MRLCM-YOLO: A lightweight and multi scale enhanced model for detecting cowpea pests in complex field environments

• Proposes MRLCM-YOLO, a lightweight and high-precision pest detection model tailored for complex field environments. • Constructs a multi-class small-object cowpea pest dataset covering 19 common pest species with detailed annotations. • Enhances feature extraction and detection robustness using RepViT backbone and CGRFPN context-aware fusion module. • Achieves superior balance between detection performance and model size, enabling efficient deployment on edge devices. Insect pests significantly threaten both the yield and quality of crops, particularly in high value varieties such as cowpeas. To address key challenges including dense small object detection, complex and cluttered field environments, class imbalance, and limitations in deployment resources, this study introduces a lightweight yet high accuracy object detection model MRLCM-YOLO based on the YOLOv11 framework. The model incorporates RepViT, a reparameterized vision transformer as its backbone, to enhance both feature expressiveness and inference speed. To improve multi scale contextual representation, a novel feature fusion mechanism termed CGRFPN is proposed. Additionally, the LSKM module, based on large separable kernel attention, is employed to strengthen attention on target regions. A decoupled detection head, MultiSEAMHead, is further integrated to enhance model robustness by disentangling the classification and localization tasks. For training and validation purposes, a high-resolution cowpea pest dataset was curated, comprising 3,855 annotated images spanning 19 pest categories. Experimental findings demonstrate that MRLCM-YOLO achieves 87.9% mAP 50 and 57.2% mAP 50–95 , representing gains of 0.5% and 0.9%, respectively, over YOLOv11. With a model size of just 9.1 million parameters, MRLCM-YOLO achieves an effective trade-off between detection performance and computational cost, rendering it particularly well suited for deployment in practical agricultural scenarios.