#az2418

This map is very innovative if compared to other studies of urban perception by the level of interaction it allows. This method developed uses geo-tagged street views and a web-based visual survey. An online experiment conducted in this thesis collected 394 participants in 20 days who were asked to guess the locations of street views from a familiar neighborhood.  Results are presented in the form of interactive visualizations. According to the author: analysis reveals that memory for exact location of place improves with degree of interaction and proximity to center, rather than number of encounters; memory for one location may vary dramatically between different viewpoints. The results also suggest that the irregularity of urban structure doesn’t prevent the forming of strong mental images.

The selfiecity project collected 3840 selfies from Instagram. We analyzed them using human judgements and automatic methods (for more details: see dataset on selfiecity). The project brings together Demographics, pose, general features and aparent mood of the person on the picture.Demographics is location (captured by Instagram app) and gender and age (tagged and guesses by Mechanical Turk workers.) Pose is the direction a person is facing (up/down, left/right, head tilt). This was automatically extracted by the Rekognition API. Features is an estimate of facial attributes by Rekognition, such as the presence of glasses, or if mouth or eyes are open. Question marks indicate unclear results. Mood is the estimated mood of a person - again automatically extracted by Rekognition.