A user points a handheld communication device to capture and display a real-time video stream. The handheld communication device detects geographic position, camera direction, and tilt of the image capture device. The user sends a search request to a server for nearby points of interest. The handheld communication device receives search results based on the search request, geographic position, camera direction, and tilt of the handheld communication device. The handheld communication device visually augments the captured video stream with data related to each point of interest. The user then selects a point of interest to visit. The handheld communication device visually augments the captured video stream with a directional map to a selected point of interest in response to the user input.