Fenqi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fenqi Zhang has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Guangling Sun
School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
DRSE‐YOLO: Efficient and Lightweight Architecture for Accurate Waste Detection
This paper introduces DRSE‐YOLO, an efficient waste detection model designed to address detection accuracy and lightweight design challenges. The RCCA module in the model's neck enhances multi‐scale feature representation, thereby improving detection performance. The DySample module optimizes upsampling through adaptive point‐sampling, reducing computational demands and improving resource efficiency. The Slim‐Neck module is applied to select convolutional layers and C2f modules to streamline the model and enhance computational efficiency. The ECC‐Head integrates asymmetric depth convolution, point convolution, and an attention mechanism, balancing accuracy with reduced parameters and computational load. Evaluated on a custom dataset comprising 46 waste classes and approximately 25,000 images, DRSE‐YOLO achieves significant improvements over YOLOv8n, including a higher mAP@0.5 (+1.59%) and mAP@0.5:95 (+2.08%), alongside a reduced parameter count (2.43 M vs. 3.2 M) and GFLOPs (5.8 vs. 8.2, a 24.4% reduction). These results underscore DRSE‐YOLO's efficiency and accuracy.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessDRSE‐YOLO: Efficient and Lightweight Architecture for Accurate Waste Detection
This paper introduces DRSE‐YOLO, an efficient waste detection model designed to address detection accuracy and lightweight design challenges. The RCCA module in the model's neck enhances multi‐scale feature representation, thereby improving detection performance. The DySample module optimizes upsampling through adaptive point‐sampling, reducing computational demands and improving resource efficiency. The Slim‐Neck module is applied to select convolutional layers and C2f modules to streamline the model and enhance computational efficiency. The ECC‐Head integrates asymmetric depth convolution, point convolution, and an attention mechanism, balancing accuracy with reduced parameters and computational load. Evaluated on a custom dataset comprising 46 waste classes and approximately 25,000 images, DRSE‐YOLO achieves significant improvements over YOLOv8n, including a higher mAP@0.5 (+1.59%) and mAP@0.5:95 (+2.08%), alongside a reduced parameter count (2.43 M vs. 3.2 M) and GFLOPs (5.8 vs. 8.2, a 24.4% reduction). These results underscore DRSE‐YOLO's efficiency and accuracy.