Version 1
: Received: 30 April 2024 / Approved: 30 April 2024 / Online: 1 May 2024 (04:22:08 CEST)
How to cite:
Lyu, Z.; Lu, A.; Ma, Y. Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Preprints2024, 2024050018. https://doi.org/10.20944/preprints202405.0018.v1
Lyu, Z.; Lu, A.; Ma, Y. Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Preprints 2024, 2024050018. https://doi.org/10.20944/preprints202405.0018.v1
Lyu, Z.; Lu, A.; Ma, Y. Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Preprints2024, 2024050018. https://doi.org/10.20944/preprints202405.0018.v1
APA Style
Lyu, Z., Lu, A., & Ma, Y. (2024). Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation. Preprints. https://doi.org/10.20944/preprints202405.0018.v1
Chicago/Turabian Style
Lyu, Z., Anjiang Lu and Yinglong Ma. 2024 "Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation" Preprints. https://doi.org/10.20944/preprints202405.0018.v1
Abstract
Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
