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

TL;DR

This paper introduces DFRCP, a novel feature fusion method enhancing YOLOv11 for motion blur robust pest detection, achieving higher accuracy on blurred images with efficient processing suitable for edge devices.

Contribution

The paper proposes DFRCP, a dynamic fuzzy feature fusion module that improves object detection under motion blur by adaptively combining features and accelerating processing with CUDA kernels.

Findings

Achieves 10.4% higher accuracy on blurred test sets.

Provides over 400x speedup with CUDA implementation.

Effective on a private wheat pest dataset with motion blur.

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.