Transmitting large numbers of photos in a wireless environment with bandwidth constraints is challenging. In this project, the research team aims to develop a framework to quantify the quality of crowdsourced photos based on the accessible geographical and geometrical information (called metadata) including the smartphone's orientation, position and all related parameters of the built-in camera. From the metadata, information such as where and how the photo is taken can be inferred, and then only the most useful photos may be transmitted. Specifically, the project addresses three closely intertwined issues in resource-aware crowdsourcing. The first part investigates how to select photos based on the collected metadata by considering two scenarios: Point of Interest where the selected photos should be about a specific location or object, and Area of Interest where selected photos are related to an area. For both cases, various algorithms are designed to quantify the coverage of the photos based on the metadata, and then to select the minimum number of photos based on the coverage requirement, or to select a predefined number of photos to maximize the photo coverage. The second part focuses on metadata transmission and redundancy removal when crowdsourcing is based on peer-to-peer (P2P) communications. The third part investigates techniques to automatically and accurately generate metadata based on sensors available on most off-the-shelf smartphones.
The proposed research could potentially have substantial impacts on emergency responders and service providers by allowing them to identify the most useful information from crowdsourced photos under resource constraints. The results from this research are likely to foster new research directions on supporting resource-aware crowdsourcing in wireless networks. The project will engage under-represented students in the proposed research. The scholarly discovery of this project will be disseminated broadly to the community.
|Effective start/end date||10/1/14 → 9/30/18|
- National Science Foundation: $503,522.00