SGPS ‐ YOLO : A Novel Lightweight Object Detection Method for Complex Environments

ABSTRACT Object detection is an essential task in the domain of computer vision; however, its performance often deteriorates under adverse conditions such as low illumination and fog. To tackle these challenges, we propose SGPS‐YOLO, a lightweight and robust object detection framework built upon the YOLOv11 architecture. The proposed SharedPyramidConv module leverages dilated convolutions and shared kernel strategies to ensure multi‐scale semantic consistency while preserving fine‐grained spatial details. The designed GroupEfficientDetect module adopts a grouped convolutional architecture to effectively extract salient features from complex backgrounds while reducing computational overhead. Additionally, we incorporate the Powerful‐IoU loss function, which includes an adaptive penalty factor and gradient modulation mechanism to improve localization accuracy, and integrate the Shuffle Attention mechanism to enhance feature representation across scales. Results from experiments on the Complex VOC dataset demonstrate that SGPS‐YOLO achieves a 3.2% improvement in and a 4.2% boost in , while reducing the number of parameters by 9.4%, compared to YOLOv11s. Similar performance improvements and lightweight characteristics were also observed on the public datasets RTTS and ExDark.