ASP-Det: Toward Appearance-Similar Light-Trap Agricultural Pest Detection and Recognition.

Automatic pest detection and recognition using computer vision techniques are a hot topic in modern intelligent agriculture but suffer from a serious challenge: difficulty distinguishing the targets of similar pests in 2D images. The appearance-similarity problem could be summarized into two aspects: texture similarity and scale similarity. In this paper, we re-consider the pest similarity problem and state a new task for the specific agricultural pest detection, namely Appearance Similarity Pest Detection (ASPD) task. Specifically, we propose two novel metrics to define the texture-similarity and scale-similarity problems quantitatively, namely Multi-Texton Histogram (MTH) and Object Relative Size (ORS). Following the new definition of ASPD, we build a task-specific dataset named PestNet-AS that is collected and re-annotated from PestNet dataset and also present a corresponding method ASP-Det. In detail, our ASP-Det is designed to solve the texture-similarity by proposing a Pairwise Self-Attention (PSA) mechanism and Non-Local Modules to construct a domain adaptive balanced feature module that could provide high-quality feature descriptors for accurate pest classification. We also present a Skip-Calibrated Convolution (SCC) module that can balance the scale variation among the pest objects and re-calibrate the feature maps into the sizing equivalent of pests. Finally, ASP-Det integrates the PSA-Non Local and SCC modules into a one-stage anchor-free detection framework with a center-ness localization mechanism. Experiments on PestNet-AS show that our ASP-Det could serve as a strong baseline for the ASPD task.

Automatic Crop Pest Detection Oriented Multiscale Feature Fusion Approach.

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.

Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection.

An accurate and robust pest detection and recognition scheme is an important step to enable the high quality and yield of agricultural products according to integrated pest management (IPM). Due to pose-variant, serious overlap, dense distribution, and interclass similarity of agricultural pests, the precise detection of multi-classes pest faces great challenges. In this study, an end-to-end pest detection algorithm has been proposed on the basis of deep convolutional neural networks. The detection method adopts a deformable residual network to extract pest features and a global context-aware module for obtaining region-of-interests of agricultural pests. The detection results of the proposed method are compared with the detection results of other state-of-the-art methods, for example, RetinaNet, YOLO, SSD, FPN, and Cascade RCNN modules. The experimental results show that our method can achieve an average accuracy of 77.8% on 21 categories of agricultural pests. The proposed detection algorithm can achieve 20.9 frames per second, which can satisfy real-time pest detection.

MSR-RCNN: A Multi-Class Crop Pest Detection Network Based on a Multi-Scale Super-Resolution Feature Enhancement Module.

Pest disaster severely reduces crop yield and recognizing them remains a challenging research topic. Existing methods have not fully considered the pest disaster characteristics including object distribution and position requirement, leading to unsatisfactory performance. To address this issue, we propose a robust pest detection network by two customized core designs: multi-scale super-resolution (MSR) feature enhancement module and Soft-IoU (SI) mechanism. The MSR (a plug-and-play module) is employed to improve the detection performance of small-size, multi-scale, and high-similarity pests. It enhances the feature expression ability by using a super-resolution component, a feature fusion mechanism, and a feature weighting mechanism. The SI aims to emphasize the position-based detection requirement by distinguishing the performance of different predictions with the same Intersection over Union (IoU). In addition, to prosper the development of agricultural pest detection, we contribute a large-scale light-trap pest dataset (named LLPD-26), which contains 26-class pests and 18,585 images with high-quality pest detection and classification annotations. Extensive experimental results over multi-class pests demonstrate that our proposed method achieves the best performance by 67.4% of mAP on the LLPD-26 while being 15.0 and 2.7% gain than state-of-the-art pest detection AF-RCNN and HGLA respectively. Ablation studies verify the effectiveness of the proposed components.

Prior knowledge auxiliary for few-shot pest detection in the wild.

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.

ZmCCA1a on Chromosome 10 of Maize Delays Flowering of Arabidopsis thaliana.

