Multimedia for Mobile Environment: Image Enhanced Navigation Shantanu Gautam, Gabi Sarkis, Edwin Tjandranegara, Evan Zelkowitz, Yung-Hsiang Lu * , and Edward J. Delp School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana Abstract As mobile systems (such as laptops and mobile telephones) continue growing, navigation assistance and location-based services are becoming increasingly important. Existing technology allow mobile users to access Internet services (e.g. email and web surfing), simple multimedia services (e.g. music and video clips), and make telephone calls. However, the potential of advanced multimedia services has not been fully developed, especially multimedia for navigation or location based services. At Purdue University, we are developing an image database, known as LAID, in which every image is annotated with its location, compass heading, acquisition time, and weather conditions. LAID can be used to study several types of navigation problems: A mobile user can take an image and transmit the image to the LAID sever. The server compares the image with the images stored in the database to determine where the user is located. We refer to this as the “forward” navigation problem. The second type of problem is to provide a “virtual tour on demand.” A user inputs a starting and an ending addresses and LAID retrieves the images along a route that connects the two addresses. This is a generalization of route planning. Our database currently contains over 20000 images and covers approximately 25% of the city of West Lafayette, Indiana. keywords: multimedia, navigation, GPS, image processing 1 Introduction As world-wide travel continues growing, navigation assistance for mobile users becomes increasingly impor- tant. Concurrently, broadband wireless networks are being widely deployed. Existing technology can allow mobile users to check email, trade stocks, watch sports, or make phone calls. We believe the potential of multimedia has not been fully explored for mobile users, especially multimedia for navigation. We use two user scenarios to demonstrate how multimedia may help future travelers. In the first example, a family takes a road trip. As the vehicle is moving, they can preview the route. One of the family members says to the driver, “In one minute, we will see a gas station on the left.” “In two minutes, we will see Burger King on the right.” “You need to turn left when you see the second traffic light.” “We will see a shopping mall and I want to see which items are on sale.” Existing navigation technology is mostly map-based: users read maps and cannot see the route. Some studies have shown that maps are not intuitive to many people and people usually navigate based on direct visual cues, i.e., images. In the second example, an airline passenger uses the personal display to navigate the destination city. The passenger can see the route from the airport gate to the rental car company and from the company to the hotel. The passenger discovers several landmarks along the route. On the same airplane, another passenger wants to see a city that is not included in this trip. The passenger can select a city and drive-through the city virtually and see real images taken in the city. The two scenarios share three important common requirements. First, they need high-density (spatial) high-quality images to provide a realistic drive through experience. Second, they are personalized based on * Please address all questions to Yung-Hsiang Lu, yunglu@purdue.edu. Multimedia Content Analysis, Management, and Retrieval 2006, edited by Edward Y. Chang, Alan Hanjalic, Nicu Sebe, Proc. of SPIE-IS&T Electronic Imaging, SPIE Vol. 6073, 60730F, © 2006 SPIE-IS&T · 0277-786X/06/$15 SPIE-IS&T/ Vol. 6073 60730F-1