Method and device for detecting weeds in corn field based on improved YOLOv11

By improving the YOLOv11 network and combining the SimAM, AC_C3k2 modules and the DySample upsampling operator, a lightweight target detection network CW-YOLO was constructed, which solved the problems of low efficiency and high resource consumption in complex field weed detection, and achieved efficient and robust weed identification and detection.

CN120877066APending Publication Date: 2025-10-31XINJIANG AIR & EARTH INTEGRATION LABORATORY TECHNOLOGY CO LTD +1
0 Cites 2 Cited by

Patent Information

Application Number
CN202511023513.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-24
Publication Date
2025-10-31

AI Technical Summary

Technical Problem

Existing weed detection algorithms are inefficient and resource-intensive in complex field environments, making them difficult to deploy on edge computing hardware. They also suffer from issues such as missed detections, inaccurate bounding box regression, and category confusion.

Method used

The YOLOv11 network is improved by compressing its width and depth, introducing the parameterless spatial attention mechanism SimAM, designing the AC_C3k2 module, and introducing the DySample upsampling operator to construct a lightweight object detection network CW-YOLO, thereby enhancing the model's robustness and detection capabilities in complex environments.

Benefits of technology

While maintaining detection accuracy, the model significantly reduces complexity and computational resource requirements, improving detection efficiency and robustness in complex farmland scenarios, and is suitable for intelligent detection of agricultural weeds under low-resource equipment conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a corn field weed detection method and device based on improved YOLOv11, and the method comprises the steps: collecting a weed picture, marking with a LabelImg marking tool, and constructing a data set with various types of weeds; based on the weed data set, performing structure optimization on the YOLOv11 target detection network to obtain a first optimized network; integrating a parameter-free space attention mechanism SimAM module in the first optimization network to obtain a second optimization network; on the basis of the second optimization network, designing an ACC3k2 module, obtaining a third optimization network, and constructing a feature enhancement network; on the basis of the third optimized network, introducing a DySample up-sampling operator to obtain a fourth optimized network; and taking the fourth optimized network as a final lightweight weed detection network, and detecting weeds in the corn field based on the lightweight weed detection network. The device comprises a processor and a memory. According to the invention, a feasible path is provided for realizing agricultural field intelligent weeding, and a technical support is provided for promoting automatic, efficient and green development of agricultural production.
Need to check novelty before this filing date? Find Prior Art