Maize (Zea mays) is a major cereal crop that originated at low latitudes, and thus photoperiod sensitivity is an important barrier to the use of tropical/subtropical germplasm in temperate regions. However, studies of the mechanisms underlying circadian regulation in maize are at an early stage. In this study we cloned ZmCCA1a on chromosome 10 of maize by map-based cloning. The gene is homologous to the Myb transcription factor genes AtCCA1/AtLHY in Arabidopsis thaliana; the deduced Myb domain of ZmCCA1a showed high similarity with that of AtCCA1/AtLHY and ZmCCA1b. Transiently or constitutively expressed ZmCCA1a-YFPs were localized to nuclei of Arabidopsis mesophyll protoplasts, agroinfiltrated tobacco leaves, and leaf and root cells of transgenic seedlings of Arabidopsis thaliana. Unlike AtCCA1/AtLHY, ZmCCA1a did not form homodimers nor interact with ZmCCA1b. Transcripts of ZmCCA1a showed circadian rhythm with peak expression around sunrise in maize inbred lines CML288 (photoperiod sensitive) and Huangzao 4 (HZ4; photoperiod insensitive). Under short days, transcription of ZmCCA1a in CML288 and HZ4 was repressed compared with that under long days, whereas the effect of photoperiod on ZmCCA1a expression was moderate in HZ4. In ZmCCA1a-overexpressing A. thaliana (ZmCCA1a-ox) lines, the circadian rhythm was disrupted under constant light and flowering was delayed under long days, but the hypocotyl length was not affected. In addition, expression of endogenous AtCCA1/AtLHY and the downstream genes AtGI, AtCO, and AtFt was repressed in ZmCCA1a-ox seedlings. The present results suggest that the function of ZmCCA1a is similar, at least in part, to that of AtCCA1/AtLHY and ZmCCA1b, implying that ZmCCA1a is likely to be an important component of the circadian clock pathway in maize.

[Identification and characterization of epidermal growth factor receptor ligands in Bombyx mori].

Epidermal growth factor receptor (EGFR) is a multi-functional receptor distributed throughout the metazoa. Study on its ligands so far remained mainly on mammals, including how ligands are processed into active forms, their interaction with EGFR, and the signaling pathway they induce. However, in invertebrates, ligands are more divergent among species. Currently, except for Drosophila, less is known about the insect EGFR ligands. Here, we identified two EGFR ligands in Bombyx mori by homology search, domain prediction, analysis of the potential translation initiation sequence and construction of phylogenetic tree, termed as BmEGF-1 and BmEGF-2. BmEGF-1 shows the greatest similarity to Drosophila Spitz and their Rhomboid-recognition motifs are highly identical. BmEGF-2 is a homolog to Drosophila Vein. Then we purified BmEGF-1 extracellular domain expressed in E. coli, and performed pull-down assay with BmEGFR extracellular domain secreted by Sf9 cells. The result confirmed their interaction. Lastly, we found the phosphorylation level of ERK and p38 MAPK was elevated after expression of BmEGF-1 in BmE cells, which suggested that BmEGF-1 is not only able to activate the canonical ERK signaling pathway, but may participate in other cellular processes by inducing p38 MAPK signaling pathway. Our study provides reference to further study of the biological function of BmEGF in silkworm.

A Fas associated factor negatively regulates anti-bacterial immunity by promoting Relish degradation in Bombyx mori.

Negative regulation is required to keep NF-κB-dependent immune response under tight control. In previous study, we have identified a Fas associated factor (FAF) family member in Bombyx mori, BmFAF, and proposed it may act as a negative regulator in immune response. In this study, we found knock-down of BmFAF by RNAi led to a remarkable increase in transcriptional level of several antimicrobial peptide genes, including BmCecropinA1 and BmMoricin, and higher survival rate to Gram-negative bacterial infection. We also confirmed the regulatory role of BmFAF in suppressing NF-κB-dependent transcription by employing an inducible promoter in BmE cells. Consistent with these physiological phenotypes, BmFAF suppressed the activity of the essential transcription factor, Relish, in IMD signaling pathway by promoting its proteasomal degradation through direct interaction. In addition, by constructing various truncation mutants, we further demonstrated that UBA domain in BmFAF is required for the inhibitory role, and potential ubiquitination also occurs in this domain. Taken together, our results suggest that BmFAF is a negative regulator of IMD pathway by mediating degradation of Relish.

Paralytic peptide activates insect humoral immune response via epidermal growth factor receptor.

Paralytic peptide (PP) activates innate immunity of silkworm Bombyx mori, inducing production of anti-microbial peptides (AMPs) and phagocytosis-related proteins; however the signal pathways of PP-dependent immune responses are not clear. In present study, we characterized BmE cells as a PP-responsive cell line by examining the expression of AMP genes and activation of p38 mitogen-activated protein kinase (p38 MAPK) under PP stimulation, and we also found PP directly binds to BmE cell membrane. Then we found that PP-dependent expression of AMP genes is suppressed by tyrosine kinase inhibitor (genistein) both in BmE cells and in fat body of silkworm larvae. Moreover, the specific tyrosine kinase epidermal growth factor receptor (EGFR) inhibitor (AG1478) attenuates PP-induced expression of AMP genes in BmE cells and fat body of silkworm and RNA interference (RNAi) to BmEGFR also suppresses PP-induced expression of AMP genes. Furthermore, the PP-induced p38 MAPK phosphorylation is inhibited by AG1478. Our results suggest that BmE cells can be used as a cell model to investigate the signal pathway of PP-dependent humoral immune response and receptor tyrosine kinase EGFR/p38 MAPK pathway is involved in the production of AMPs induced by PP.