Supporting the annual international black-faced spoonbill census with a low-cost unmanned aerial vehicle

The black-faced spoonbill (BFS) is a globally endangered species. The annual international BFS census (IBFSC) thus serves as an important initiative to manage and protect the population of this bird. This work attempts to investigate the feasibility of supporting the annual IBFSC with a low-cost unmanned aerial vehicle system (UAVS). A total of six missions were completed to investigate various locations and areas from November 2012 to April 2013, when BFS transited at Taijiang National Park. The flight plan for each mission was made through the automatic mission planning system. All photographs taken in one mission were stitched to a seamless and color-balanced mosaic that can be geo-referenced and displayed on a Web-based platform, such as Google Earth. A close-up photograph of a few BFSs was acquired at a low altitude of 50 m to validate the proposed approach of image processing, including unsupervised classification, hit or miss transform and binary large object analysis. The results show that the selection of one statistical attribute (maximum value in red channel) and two geometrical attributes (size and circularity) is appropriate for identifying BFS without ambiguity. The success of this work encourages us to conduct a large-scale deployment of UAVS in the coming IBFSC.