area.

Navigation systems allow drivers to find the shortest or fastest path between two or multiple locations mostly using time or distance as input parameters. Various researchers extended traditional route planning approaches by taking into account the user's preferences, such as enjoying a coastal view or alpine landscapes during a drive. Current approaches mainly rely on volunteered geographic information (VGI), such as point of interest (POI) data from OpenStreetMap, or social media data, such as geotagged photos from Flickr, to generate scenic routes. While these approaches use proximity, distribution or other spatial relationships of the data sets, they do not take into account the actual view on specific route segments. In this paper, we propose Autobahn: a system for generating scenic routes using Google Street View images to classify route segments based on their visual characteristics enhancing the driving experience. We show that this vision-based approach can complement other approaches for scenic route planning and introduce a personalized scenic route by aligning the characteristics of the route to the preferences of the user.

Recent work has identified the lack of space usage rule (SUR) data -- e.g. "no smoking", "no campfires" -- as an important limitation of online/mobile maps that presents risks to user safety and the environment. In order to address this limitation, a large-scale means of mapping SURs must be developed. In this paper, we introduce and motivate the problem of mapping space usage rules and take the first steps towards identifying solutions. We show how computer vision can be employed to identify SUR indicators in the environment (e.g. "No Smoking" signs) with reasonable accuracy and describe techniques that can assign each rule to the appropriate geographic feature.