Urban floods have become a constant threat to human life and property. Also, high resolution cameras in smart phones have become ubiquitous. This work involves using Computer Vision algorithms to estimate the depth of flooding based on images taken by the general public which are geo-tagged and time-stamped. This approach will help in the implementation of effective and timely urban flood relief and management. This data can also be used to assess the effectiveness of preventive measures taken in the past and to plan remedial measures in the future.