Bo Ma

Accurate monitoring of orchard pests is vital for green and efficient apple production. Yet images captured by intelligent pest-monitoring lamps often contain small targets, weak boundaries, and crowded scenes, which hamper detection accuracy. We present MDAS-YOLO, a lightweight detection framework tailored for smart pest monitoring in apple orchards. At the input stage, we adopt the LIME++ enhancement to mitigate low illumination and non-uniform lighting, improving image quality at the source. On the model side, we integrate three structural innovations: (1) a C3k2-MESA-DSM module in the backbone to explicitly strengthen contours and fine textures via multi-scale edge enhancement and dual-domain feature selection; (2) an AP-BiFPN in the neck to achieve adaptive cross-scale fusion through learnable weighting and differentiated pooling; and (3) a SimAM block before the detection head to perform zero-parameter, pixel-level saliency re-calibration, suppressing background redundancy without extra computation. On a self-built apple-orchard pest dataset, MDAS-YOLO attains 95.68% mAP, outperforming YOLOv11n by 6.97 percentage points while maintaining a superior trade-off among accuracy, model size, and inference speed. Overall, the proposed synergistic pipeline—input enhancement, early edge fidelity, mid-level adaptive fusion, and end-stage lightweight re-calibration—effectively addresses small-scale, weak-boundary, and densely distributed pests, providing a promising and regionally validated approach for intelligent pest monitoring and sustainable orchard management, and offering methodological insights for future multi-regional pest monitoring research.

Accurate detection of Jinxiu Malus fruits in unstructured orchard environments is hampered by frequent overlap, occlusion, and variable illumination. To address these challenges, we propose YOLOv8-MSP-PD (YOLOv8 with Multi-Scale Pyramid Fusion and Proportional Distance IoU), a lightweight model built on an enhanced YOLOv8 architecture. We replace the backbone with MobileNetV4, incorporating unified inverted bottleneck (UIB) modules and depth-wise separable convolutions for efficient feature extraction. We introduce a spatial pyramid pooling fast cross-stage partial connections (SPPFCSPC) module for multi-scale feature fusion and a modified proportional distance IoU (MPD-IoU) loss to optimize bounding-box regression. Finally, layer-adaptive magnitude pruning (LAMP) combined with knowledge distillation compresses the model while retaining performance. On our custom Jinxiu Malus dataset, YOLOv8-MSP-PD achieves a mean average precision (mAP) of 92.2% (1.6% gain over baseline), reduces floating-point operations (FLOPs) by 59.9%, and shrinks to 2.2 MB. Five-fold cross-validation confirms stability, and comparisons with Faster R-CNN and SSD demonstrate superior accuracy and efficiency. This work offers a practical vision solution for agricultural robots and guidance for lightweight detection in precision agriculture.

Currently, intelligent pest monitoring systems transmit entire monitoring images to cloud servers for analysis. This approach not only consumes significant bandwidth and increases monitoring costs, but also struggles with accurately recognizing small-target and overlapping pests. To overcome these challenges, this paper introduces a two-stage multi-feature fusion small-target pest detection algorithm based on edge computing devices, termed TFEMRNet. The algorithm initially conducts semantic segmentation on an edge processor, followed by uploading the segmented images to a cloud server for target identification. Specifically, the semantic segmentation model TFENet incorporates a Multi-Attention Channel Aggregation (MACA) module, which integrates semantic features from EfficientNet-Pest and Swin Transformer, thereby enhancing the model’s ability to extract features of small-target pests. Experimental results demonstrate that TFEMRNet surpasses models such as YOLOv11, Fast R-CNN, and Mask R-CNN on small-target pest datasets, achieving precision of 96.75%, recall of 96.45%, and an F1 score of 95.60%. Notably, the TFENet model within TFEMRNet attains an IoU of 91.63% in semantic segmentation accuracy, outperforming other segmentation models such as U-Net and PSPNet. These findings affirm TFEMRNet’s superior efficacy in small-target pest detection, offering an effective solution for agricultural pest monitoring.