On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild

TL;DR

This paper develops and benchmarks real-time semantic segmentation models to detect aphid clusters in crop fields, aiming to enable autonomous pest control and reduce pesticide waste.

Contribution

It introduces a large field-collected aphid dataset and compares four state-of-the-art real-time segmentation models for effective pest detection.

Findings

Real-time models achieve high segmentation accuracy.

Benchmarking shows trade-offs between speed and accuracy.

Potential to reduce pesticide use and improve crop yields.

Abstract

Aphid infestations can cause extensive damage to wheat and sorghum fields and spread plant viruses, resulting in significant yield losses in agriculture. To address this issue, farmers often rely on chemical pesticides, which are inefficiently applied over large areas of fields. As a result, a considerable amount of pesticide is wasted on areas without pests, while inadequate amounts are applied to areas with severe infestations. The paper focuses on the urgent need for an intelligent autonomous system that can locate and spray infestations within complex crop canopies, reducing pesticide use and environmental impact. We have collected and labeled a large aphid image dataset in the field, and propose the use of real-time semantic segmentation models to segment clusters of aphids. A multiscale dataset is generated to allow for learning the clusters at different scales. We compare the segmentation speeds and accuracy of four state-of-the-art real-time semantic segmentation models on the aphid cluster dataset, benchmarking them against nonreal-time models. The study results show the effectiveness of a real-time solution, which can reduce inefficient pesticide use and increase crop yields, paving the way towards an autonomous pest detection system.