Description

Due to the existence of many useful applications, people are sharing billions of photos taken by smartphones. Photos are often geographically correlated and this correlation can be used to enrich traditional map experience. However, the sheer amount of photos poses big challenges for image processing and storage at the server end. Due to the limitations of communication bandwidth, storage, and processing capability, it is a challenge to transfer the huge amount of crowd sourced photos. In image sensing four optimization problems regarding the trade-offs between photo utility and resource constraints, namely Max-Utility, online Max-Utility, Min-Selection, and Min-Selection with k-coverage. To address this problem, we propose a framework, called Smart Photo, to quantify the quality (utility) of crowd sourced photos based on the accessible geographical and geometrical information. We use Greedy algorithm can be used to find a solution. It works as a multi-round selection process. In each round, the weighted contribution (utility) of every unselected photos is calculated. The photo with the most contribution to the total utility is selected.