Ping Hunt builds scavenger hunts automatically from street-level imagery
Ping Hunt generates location scavenger hunts from street-level photos near the player, removing the need for a human author to design routes and clues. Its designers found that targets such as red doors or bins are too generic, so they now favour geometric features like corners, staircases and rooflines over colour. The system also flags areas where imagery is too sparse or unclear, rather than producing hunts that frustrate players. Because street imagery ages, the matching process accepts a range of similarity that widens for older photos. The team also found that confirmation messages should explain what the player matched, to make the game more instructive.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.



Discussion (0)
Log in to join the discussion and vote.
Log in