This project will determine the logistical and economic feasibility of developing an automatic detection system suitable for insect traps. Existing software will be adapted and tested to determine the suitability of digital shape and pattern recognition and hyperspectral signatures to differentiate between model species of fruit flies, moths and beetles. This project may lead to the development of insect traps incorporating miniature cameras and relay the information wirelessly to a web-based interface.

The expanded network of early-warning ‘smart traps' would link directly to key surveillance agencies and greatly enhance trapping efficiency. It would also maintain an inspector's alertness to the presence of an EPP by reducing the number of manual inspections. If successful, this project will increase capacity to safeguard Australia's plant industries.

What is the biosecurity problem?

Current biosecurity insect trapping programs in Australia use low-cost or disposable units which are inspected on a weekly or fortnightly basis, and re-lured or replaced monthly or quarterly. Inspectors visit trap sites and collect specimens, remove debris and non-target species from traps. Many inspectors never encounter target species. While that is a good thing, it also means many costly trips to trap sites.

The main output of this project is to:

• develop an improved trap design and other surveillance hardware using state-of-the-art sensor and communication/data transfer technology.

Who will be the end-users of this research?

The results will be used by federal and state agencies involved in broad-scale surveillance (especially NAQS, OCPPO, QDPI, NSWAG, PIRVIC, DPI TAS, SARDI, DAFWA, DBIRD NT).