Specialized pest control for agriculture is a high-priority agricultural issue. There are multiple categories of tiny pests, which pose significant challenges to monitoring. Previous work mainly relied on manual monitoring of pests, which was labor-intensive and time-consuming. Recently, deep-learning-based pest detection methods have achieved remarkable improvements and can be used for automatic pest monitoring. However, there are two main obstacles in the task of pest detection. (1) Small pests often go undetected because much information is lost during the network training process. (2) The highly similar physical appearances of some categories of pests make it difficult to distinguish the specific categories for networks. To alleviate the above problems, we proposed the multi-category pest detection network (MCPD-net), which includes a multiscale feature pyramid network (MFPN) and a novel adaptive feature region proposal network (AFRPN). MFPN can fuse the pest information in multiscale features, which significantly improves detection accuracy. AFRPN solves the problem of anchor and feature misalignment during RPN iterating, especially for small pest objects. In extensive experiments on the multi-category pests dataset 2021 (MPD2021), the proposed method achieved 67.3% mean average precision (mAP) and 89.3% average recall (AR), outperforming other deep learning-based models.

It is well recognized that aphid infestation severely reduces crop yield and further leads to significant economic loss. Therefore, accurately and efficiently detecting aphids is of vital importance in pest management. However, most existing detection methods suffer from unsatisfactory performance without fully considering the aphid characteristics, including tiny size, dense distribution, and multi-viewpoint data quality. In addition, existing clustered tiny-sized pest detection methods improve performance at the cost of time and do not meet the real-time requirements. To address the aforementioned issues, we propose a robust aphid detection method with two customized core designs: a Transformer feature pyramid network (T-FPN) and a multi-resolution training method (MTM). To be specific, the T-FPN is employed to improve the feature extraction capability by a feature-wise Transformer module (FTM) and a channel-wise feature recalibration module (CFRM), while the MTM aims at purifying the performance and lifting the efficiency simultaneously with a coarse-to-fine training pattern. To fully demonstrate the validity of our methods, abundant experiments are conducted on a densely clustered tiny pest dataset. Our method can achieve an average recall of 46.1% and an average precision of 74.2%, which outperforms other state-of-the-art methods, including ATSS, Cascade R-CNN, FCOS, FoveaBox, and CRA-Net. The efficiency comparison shows that our method can achieve the fastest training speed and obtain 0.045 s per image testing time, meeting the real-time detection. In general, our TD-Det can accurately and efficiently detect in-field aphids and lays a solid foundation for automated aphid detection and ranking.

One of the main techniques in smart plant protection is pest detection using deep learning technology, which is convenient, cost-effective, and responsive. However, existing deep-learning-based methods can detect only over a dozen common types of bulk agricultural pests in structured environments. Also, such methods generally require large-scale well-labeled pest data sets for their base-class training and novel-class fine-tuning, and these significantly hinder the further promotion of deep convolutional neural network approaches in pest detection for economic crops, forestry, and emergent invasive pests. In this paper, a few-shot pest detection network is introduced to detect rarely collected pest species in natural scenarios. Firstly, a prior-knowledge auxiliary architecture for few-shot pest detection in the wild is presented. Secondly, a hierarchical few-shot pest detection data set has been built in the wild in China over the past few years. Thirdly, a pest ontology relation module is proposed to combine insect taxonomy and inter-image similarity information. Several experiments are presented according to a standard few-shot detection protocol, and the presented model achieves comparable performance to several representative few-shot detection algorithms in terms of both mean average precision (mAP) and mean average recall (mAR). The results show the promising effectiveness of the proposed few-shot detection architecture.