A novel 3D insect detection and monitoring system in plants based on deep learning

Nak Jung Choi; Kibon Ku; Sheikh Mansoor; Yong Suk Chung; Thai Thanh Tuan

doi:10.3389/fpls.2023.1236154

A novel 3D insect detection and monitoring system in plants based on deep learning

Front Plant Sci. 2023 Aug 31:14:1236154. doi: 10.3389/fpls.2023.1236154. eCollection 2023.

Authors

Nak Jung Choi¹, Kibon Ku², Sheikh Mansoor², Yong Suk Chung², Thai Thanh Tuan²

Affiliations

¹ Crop Foundation Division, National Institute of Crop Science, Rural Development Administration, Jeollabuk-do, Republic of Korea.
² Department of Plant Resources and Environment, Jeju National University, Jeju, Republic of Korea.

Abstract

Insects can have a significant impact on biodiversity, ecology, and the economy. Certain insects, such as aphids, caterpillars, and beetles, feed on plant tissues, including leaves, stems, and fruits. They can cause direct damage by chewing on the plant parts, resulting in holes, defoliation, or stunted growth. This can weaken the plant and affect its overall health and productivity. Therefore, the aim of this research was to develop a model system that can identify insects and track their behavior, movement, size, and habits. We successfully built a 3D monitoring system that can track insects over time, facilitating the exploration of their habits and interactions with plants and crops. This technique can assist researchers in comprehending insect behavior and ecology, and it can be beneficial for further research in these areas.

Keywords: 3D reconstruction; behavior analysis; habit exploration; insect; monitoring.

Grants and funding

This research was carried out with the support of “Cooperative Research Program for Agriculture Science & Technology Development (Development of an approach to analyze timing and locality of migratory pests occurrence for rice using information derived from an automated surveillance system: PJ01562001)” Rural Development Administration, Republic of Korea.