Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models

TL;DR

This paper presents a deep learning-based method for detecting aphid clusters in crop fields, introducing a large annotated dataset and comparing multiple models to improve pest detection accuracy for targeted pest management.

Contribution

The study introduces a novel large-scale aphid dataset, evaluates four state-of-the-art detection models, and proposes a clustering refinement method to enhance detection performance.

Findings

Models achieved similar average precision and recall.

Clustering refinement improved performance by around 17%.

The dataset will be publicly available for research.

Abstract

Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying chemicals across entire fields is both environmentally unsustainable and costly. Hence, precise localization and management of aphids are essential for targeted pesticide application. The paper primarily focuses on using deep learning models for detecting aphid clusters. We propose a novel approach for estimating infection levels by detecting aphid clusters. To facilitate this research, we have captured a large-scale dataset from sorghum fields, manually selected 5,447 images containing aphids, and annotated each individual aphid cluster within these images. To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151,380 image patches. Then, we implemented and compared the performance of four state-of-the-art object detection models (VFNet, GFLV2, PAA, and ATSS) on the aphid dataset. Extensive experimental results show that all models yield stable similar performance in terms of average precision and recall. We then propose to merge close neighboring clusters and remove tiny clusters caused by cropping, and the performance is further boosted by around 17%. The study demonstrates the feasibility of automatically detecting and managing insects using machine learning models. The labeled dataset will be made openly available to the research community.