What type of study is this?

This is a In Vitro Study study.

August 21, 2025Open Access

Fast real-time detection and counting of thrips in greenhouses with multi-level feature attention and fusion

ZHZhangzhang HeJingchu University of Technology XCXinyue ChenUniversity of Florida Health YGYing GaoTongji University

Key Points

TCD-Net achieves an F1 score of 85.67% for thrips detection, highlighting its efficacy in real-time monitoring.
The model utilizes a lightweight backbone network with optimized convolution layers, reducing computational complexity while maintaining performance.
Through a hybrid attention mechanism, TCD-Net enhances global and local feature extraction, essential for tiny pest detection.
Publicly available dataset with over 47K thrips annotations supports further research and improvement in pest monitoring techniques.

Abstract

Thrips can damage over 200 species across 62 plant families, causing significant economic losses worldwide. Their tiny size, rapid reproduction, and wide host range make them prone to outbreaks, necessitating precise and efficient population monitoring methods. Existing intelligent counting methods lack effective solutions for tiny pests like thrips. In this work, we propose the Thrip Counting and Detection Network (TCD-Net). TCD-Net is an fully convolutional network consisting of a backbone network, a feature pyramid, and an output head. First, we propose a lightweight backbone network, PartialNeXt, which optimizes convolution layers through Partial Convolution (PConv), ensuring both network performance and reduced complexity. Next, we design a lightweight channel-spatial hybrid attention mechanism to further refine multi-scale features, enhancing the model’s ability to extract global and local features with minimal computational cost. Finally, we introduce the Adaptive Feature Mixer Feature Pyramid Network (AFM-FPN), where the Adaptive Feature Mixer (AFM) replaces the traditional element-wise addition at the P level, enhancing the model’s ability to select and retain thrips features, improving detection performance for extremely small objects. The model is trained with the Object Counting Loss (OC Loss) specifically designed for the detection of tiny pests, allowing the network to predict a small spot region for each thrips, enabling real-time and precise counting and detection. We collected a dataset containing over 47K thrips annotations to evaluate the model’s performance. The results show that TCD-Net achieves an F1 score of 85. 67%, with a counting result correlation of 75. 50%. The model size is only 21. 13M, with a computational cost of 114. 36 GFLOPs. Compared to existing methods, TCD-Net achieves higher thrips counting and detection accuracy with lower computational complexity. The dataset is publicly available at github. com/ZZL0897/thripₗeafdataset.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper