Motion Blur Robust Wheat Pest Damage Detection with Dynamic Fuzzy Feature Fusion

2026-01-06

arXiv.org

AI Summary

This work addresses the challenge of motion blur in wheat pest and disease images, which degrades object boundaries and severely compromises detection accuracy, while existing methods struggle to balance structural fidelity and deployment efficiency. Building upon YOLOv11, we propose the Dynamic Blur-Robust Convolutional Pyramid (DFRCP), which integrates a dynamic robust switching unit and a transparent convolution mechanism to enable content-adaptive fusion of pristine and blurred features. An efficient CUDA kernel is further designed to accelerate blurred feature generation. Combined with dynamic blur synthesis, nonlinear interpolation, and rotation-based augmentation, our model achieves a 10.4% improvement in detection accuracy over the YOLOv11 baseline on blurred test sets, with manageable training overhead and significantly reduced reliance on manual data curation, thereby achieving an effective trade-off between accuracy and edge-deployment efficiency.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Motion blur caused by camera shake produces ghosting artifacts that substantially degrade edge side object detection. Existing approaches either suppress blur as noise and lose discriminative structure, or apply full image restoration that increases latency and limits deployment on resource constrained devices. We propose DFRCP, a Dynamic Fuzzy Robust Convolutional Pyramid, as a plug in upgrade to YOLOv11 for blur robust detection. DFRCP enhances the YOLOv11 feature pyramid by combining large scale and medium scale features while preserving native representations, and by introducing Dynamic Robust Switch units that adaptively inject fuzzy features to strengthen global perception under jitter. Fuzzy features are synthesized by rotating and nonlinearly interpolating multiscale features, then merged through a transparency convolution that learns a content adaptive trade off between original and fuzzy cues. We further develop a CUDA parallel rotation and interpolation kernel that avoids boundary overflow and delivers more than 400 times speedup, making the design practical for edge deployment. We train with paired supervision on a private wheat pest damage dataset of about 3,500 images, augmented threefold using two blur regimes, uniform image wide motion blur and bounding box confined rotational blur. On blurred test sets, YOLOv11 with DFRCP achieves about 10.4 percent higher accuracy than the YOLOv11 baseline with only a modest training time overhead, reducing the need for manual filtering after data collection.

Problem

• motion blur
• pest damage detection
• object detection
• edge devices
• image degradation

Innovation

• Dynamic Fuzzy Feature Fusion
• Motion Blur Robustness
• YOLOv11 Enhancement
• CUDA Parallel Kernel
• Edge Deployment