Keywords: Web development, mobile computing, computer vision

- Review existing computer vision toolchains for insect detection and classification. - Implement a toolchain that runs locally in a browser operating on photos uploaded by the user or taken with a connected camera. - Evaluate speed on different hardware (desktop/laptop, smartphone, single-board computer) and optimise, if necessary. - Evaluate user experience and address issues, if necessary. - Optional: Well-documented open-source release. - Optional: Node.js implementation.

Reference: Kim Bjerge, Henrik Karstoft, Hjalte M.R. Mann, Toke T. Høye, A deep learning pipeline for time-lapse camera monitoring of insects and their floral environments, Ecological Informatics, Volume 84, 2024, 102861, ISSN 1574-9541, https://doi.org/10.1016/j.ecoinf.2024.102861. Note - this example is a pipeline for an edge device, not for a browser.