Interactive Image-Based Aphid Counting in Yellow Water Traps under Stirring Actions

TL;DR

This paper introduces an interactive stirring approach combined with an optimized Yolov5-based detection network and a confidence evaluation system to improve aphid counting accuracy in water traps, addressing occlusion issues.

Contribution

It presents a novel interactive stirring method and a confidence-based counting system that significantly enhance aphid detection and counting accuracy over existing static methods.

Findings

Detection performance improved by 33.9% in AP@0.5

Counting accuracy closely matches manual counts

Proposed method outperforms static counting approaches

Abstract

The current vision-based aphid counting methods in water traps suffer from undercounts caused by occlusions and low visibility arising from dense aggregation of insects and other objects. To address this problem, we propose a novel aphid counting method through interactive stirring actions. We use interactive stirring to alter the distribution of aphids in the yellow water trap and capture a sequence of images which are then used for aphid detection and counting through an optimized small object detection network based on Yolov5. We also propose a counting confidence evaluation system to evaluate the confidence of count-ing results. The final counting result is a weighted sum of the counting results from all sequence images based on the counting confidence. Experimental results show that our proposed aphid detection network significantly outperforms the original Yolov5, with improvements of 33.9% in AP@0.5 and 26.9% in AP@[0.5:0.95] on the aphid test set. In addition, the aphid counting test results using our proposed counting confidence evaluation system show significant improvements over the static counting method, closely aligning with manual counting results.