This project will leverage advances in image processing and machine learning to develop new techniques for high throughput sampling of pollinator populations in crops.
The supervisory team for this project also includes Dr Chuong Nguyen (Data61) and Dr Sarina Macfadyen (CSIRO).
A complimentary scholarship for this project is available. To find out more, refer to the Postgraduate Research Stipend and Supplementary Scholarship in Digital Agriculture Data61.
School of Life and Environmental Sciences
PHD
Our goal is to produce an inexpensive system that would allow researchers and growers to automatically identify and quantify floral visitors. There are ~2200 species of native bee in Australia alone, and an estimated 30,000 species of fly, many of which are pollinators. Potential avenues for automated pollinator counting and identification include (but are not limited to) one or a combination of the following: acoustic cues from wing beat frequencies, using machine vision to classify images from camera traps, thermal imaging to identify pollinators by their heat signatures, use of scanning polarised LIDAR to detect species-specific wing beat frequencies, and/ or machine vision to identify pollinators from videos using species-specific flight patterns. Depending on collaborator/student interest, we can explore any or all of these potential techniques.
The supervisory team for this project also includes Dr Chuong Nguyen (Data61) and Dr Sarina Macfadyen (CSIRO).
A complimentary scholarship for this project is available. To find out more, refer to the Postgraduate Research Stipend and Supplementary Scholarship in Digital Agriculture Data61.
In addition to the academic requirements set out in the Science Postgraduate Handbook, you may be required to satisfy a number of inherent requirements to complete this degree. Example of inherent requirement may include:
The opportunity ID for this research opportunity is 2353