The intelligent pest-monitoring light trap based on machine vision employs specific light spectra to attract pests, infrared heating to eliminate pests, and artificial intelligence models to recognize and count them. Achieving optimal model performance requires a high-quality insect annotated dataset. However, traditional manual annotation is expert-dependent, time-consuming, and inefficient for large-scale multi-class insect labeling. This study establishes an efficient, few-shot learning approach to construct a large-scale light-trapped insect dataset through a two-stage annotation framework: detection followed by classification. Specifically, a MLTIDD addresses scale and receptive field disparities between large and tiny insects. Based on a fine-tuned Grounding DINO, SAM and SAHI are integrated to detect insects at multiple scales. Subsequently, InsectSSRL, an iBOT-based self-supervised method, learns robust insect feature representations from the extensive set of unlabeled insect sub-images detected by MLTIDD. It enhances feature extraction capability for insect sub-images through three proxy tasks. This feature extractor supports a classification model to pre-classify insect sub-images. Following expert correction, labels are traced back to original images to complete annotation work for the light-trapped insect dataset. Experimental results demonstrate that under limited samples, MLTIDD achieved 79.6% average precision (AP)_50–95 and 90.8% average recall (AR), surpassing DINO by 7.0 and 4.7 percentage points. InsectSSRL attained 85.87% top-1 accuracy in k-NN evaluation. In few-shot classification, Swin-T pre-trained with InsectSSRL and fine-tuned on 5% of InsectID achieved 80.35% accuracy, exceeding iBOT by 2.08 and COCO-based transfer learning by 11.3 percentage points. The proposed pipeline improved mAP_50–95 by 10.91 and AR by 8.26 percentage points compared to DINO and iBOT, while reducing expert annotation time by approximately 80% relative to manual labeling.

Cruciferous vegetables are important edible vegetable crops. However, they are susceptible to various pests during their growth process, which requires real-time and accurate monitoring of these pests for pest forecasting and scientific control. Hanging yellow sticky boards is a common way to monitor and trap those pests which are attracted to the yellow color. To achieve real-time, low-cost, intelligent monitoring of these vegetable pests on the boards, we established an intelligent monitoring system consisting of a smart camera, a web platform and a pest detection algorithm deployed on a server. After the operator sets the monitoring preset points and shooting time of the camera on the system platform, the camera in the field can automatically collect images of multiple yellow sticky boards at fixed places and times every day. The pests trapped on the yellow sticky boards in vegetable fields, Plutella xylostella, Phyllotreta striolata and flies, are very small and susceptible to deterioration and breakage, which increases the difficulty of model detection. To solve the problem of poor recognition due to the small size and breaking of the pest bodies, we propose an intelligent pest detection algorithm based on an improved Cascade R-CNN model for three important cruciferous crop pests. The algorithm uses an overlapping sliding window method, an improved Res2Net network as the backbone network, and a recursive feature pyramid network as the neck network. The results of field tests show that the algorithm achieves good detection results for the three target pests on the yellow sticky board images, with precision levels of 96.5, 92.2 and 75.0%, and recall levels of 96.6, 93.1 and 74.7%, respectively, and an F₁ value of 0.880. Compared with other algorithms, our algorithm has a significant advantage in its ability to detect small target pests. To accurately obtain the data for the newly added pests each day, a two-stage pest matching algorithm was proposed. The algorithm performed well and achieved results that were highly consistent with manual counting, with a mean error of only 2.2%. This intelligent monitoring system realizes precision, good visualization, and intelligent vegetable pest monitoring, which is of great significance as it provides an effective pest prevention and control option for farmers.

Agromyzid leafminers cause significant economic losses in both vegetable and horticultural crops, and precise assessments of pesticide needs must be based on the extent of leaf damage. Traditionally, surveyors estimate the damage by visually comparing the proportion of damaged to intact leaf area, a method that lacks objectivity, precision, and reliable data traceability. To address these issues, an advanced survey system that combines augmented reality (AR) glasses with a camera and an artificial intelligence (AI) algorithm was developed in this study to objectively and accurately assess leafminer damage in the field. By wearing AR glasses equipped with a voice-controlled camera, surveyors can easily flatten damaged leaves by hand and capture images for analysis. This method can provide a precise and reliable diagnosis of leafminer damage levels, which in turn supports the implementation of scientifically grounded and targeted pest management strategies. To calculate the leafminer damage level, the DeepLab-Leafminer model was proposed to precisely segment the leafminer-damaged regions and the intact leaf region. The integration of an edge-aware module and a Canny loss function into the DeepLabv3+model enhanced the DeepLab-Leafminer model's capability to accurately segment the edges of leafminer-damaged regions, which often exhibit irregular shapes. Compared with state-of-the-art segmentation models, the DeepLab-Leafminer model achieved superior segmentation performance with an Intersection over Union (IoU) of 81.23% and an F₁ score of 87.92% on leafminer-damaged leaves. The test results revealed a 92.38% diagnosis accuracy of leafminer damage levels based on the DeepLab-Leafminer model. A mobile application and a web platform were developed to assist surveyors in displaying the diagnostic results of leafminer damage levels. This system provides surveyors with an advanced, user-friendly, and accurate tool for assessing agromyzid leafminer damage in agricultural fields using wearable AR glasses and an AI model. This method can also be utilized to automatically diagnose pest and disease damage levels in other crops based on leaf images.